概述
CVPR 2019 追踪之论文纲要（修正于2020.08.28）
- 讲在前面
- 论文目录
讲在前面
- 论坛很多博客都对论文做了总结和分类，但就医学领域而言，对这些论文的筛选信息显然需要更加精细的把控，所以自己对这900篇的论文做一个大致从名称上的筛选，希望能找到些能解决当前问题的答案。
- 论文链接建议直接Google论文名，比去各种论文或顶会网站找不知道快捷多少。
- 下面皆为机器翻译，我会慢慢修正，但现在请结合。有兴趣的可以问我要处理这些论文并自动翻译的脚本。
- Respect！
论文目录
| 论文 | 概要 |
|---|---|
| 1.3D Appearance Super-Resolution With Deep Learning 深度学习的3D外观超高分辨率 | |
| 2.3D Guided Fine-Grained Face Manipulation 3D引导的细纹面部操纵 | |
| 3.3D Hand Shape and Pose From Images in the Wild 野外图像中的3D手形和姿势 | |
| 4.3D Human Pose Estimation in Video With Temporal Convolutions and Semi-Supervised Training 具有时间卷积和半监督训练的视频中的3D人姿估计 | |
| 5.3D Local Features for Direct Pairwise Registration 直接成对注册的3D局部特征 | |
| 6.3D Motion Decomposition for RGBD Future Dynamic Scene Synthesis RGBD未来动态场景合成的3D运动分解 | |
| 7.3D-SIS_ 3D Semantic Instance Segmentation of RGB-D Scans RGB-D扫描的3D-SIS_ 3D语义实例分割 | |
| 8.4D Spatio-Temporal ConvNets_ Minkowski Convolutional Neural Networks 4D时空卷积网络_ Minkowski卷积神经网络 | |
| 9.A Bayesian Perspective on the Deep Image Prior 关于深度图像先验的贝叶斯视角 | |
| 10.ABC_ A Big CAD Model Dataset for Geometric Deep Learning ABC_用于几何深度学习的大型CAD模型数据集 | |
| 11.Accel_ A Corrective Fusion Network for Efficient Semantic Segmentation on Video Accel_用于视频上有效语义分割的校正融合网络 | |
| 12.Accelerating Convolutional Neural Networks via Activation Map Compression 通过激活图压缩来加速卷积神经网络 | |
| 13.A-CNN_ Annularly Convolutional Neural Networks on Point Clouds 点云上的A-CNN_环状卷积神经网络 | |
| 14.A Compact Embedding for Facial Expression Similarity 面部表情相似性的紧凑嵌入 | |
| 15.A Convex Relaxation for Multi-Graph Matching 多图匹配的凸松弛 | |
| 16.Acoustic Non-Line-Of-Sight Imaging 声学非视线成像 | |
| 17.A Cross-Season Correspondence Dataset for Robust Semantic Segmentation 用于稳健语义分割的跨季节对应数据集 | |
| 18.Action4D_ Online Action Recognition in the Crowd and Clutter Action4D_人群和杂物中的在线动作识别 | |
| 19.Action Recognition From Single Timestamp Supervision in Untrimmed Videos 未修饰视频中单个时间戳监督的动作识别 | |
| 20.Actively Seeking and Learning From Live Data 积极寻找和学习实时数据 | |
| 21.Activity Driven Weakly Supervised Object Detection 活动驱动的弱监督对象检测 | |
| 22.Actor-Critic Instance Segmentation 演员关键实例分割 | |
| 23.AdaCos_ Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations AdaCos_自适应缩放余弦Logits以有效学习深脸表示 | |
| 24.AdaFrame_ Adaptive Frame Selection for Fast Video Recognition AdaFrame_用于快速视频识别的自适应帧选择 | |
| 25.AdaGraph_ Unifying Predictive and Continuous Domain Adaptation Through Graphs AdaGraph_通过图统一预测性和连续域自适应 | |
| 26.Adapting Object Detectors via Selective Cross-Domain Alignment 通过选择性的跨域对齐调整目标检测器 | |
| 27.Adaptive Confidence Smoothing for Generalized Zero-Shot Learning 广义零射学习的自适应置信平滑 | |
| 28.AdaptiveFace_ Adaptive Margin and Sampling for Face Recognition AdaptiveFace_用于人脸识别的自适应余量和采样 | |
| 29.Adaptive NMS_ Refining Pedestrian Detection in a Crowd 自适应NMS_完善人群中的行人检测 | |
| 30.Adaptive Pyramid Context Network for Semantic Segmentation 自适应金字塔上下文网络的语义分割 | |
| 31.Adaptive Transfer Network for Cross-Domain Person Re-Identification 跨域人员重新识别的自适应传输网络 | |
| 32.Adaptive Weighting Multi-Field-Of-View CNN for Semantic Segmentation in Pathology 自适应加权多视野CNN用于病理学中的语义分割 | |
| 33.A Dataset and Benchmark for Large-Scale Multi-Modal Face Anti-Spoofing 大规模多模式人脸反欺骗的数据集和基准 | |
| 34.Additive Adversarial Learning for Unbiased Authentication 无偏认证的加性对抗学习 | |
| 35.A Decomposition Algorithm for the Sparse Generalized Eigenvalue Problem 稀疏广义特征值问题的分解算法 | |
| 36.ADVENT_ Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation ADVENT_语义分割中域自适应的对抗熵最小化 | |
| 37.Adversarial Attacks Beyond the Image Space 超越图像空间的对抗性攻击 | |
| 38.Adversarial Defense by Stratified Convolutional Sparse Coding 分层卷积稀疏编码的对抗防御 | |
| 39.Adversarial Defense Through Network Profiling Based Path Extraction 通过基于网络分析的路径提取进行对抗性防御 | |
| 40.Adversarial Semantic Alignment for Improved Image Captions 对抗性语义对齐，可改善图像字幕 | |
| 41.Adversarial Structure Matching for Structured Prediction Tasks 结构化预测任务的对抗结构匹配 | |
| 42.AE2-Nets_ Autoencoder in Autoencoder Networks AE2-Nets_自动编码器网络中的自动编码器 | |
| 43.AET vs. AED_ Unsupervised Representation Learning by Auto-Encoding Transformations Rather Than Data AET与AED_通过自动编码转换而不是数据进行无监督表示学习 | |
| 44.A General and Adaptive Robust Loss Function 通用自适应鲁棒损失函数 | |
| 45.A Generative Adversarial Density Estimator 生成对抗性密度估计器 | |
| 46.A Generative Appearance Model for End-To-End Video Object Segmentation 端到端视频对象分割的生成外观模型 | |
| 47.Aggregation Cross-Entropy for Sequence Recognition 聚合交叉熵用于序列识别 | |
| 48.AIRD_ Adversarial Learning Framework for Image Repurposing Detection AIRD_图像重用检测的对抗学习框架 | |
| 49.A Kernelized Manifold Mapping to Diminish the Effect of Adversarial Perturbations 核化的流形映射以减少对抗性扰动的影响 | |
| 50.All About Structure_ Adapting Structural Information Across Domains for Boosting Semantic Segmentation 关于结构的全部信息_跨域适应结构信息以促进语义分割 |
| 论文 | 概要 |
|---|---|
| 51.All-Weather Deep Outdoor Lighting Estimation 全天候深室外照明估算 | |
| 52.All You Need Is a Few Shifts_ Designing Efficient Convolutional Neural Networks for Image Classification 您需要做的只是几项转变_设计用于图像分类的高效卷积神经网络 | |
| 53.A Local Block Coordinate Descent Algorithm for the CSC Model CSC模型的局部块坐标下降算法 | |
| 54.Amodal Instance Segmentation With KINS Dataset 使用KINS数据集的非模式实例细分 | |
| 55.An Alternative Deep Feature Approach to Line Level Keyword Spotting 线级关键字发现的另一种深度特征方法 | |
| 56.Analysis of Feature Visibility in Non-Line-Of-Sight Measurements 非视距测量中的特征可见性分析 | |
| 57.An Efficient Schmidt-EKF for 3D Visual-Inertial SLAM 适用于3D视觉惯性SLAM的高效Schmidt-EKF | |
| 58.An End-To-End Network for Panoptic Segmentation 全景分割的端到端网络 | |
| 59.A Neural Network Based on SPD Manifold Learning for Skeleton-Based Hand Gesture Recognition 基于SPD流形学习的神经网络基于骨骼的手势识别 | |
| 60.A Neural Temporal Model for Human Motion Prediction 人体运动预测的神经时间模型 | |
| 61.A Neurobiological Evaluation Metric for Neural Network Model Search 神经网络模型搜索的神经生物学评估指标 | |
| 62.Animating Arbitrary Objects via Deep Motion Transfer 通过深度运动传递对任意对象进行动画处理 | |
| 63.An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection 迭代协作自顶向下和自底向上推理网络用于显着目标检测 | |
| 64.Answer Them All! Toward Universal Visual Question Answering Models 全部回答！走向通用视觉问答模型 | |
| 65.AOGNets_ Compositional Grammatical Architectures for Deep Learning AOGNets_深度学习的组合语法架构 | |
| 66.A Parametric Top-View Representation of Complex Road Scenes 复杂道路场景的参数顶视图表示 | |
| 67.APDrawingGAN_ Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs APDrawingGAN_使用分层GAN从人脸照片生成艺术肖像画 | |
| 68.ApolloCar3D_ A Large 3D Car Instance Understanding Benchmark for Autonomous Driving ApolloCar3D_大型3D汽车实例了解自动驾驶基准 | |
| 69.Arbitrary Shape Scene Text Detection With Adaptive Text Region Representation 具有自适应文本区域表示的任意形状场景文本检测 | |
| 70.Argoverse_ 3D Tracking and Forecasting With Rich Maps Argoverse_使用丰富地图进行3D跟踪和预测 | |
| 71.A Robust Local Spectral Descriptor for Matching Non-Rigid Shapes With Incompatible Shape Structures 用于匹配非刚性形状与不兼容形状结构的鲁棒局部光谱描述符 | |
| 72.Art2Real_ Unfolding the Reality of Artworks via Semantically-Aware Image-To-Image Translation Art2Real_通过语义感知的图像到图像翻译展现艺术品的真实性 | |
| 73.A Simple Baseline for Audio-Visual Scene-Aware Dialog 视听场景感知对话框的简单基准 | |
| 74.A Simple Pooling-Based Design for Real-Time Salient Object Detection 基于池的实时显着目标检测的简单设计 | |
| 75.A Skeleton-Bridged Deep Learning Approach for Generating Meshes of Complex Topologies From Single RGB Images 从单个RGB图像生成复杂拓扑网格的骨架桥接深度学习方法 | |
| 76.Assessing Personally Perceived Image Quality via Image Features and Collaborative Filtering 通过图像功能和协作过滤评估个人感知的图像质量 | |
| 77.Assessment of Faster R-CNN in Man-Machine Collaborative Search 人机协同搜索中更快的R-CNN评估 | |
| 78.Assisted Excitation of Activations_ A Learning Technique to Improve Object Detectors 辅助激活激励_一种改进物体检测器的学习技术 | |
| 79.Associatively Segmenting Instances and Semantics in Point Clouds 点云中的实例和语义的关联分段 | |
| 80.A Structured Model for Action Detection 动作检测的结构化模型 | |
| 81.A Sufficient Condition for Convergences of Adam and RMSProp Adam和RMSProp收敛的充分条件 | |
| 82.A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning 理论上合理的三重态损失上限，用于提高深度度量学习的效率 | |
| 83.ATOM_ Accurate Tracking by Overlap Maximization ATOM_通过重叠最大化进行精确跟踪 | |
| 84.Attending to Discriminative Certainty for Domain Adaptation 参加域适应性的判别确定性 | |
| 85.Attention-Based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions 存在未知组合失真时基于注意力的图像恢复操作自适应选择 | |
| 86.Attention Based Glaucoma Detection_ A Large-Scale Database and CNN Model 基于注意力的青光眼检测_大型数据库和CNN模型 | |
| 87.Attention-Guided Unified Network for Panoptic Segmentation 全景分割的注意力指导统一网络 | |
| 88.Attentive Region Embedding Network for Zero-Shot Learning 零发散学习的注意力区域嵌入网络 | |
| 89.Attentive Relational Networks for Mapping Images to Scene Graphs 将图像映射到场景图的细心关系网络 | |
| 90.Attribute-Driven Feature Disentangling and Temporal Aggregation for Video Person Re-Identification 用于视频人重新识别的属性驱动特征分解和时间聚合 | |
| 91.Audio Visual Scene-Aware Dialog 视听场景感知对话框 | |
| 92.AutoAugment_ Learning Augmentation Strategies From Data AutoAugment_从数据中学习扩增策略 | |
| 93.Auto-DeepLab_ Hierarchical Neural Architecture Search for Semantic Image Segmentation Auto-DeepLab_分层神经体系结构搜索，用于语义图像分割 | |
| 94.Automatic Face Aging in Videos via Deep Reinforcement Learning 通过深度强化学习在视频中自动进行面部老化 | |
| 95.A Variational Auto-Encoder Model for Stochastic Point Processes 随机点过程的变分自动编码器模型 | |
| 96.A Variational EM Framework With Adaptive Edge Selection for Blind Motion Deblurring 用于盲运动去模糊的具有自适应边缘选择的变体EM框架 | |
| 97.BAD SLAM_ Bundle Adjusted Direct RGB-D SLAM BAD SLAM_捆绑调整后的直接RGB-D SLAM | |
| 98.Bag of Tricks for Image Classification with Convolutional Neural Networks 使用卷积神经网络进行图像分类的技巧包 | |
| 99.Barrage of Random Transforms for Adversarially Robust Defense 对抗性鲁棒防御的随机变换弹幕 | |
| 100.Bayesian Hierarchical Dynamic Model for Human Action Recognition 人体动作识别的贝叶斯层次动态模型 |
| 论文 | 概要 |
|---|---|
| 101.BeautyGlow_ On-Demand Makeup Transfer Framework With Reversible Generative Network BeautyGlow_具有可逆生成网络的按需化妆转移框架 | |
| 102.Beyond Gradient Descent for Regularized Segmentation Losses 超越梯度下降的规则分割损失 | |
| 103.Beyond Tracking_ Selecting Memory and Refining Poses for Deep Visual Odometry 超越跟踪_为深度视觉里程表选择内存并完善姿势 | |
| 104.Bi-Directional Cascade Network for Perceptual Edge Detection 双向级联网络，用于感知边缘检测 | |
| 105.Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction 无监督单眼深度预测的双边循环约束和自适应正则化 | |
| 106.Binary Ensemble Neural Network_ More Bits per Network or More Networks per Bit_ 二进制集成神经网络_每个网络更多位或每个位更多网络_ | |
| 107.Biologically-Constrained Graphs for Global Connectomics Reconstruction 用于全局Connectomics重建的生物约束图 | |
| 108.Blending-Target Domain Adaptation by Adversarial Meta-Adaptation Networks 对抗性元自适应网络的混合目标域自适应 | |
| 109.Blind Geometric Distortion Correction on Images Through Deep Learning 通过深度学习对图像进行盲几何失真校正 | |
| 110.Blind Super-Resolution With Iterative Kernel Correction 具有迭代内核校正的盲超分辨率 | |
| 111.Boosting Local Shape Matching for Dense 3D Face Correspondence 增强局部形状匹配以实现密集的3D人脸对应 | |
| 112.Bottom-Up Object Detection by Grouping Extreme and Center Points 通过对极端点和中心点进行分组来进行自下而上的对象检测 | |
| 113.Box-Driven Class-Wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation 框驱动的明智区域掩蔽和填充率引导损失，用于弱监督语义分割 | |
| 114.Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence 通过时空对应桥接立体匹配和光流 | |
| 115.BubbleNets_ Learning to Select the Guidance Frame in Video Object Segmentation by Deep Sorting Frames BubbleNets_学习通过深度排序框架选择视频对象分割中的指导框架 | |
| 116.Building Detail-Sensitive Semantic Segmentation Networks With Polynomial Pooling 使用多项式池构建对细节敏感的语义分割网络 | |
| 117.Building Efficient Deep Neural Networks With Unitary Group Convolutions 利用Unit群卷积构建高效的深度神经网络 | |
| 118.C3AE_ Exploring the Limits of Compact Model for Age Estimation C3AE_探索年龄估计的紧凑模型的极限 | |
| 119.CAM-Convs_ Camera-Aware Multi-Scale Convolutions for Single-View Depth CAM-Convs_用于单视图深度的相机感知多尺度卷积 | |
| 120.CapSal_ Leveraging Captioning to Boost Semantics for Salient Object Detection CapSal_利用字幕来增强语义以进行显着对象检测 | |
| 121.Capture, Learning, and Synthesis of 3D Speaking Styles 捕捉，学习和综合3D语音样式 | |
| 122.Cascaded Generative and Discriminative Learning for Microcalcification Detection in Breast Mammograms 乳房X线照片微钙化检测的级联生成和判别学习 | |
| 123.Cascaded Partial Decoder for Fast and Accurate Salient Object Detection 级联部分解码器，用于快速，准确的显着目标检测 | |
| 124.Cascaded Projection_ End-To-End Network Compression and Acceleration 级联投影_端到端网络压缩和加速 | |
| 125.Catastrophic Child’s Play_ Easy to Perform, Hard to Defend Adversarial Attacks 灾难性的儿童游戏_易于执行，难以防御对抗性攻击 | |
| 126.Centripetal SGD for Pruning Very Deep Convolutional Networks With Complicated Structure 向心SGD用于修剪结构复杂的超深卷积网络 | |
| 127.Characterizing and Avoiding Negative Transfer 表征并避免负迁移 | |
| 128.Character Region Awareness for Text Detection 用于文本检测的字符区域意识 | |
| 129.Class-Balanced Loss Based on Effective Number of Samples 基于有效样本数的类平衡损失 | |
| 130.Classification-Reconstruction Learning for Open-Set Recognition 用于开放集识别的分类重建学习 | |
| 131.CLEVR-Ref+_ Diagnosing Visual Reasoning With Referring Expressions CLEVR-Ref + _使用引用表达式诊断视觉推理 | |
| 132.ClusterNet_ Deep Hierarchical Cluster Network With Rigorously Rotation-Invariant Representation for Point Cloud Analysis ClusterNet_具有严格旋转不变表示的深度层次集群网络，用于点云分析 | |
| 133.C-MIL_ Continuation Multiple Instance Learning for Weakly Supervised Object Detection C-MIL_用于弱监督对象检测的连续多实例学习 | |
| 134.Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images 全局全局协作网络，可对超高分辨率图像进行内存有效的分割 | |
| 135.Collaborative Spatiotemporal Feature Learning for Video Action Recognition 协作时空特征学习的视频动作识别 | |
| 136.Coloring With Limited Data_ Few-Shot Colorization via Memory Augmented Networks 通过有限的数据进行着色_通过内存增强网络进行少量着色 | |
| 137.Combinatorial Persistency Criteria for Multicut and Max-Cut Multicut和Max-Cut的组合持久性标准 | |
| 138.ComDefend_ An Efficient Image Compression Model to Defend Adversarial Examples ComDefend_一种有效的图像压缩模型来防御对抗性示例 | |
| 139.Compact Feature Learning for Multi-Domain Image Classification 紧凑特征学习，用于多域图像分类 | |
| 140.Competitive Collaboration_ Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation 竞争性协作_深度，相机运动，光流和运动分割的联合无监督学习 | |
| 141.Composing Text and Image for Image Retrieval - an Empirical Odyssey 文字和图像的组合以进行图像检索-一种经验式的奥德赛 | |
| 142.Compressing Convolutional Neural Networks via Factorized Convolutional Filters 通过分解卷积滤波器压缩卷积神经网络 | |
| 143.Compressing Unknown Images With Product Quantizer for Efficient Zero-Shot Classification 使用产品量化器压缩未知图像以实现有效的零散分类 | |
| 144.Conditional Adversarial Generative Flow for Controllable Image Synthesis 条件对抗生成流可控图像合成 | |
| 145.Conditional Single-View Shape Generation for Multi-View Stereo Reconstruction 用于多视图立体声重建的条件单视图形状生成 | |
| 146.Connecting the Dots_ Learning Representations for Active Monocular Depth Estimation 连接Dots_学习表示以进行主动单眼深度估计 | |
| 147.Connecting Touch and Vision via Cross-Modal Prediction 通过跨模态预测连接触摸和视觉 | |
| 148.Constrained Generative Adversarial Networks for Interactive Image Generation 用于交互式图像生成的约束生成对抗网络 | |
| 149.Content Authentication for Neural Imaging Pipelines_ End-To-End Optimization of Photo Provenance in Complex Distribution Channels 神经成像管道的内容认证_复杂分销渠道中照片来源的端到端优化 | |
| 150.Content-Aware Multi-Level Guidance for Interactive Instance Segmentation 交互式实例细分的内容感知多级指南 |
| 论文 | 概要 |
|---|---|
| 151.Context and Attribute Grounded Dense Captioning 上下文和属性基础密集字幕 | |
| 152.Context-Aware Visual Compatibility Prediction 上下文感知的视觉兼容性预测 | |
| 153.Context-Reinforced Semantic Segmentation 上下文增强的语义分割 | |
| 154.Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection 对比先验和流体金字塔积分，用于RGBD显着物体检测 | |
| 155.Convolutional Recurrent Network for Road Boundary Extraction 卷积递归网络用于道路边界提取 | |
| 156.Convolutional Relational Machine for Group Activity Recognition 卷积关系机的群体活动识别 | |
| 157.Co-Occurrence Neural Network 共现神经网络 | |
| 158.Co-Occurrent Features in Semantic Segmentation 语义分割中的并发特征 | |
| 159.Coordinate-Based Texture Inpainting for Pose-Guided Human Image Generation 基于坐标的人像引导下的纹理修复 | |
| 160.Coordinate-Free Carlsson-Weinshall Duality and Relative Multi-View Geometry 无坐标Carlsson-Weinshall对偶和相对多视图几何 | |
| 161.Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing 通过掩码引导的全卷积网络和多尺度标签平滑进行共显着性检测 | |
| 162.CRAVES_ Controlling Robotic Arm With a Vision-Based Economic System CRAVES_通过基于视觉的经济系统控制机械臂 | |
| 163.Cross-Classification Clustering_ An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics 交叉分类聚类_ Connectomics中用于3-D实例分割的高效多对象跟踪技术 | |
| 164.Cross Domain Model Compression by Structurally Weight Sharing 通过结构权重共享进行跨域模型压缩 | |
| 165.CrossInfoNet_ Multi-Task Information Sharing Based Hand Pose Estimation CrossInfoNet_基于多任务信息共享的手势估计 | |
| 166.Cross-Modality Personalization for Retrieval 跨模态个性化检索 | |
| 167.Cross-Modal Relationship Inference for Grounding Referring Expressions 接地引用表达式的跨模态关系推断 | |
| 168.Cross-Modal Self-Attention Network for Referring Image Segmentation 用于参考图像分割的跨模态自注意力网络 | |
| 169.Cross-Task Weakly Supervised Learning From Instructional Videos 跨任务弱指导学习教学视频 | |
| 170.Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks 网格编码器/解码器网络的人群计数和密度估计 | |
| 171.CrowdPose_ Efficient Crowded Scenes Pose Estimation and a New Benchmark CrowdPose_有效的拥挤场景姿势估计和新基准 | |
| 172.Curls & Whey_ Boosting Black-Box Adversarial Attacks 卷毛和乳清_增强黑盒对抗性攻击 | |
| 173.Customizable Architecture Search for Semantic Segmentation 可定制的体系结构搜索以进行语义细分 | |
| 174.Cycle-Consistency for Robust Visual Question Answering 循环一致性，用于健壮的视觉问题解答 | |
| 175.Cyclic Guidance for Weakly Supervised Joint Detection and Segmentation 用于弱监督关节检测和分割的循环引导 | |
| 176.D3TW_ Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation D3TW_区分微分动态时间扭曲，用于弱监督的动作对齐和分段 | |
| 177.Dance With Flow_ Two-In-One Stream Action Detection 与Flow共舞_二合一流动作检测 | |
| 178.DARNet_ Deep Active Ray Network for Building Segmentation DARNet_用于建筑物细分的深度有源射线网络 | |
| 179.Data Augmentation Using Learned Transformations for One-Shot Medical Image Segmentation 使用学习的变换进行一幅医学图像分割的数据增强 | |
| 180.Data-Driven Neuron Allocation for Scale Aggregation Networks 用于规模聚合网络的数据驱动神经元分配 | |
| 181.DDLSTM_ Dual-Domain LSTM for Cross-Dataset Action Recognition DDLSTM_用于跨数据集动作识别的双域LSTM | |
| 182.Decoders Matter for Semantic Segmentation_ Data-Dependent Decoding Enables Flexible Feature Aggregation 语义分割的解码器很重要_数据相关的解码实现了灵活的特征聚合 | |
| 183.Decorrelated Adversarial Learning for Age-Invariant Face Recognition 与装饰相关的对抗学习用于年龄不变的人脸识别 | |
| 184.Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses 基于梯度的L2对抗性攻击和防御的解耦方向和范数 | |
| 185.Deep Asymmetric Metric Learning via Rich Relationship Mining 通过丰富的关系挖掘进行深度不对称度量学习 | |
| 186.Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence 通过时间聚集和递归进行的深盲视频说明 | |
| 187.DeepCaps_ Going Deeper With Capsule Networks DeepCaps_进一步深入胶囊网络 | |
| 188.Deep ChArUco_ Dark ChArUco Marker Pose Estimation Deep ChArUco_ Dark ChArUco标记姿势估计 | |
| 189.DeepCO3_ Deep Instance Co-Segmentation by Co-Peak Search and Co-Saliency Detection DeepCO3_通过共峰搜索和共显着性检测进行的深度实例共细分 | |
| 190.Deep Dual Relation Modeling for Egocentric Interaction Recognition 自我中心交互识别的深度对偶关系建模 | |
| 191.Deep Embedding Learning With Discriminative Sampling Policy 区分样本策略的深度嵌入学习 | |
| 192.Deeper and Wider Siamese Networks for Real-Time Visual Tracking 实时视觉跟踪的更广泛的暹罗网络 | |
| 193.Deep Exemplar-Based Video Colorization 基于深度样本的视频着色 | |
| 194.DeepFlux for Skeletons in the Wild DeepFlux适用于野外骨骼 | |
| 195.Deep Geometric Prior for Surface Reconstruction 表面重建的深层几何先验 | |
| 196.Deep Global Generalized Gaussian Networks 深度全球广义高斯网络 | |
| 197.Deep High-Resolution Representation Learning for Human Pose Estimation 用于人体姿势估计的深度高分辨率表示学习 | |
| 198.Deep Incremental Hashing Network for Efficient Image Retrieval 深度增量哈希网络，可高效检索图像 | |
| 199.DeepLight_ Learning Illumination for Unconstrained Mobile Mixed Reality DeepLight_用于无限制移动混合现实的学习照明 | |
| 200.Deeply-Supervised Knowledge Synergy 深度监督的知识协同 |
| 论文 | 概要 |
|---|---|
| 201.DeepMapping_ Unsupervised Map Estimation From Multiple Point Clouds DeepMapping_来自多点云的无监督地图估计 | |
| 202.Deep Metric Learning to Rank 深度度量学习排名 | |
| 203.Deep Multimodal Clustering for Unsupervised Audiovisual Learning 用于无监督视听学习的深度多模式聚类 | |
| 204.Deep Reinforcement Learning of Volume-Guided Progressive View Inpainting for 3D Point Scene Completion From a Single Depth Image 从单个深度图像进行3D点场景完成的体积引导的渐进式视图修复的深度强化学习 | |
| 205.Deep Robust Subjective Visual Property Prediction in Crowdsourcing 众包中的深度鲁棒主观视觉属性预测 | |
| 206.Deep Single Image Camera Calibration With Radial Distortion 具有径向畸变的深层单像相机校准 | |
| 207.Deep Spectral Clustering Using Dual Autoencoder Network 使用双自动编码器网络的深度光谱聚类 | |
| 208.Deep Spherical Quantization for Image Search 用于图像搜索的深球形量化 | |
| 209.Deep Stacked Hierarchical Multi-Patch Network for Image Deblurring 用于图像去模糊的深度堆叠分层多面体网络 | |
| 210.Deep Supervised Cross-Modal Retrieval 深度监督跨模态检索 | |
| 211.Deep Surface Normal Estimation With Hierarchical RGB-D Fusion 具有分层RGB-D融合的深表面法线估计 | |
| 212.Deep Transfer Learning for Multiple Class Novelty Detection 用于多类新颖性检测的深度转移学习 | |
| 213.Deep Tree Learning for Zero-Shot Face Anti-Spoofing 深度学习的零发脸反欺骗 | |
| 214.Deep Virtual Networks for Memory Efficient Inference of Multiple Tasks 深度虚拟网络，可有效推断多个任务 | |
| 215.DeepVoxels_ Learning Persistent 3D Feature Embeddings DeepVoxels_学习持久性3D特征嵌入 | |
| 216.Defending Against Adversarial Attacks by Randomized Diversification 通过随机分散防御对抗攻击 | |
| 217.Defense Against Adversarial Images Using Web-Scale Nearest-Neighbor Search 使用Web尺度最近邻搜索防御对抗性图像 | |
| 218.Deformable ConvNets V2_ More Deformable, Better Results 可变形的ConvNets V2_更可变形，效果更好 | |
| 219.Dense Classification and Implanting for Few-Shot Learning 少量学习的密集分类和植入 | |
| 220.Dense Depth Posterior (DDP) From Single Image and Sparse Range 单图像和稀疏范围的密集深度后验（DDP） | |
| 221.Densely Semantically Aligned Person Re-Identification 语义一致的人重新识别 | |
| 222.Depth-Attentional Features for Single-Image Rain Removal 深度注意功能可去除单幅影像 | |
| 223.Depth-Aware Video Frame Interpolation 深度感知视频帧插值 | |
| 224.Depth From a Polarisation + RGB Stereo Pair 偏振+ RGB立体声对的深度 | |
| 225.Describing Like Humans_ On Diversity in Image Captioning 像人类一样描述图像字幕的多样性 | |
| 226.Destruction and Construction Learning for Fine-Grained Image Recognition 精细识别图像的破坏与构造学习 | |
| 227.Detailed Human Shape Estimation From a Single Image by Hierarchical Mesh Deformation 通过分层网格变形从单个图像进行详细的人体形状估计 | |
| 228.Detection Based Defense Against Adversarial Examples From the Steganalysis Point of View 从隐写分析的角度出发，基于检测的对抗示例对抗 | |
| 229.Detect-To-Retrieve_ Efficient Regional Aggregation for Image Search 检测到检索_图像搜索的有效区域聚合 | |
| 230.DFANet_ Deep Feature Aggregation for Real-Time Semantic Segmentation DFANet_用于实时语义细分的深度特征聚合 | |
| 231.Dichromatic Model Based Temporal Color Constancy for AC Light Sources 基于双色模型的交流光源的时间色恒量 | |
| 232.Did It Change_ Learning to Detect Point-Of-Interest Changes for Proactive Map Updates 它发生了变化吗_学习检测主动地图更新的兴趣点变化 | |
| 233.Discovering Fair Representations in the Data Domain 在数据域中发现公平的表示形式 | |
| 234.Discovering Visual Patterns in Art Collections With Spatially-Consistent Feature Learning 通过空间一致的特征学习发现艺术品收藏中的视觉模式 | |
| 235.Disentangled Representation Learning for 3D Face Shape 3D人脸形状的解缠表示学习 | |
| 236.Disentangling Adversarial Robustness and Generalization 解开对抗的鲁棒性和泛化 | |
| 237.Dissecting Person Re-Identification From the Viewpoint of Viewpoint 从角度剖析人的重新识别 | |
| 238.Dissimilarity Coefficient Based Weakly Supervised Object Detection 基于相异系数的弱监督目标检测 | |
| 239.Distant Supervised Centroid Shift_ A Simple and Efficient Approach to Visual Domain Adaptation 远程监督质心移位_一种简单有效的视觉域自适应方法 | |
| 240.Distilled Person Re-Identification_ Towards a More Scalable System 蒸馏人重新识别_建立更可扩展的系统 | |
| 241.DistillHash_ Unsupervised Deep Hashing by Distilling Data Pairs DistillHash_通过提取数据对进行无监督的深度哈希 | |
| 242.Distraction-Aware Shadow Detection 分心的阴影检测 | |
| 243.Divergence Triangle for Joint Training of Generator Model, Energy-Based Model, and Inferential Model 发散三角形，用于发电机模型，基于能量的模型和推理模型的联合训练 | |
| 244.Diversify and Match_ A Domain Adaptive Representation Learning Paradigm for Object Detection 多样化和匹配_用于对象检测的领域自适应表示学习范例 | |
| 245.Divide and Conquer the Embedding Space for Metric Learning 划分和征服度量学习的嵌入空间 | |
| 246.DMC-Net_ Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition DMC-Net_生成判别运动提示以进行快速压缩的视频动作识别 | |
| 247.DM-GAN_ Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis DM-GAN_用于文本到图像合成的动态内存生成对抗网络 | |
| 248.Domain Generalization by Solving Jigsaw Puzzles 通过拼图解决领域综合 | |
| 249.Domain-Specific Batch Normalization for Unsupervised Domain Adaptation 无监督域自适应的特定域批处理规范化 | |
| 250.Domain-Symmetric Networks for Adversarial Domain Adaptation 对抗域自适应的域对称网络 |
| 论文 | 概要 |
|---|---|
| 251.Double-DIP_ Unsupervised Image Decomposition via Coupled Deep-Image-Priors _Double-DIP__通过耦合深图像优先级的无监督图像分解 | |
| 252.Double Nuclear Norm Based Low Rank Representation on Grassmann Manifolds for Clustering 基于双核范数的格拉斯曼流形上的低秩表示法 | |
| 253.Douglas-Rachford Networks_ Learning Both the Image Prior and Data Fidelity Terms for Blind Image Deconvolution Douglas-Rachford Networks_学习图像先验和数据保真度术语以进行盲图像反卷积 | |
| 254.Dual Attention Network for Scene Segmentation 双重注意力网络的场景分割 | |
| 255.Dual Encoding for Zero-Example Video Retrieval 用于零样本视频检索的双重编码 | |
| 256.DuDoNet_ Dual Domain Network for CT Metal Artifact Reduction DuDoNet_用于减少CT金属伪影的双域网络 | |
| 257.DVC_ An End-To-End Deep Video Compression Framework DVC_端到端深度视频压缩框架 | |
| 258.Dynamic Fusion With Intra- and Inter-Modality Attention Flow for Visual Question Answering 具有模态内和模态注意流的动态融合，用于视觉问答 | |
| 259.ECC_ Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model ECC_通过双线性回归模型独立于平台的能量受限深度神经网络压缩 | |
| 260.Edge-Labeling Graph Neural Network for Few-Shot Learning 边缘标签图神经网络的少量学习 | |
| 261.Effective Aesthetics Prediction With Multi-Level Spatially Pooled Features 具有多级空间合并特征的有效美学预测 | |
| 262.Efficient Multi-Domain Learning by Covariance Normalization 协方差归一化的高效多域学习 | |
| 263.Efficient Neural Network Compression 高效的神经网络压缩 | |
| 264.Efficient Online Multi-Person 2D Pose Tracking With Recurrent Spatio-Temporal Affinity Fields 具有时空时空亲和力字段的高效在线多人2D姿势跟踪 | |
| 265.Efficient Parameter-Free Clustering Using First Neighbor Relations 使用第一邻居关系的高效无参数聚类 | |
| 266.EIGEN_ Ecologically-Inspired GENetic Approach for Neural Network Structure Searching From Scratch EIGEN_从头开始寻找神经网络结构的生态启发遗传方法 | |
| 267.Embedding Complementary Deep Networks for Image Classification 嵌入互补深度网络进行图像分类 | |
| 268.Embodied Question Answering in Photorealistic Environments With Point Cloud Perception 点云感知在真实感环境中的具体问题解答 | |
| 269.Emotion-Aware Human Attention Prediction 情绪感知的人类注意力预测 | |
| 270.End-To-End Efficient Representation Learning via Cascading Combinatorial Optimization 通过级联组合优化进行端到端有效表示学习 | |
| 271.End-To-End Interpretable Neural Motion Planner 端到端可解释神经运动计划器 | |
| 272.End-To-End Projector Photometric Compensation 端到端投影仪光度补偿 | |
| 273.End-To-End Supervised Product Quantization for Image Search and Retrieval 用于图像搜索和检索的端到端监督产品量化 | |
| 274.Engaging Image Captioning via Personality 通过个性化图片字幕 | |
| 275.Enhanced Bayesian Compression via Deep Reinforcement Learning 通过深度强化学习增强贝叶斯压缩 | |
| 276.Enhanced Pix2pix Dehazing Network 增强的Pix2pix除雾网络 | |
| 277.Enhancing Diversity of Defocus Blur Detectors via Cross-Ensemble Network 通过交叉集成网络增强散焦模糊检测器的多样性 | |
| 278.Enhancing TripleGAN for Semi-Supervised Conditional Instance Synthesis and Classification 增强TripleGAN用于半监督条件实例的合成和分类 | |
| 279.Ensemble Deep Manifold Similarity Learning Using Hard Proxies 使用硬代理整合深度流形相似性学习 | |
| 280.ESIR_ End-To-End Scene Text Recognition via Iterative Image Rectification ESIR_通过迭代图像校正实现端到端场景文本识别 | |
| 281.ESPNetv2_ A Light-Weight, Power Efficient, and General Purpose Convolutional Neural Network ESPNetv2_轻巧，节能，通用的卷积神经网络 | |
| 282.Estimating 3D Motion and Forces of Person-Object Interactions From Monocular Video 从单眼视频估计3D运动和人-物体相互作用的力 | |
| 283.Event-Based High Dynamic Range Image and Very High Frame Rate Video Generation Using Conditional Generative Adversarial Networks 使用条件生成对抗网络的基于事件的高动态范围图像和超高帧频视频生成 | |
| 284.Events-To-Video_ Bringing Modern Computer Vision to Event Cameras 视频事件_将现代计算机视觉带到事件摄像机 | |
| 285.Exact Adversarial Attack to Image Captioning via Structured Output Learning With Latent Variables 通过具有潜在变量的结构化输出学习，对图像字幕进行精确的对抗攻击 | |
| 286.Explainability Methods for Graph Convolutional Neural Networks 图卷积神经网络的可解释性方法 | |
| 287.Explainable and Explicit Visual Reasoning Over Scene Graphs 场景图的可解释和显式视觉推理 | |
| 288.Explicit Bias Discovery in Visual Question Answering Models 视觉问答模型中的显式偏差发现 | |
| 289.Explicit Spatial Encoding for Deep Local Descriptors 深度本地描述符的显式空间编码 | |
| 290.Exploiting Edge Features for Graph Neural Networks 利用图神经网络的边缘功能 | |
| 291.Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression 利用核稀疏性和熵进行可解释的CNN压缩 | |
| 292.Exploiting Temporal Context for 3D Human Pose Estimation in the Wild 利用时间上下文进行野外3D人体姿势估计 | |
| 293.Explore-Exploit Graph Traversal for Image Retrieval 浏览-利用图遍历进行图像检索 | |
| 294.Exploring Context and Visual Pattern of Relationship for Scene Graph Generation 探索上下文和关系的视觉模式以生成场景图 | |
| 295.Exploring the Bounds of the Utility of Context for Object Detection 探索用于对象检测的上下文实用工具的界限 | |
| 296.Expressive Body Capture_ 3D Hands, Face, and Body From a Single Image 富有表现力的身体捕捉_通过单个图像获得3D手，脸和身体 | |
| 297.Face Anti-Spoofing_ Model Matters, so Does Data 面对反欺骗_模型很重要，数据也很重要 | |
| 298.Face-Focused Cross-Stream Network for Deception Detection in Videos 面向面部的跨流网络，用于视频中的欺骗检测 | |
| 299.Facial Emotion Distribution Learning by Exploiting Low-Rank Label Correlations Locally 通过局部利用低排名标签相关性来进行面部情绪分布学习 | |
| 300.Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models 通过深度卷积生成模型快速灵活地进行室内场景合成 |
| 论文 | 概要 |
|---|---|
| 301.Fast and Robust Multi-Person 3D Pose Estimation From Multiple Views 从多个视图进行快速可靠的多人3D姿势估计 | |
| 302.FastDraw_ Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction Network FastDraw_通过采用顺序预测网络解决了车道检测的长尾问题 | |
| 303.Fast Human Pose Estimation 快速人体姿势估计 | |
| 304.Fast Interactive Object Annotation With Curve-GCN Curve-GCN的快速交互式对象注释 | |
| 305.Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells 通过辅助细胞的紧凑型语义分割模型的快速神经体系结构搜索 | |
| 306.Fast Spatially-Varying Indoor Lighting Estimation 快速变化的室内照明估计 | |
| 307.Fast Spatio-Temporal Residual Network for Video Super-Resolution 用于视频超分辨率的快速时空残留网络 | |
| 308.Fast User-Guided Video Object Segmentation by Interaction-And-Propagation Networks 通过交互传播网络的用户指导的视频对象快速分割 | |
| 309.FBNet_ Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search FBNet_通过可区分的神经体系结构搜索实现硬件感知的高效ConvNet设计 | |
| 310.Feature Selective Anchor-Free Module for Single-Shot Object Detection 用于单发物体检测的功能选择免锚模块 | |
| 311.Feature Space Perturbations Yield More Transferable Adversarial Examples 特征空间扰动产生更多可传递的对抗性示例 | |
| 312.Feedback Network for Image Super-Resolution 图像超分辨率反馈网络 | |
| 313.FEELVOS_ Fast End-To-End Embedding Learning for Video Object Segmentation FEELVOS_用于视频对象分割的快速端到端嵌入学习 | |
| 314.Few-Shot Adaptive Faster R-CNN 少量自适应快速R-CNN | |
| 315.Few-Shot Learning via Saliency-Guided Hallucination of Samples 通过样本的显着性幻觉进行少量学习 | |
| 316.Few-Shot Learning With Localization in Realistic Settings 在实际环境中进行本地化的少量学习 | |
| 317.FickleNet_ Weakly and Semi-Supervised Semantic Image Segmentation Using Stochastic Inference FickleNet_使用随机推理的弱半监督语义图像分割 | |
| 318.Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration 通过几何中间值对滤波器进行修剪以实现深层卷积神经网络加速 | |
| 319.FilterReg_ Robust and Efficient Probabilistic Point-Set Registration Using Gaussian Filter and Twist Parameterization 使用高斯滤波器和扭曲参数化的FilterReg_鲁棒高效的概率点集配准 | |
| 320.Finding Task-Relevant Features for Few-Shot Learning by Category Traversal 通过类别遍历查找很少学习的与任务相关的功能 | |
| 321.FineGAN_ Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery FineGAN_用于细粒度对象生成和发现的无监督分层解缠 | |
| 322.FML_ Face Model Learning From Videos FML_通过视频学习人脸模型 | |
| 323.FOCNet_ A Fractional Optimal Control Network for Image Denoising FOCNet_用于图像去噪的分数最优控制网络 | |
| 324.Foreground-Aware Image Inpainting 前景感知图像修复 | |
| 325.FSA-Net_ Learning Fine-Grained Structure Aggregation for Head Pose Estimation From a Single Image FSA-Net_从单个图像中学习细粒度结构聚合以进行头部姿势估计 | |
| 326.Fully Learnable Group Convolution for Acceleration of Deep Neural Networks 完全可学习的群卷积，用于加速深度神经网络 | |
| 327.Fully Quantized Network for Object Detection 用于物体检测的全量化网络 | |
| 328.F-VAEGAN-D2_ A Feature Generating Framework for Any-Shot Learning F-VAEGAN-D2_任意学习的特征生成框架 | |
| 329.Gait Recognition via Disentangled Representation Learning 纠缠表示学习的步态识别 | |
| 330.GA-Net_ Guided Aggregation Net for End-To-End Stereo Matching GA-Net_引导式聚合网络，用于端到端立体声匹配 | |
| 331.Gaussian Temporal Awareness Networks for Action Localization 高斯时间意识网络的行动本地化 | |
| 332.Generalizable Person Re-Identification by Domain-Invariant Mapping Network 领域不变映射网络对可概括人员的重新识别 | |
| 333.Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders 通过对齐的变分自动编码器进行广义零零点学习 | |
| 334.Generalized Zero-Shot Recognition Based on Visually Semantic Embedding 基于视觉语义嵌入的广义零拍识别 | |
| 335.Generating 3D Adversarial Point Clouds 生成3D对抗点云 | |
| 336.Generating Classification Weights With GNN Denoising Autoencoders for Few-Shot Learning 使用GNN去噪自动编码器生成分类权重以进行少量学习 | |
| 337.Generating Multiple Hypotheses for 3D Human Pose Estimation With Mixture Density Network 生成用于混合密度网络3D人体姿势估计的多个假设 | |
| 338.Geometry-Aware Distillation for Indoor Semantic Segmentation 用于室内语义分割的几何感知蒸馏 | |
| 339.Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation 用于单眼深度估计的几何感知对称域自适应 | |
| 340.Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping 一面无监督域映射的几何一致性生成对抗网络 | |
| 341.GeoNet_ Deep Geodesic Networks for Point Cloud Analysis GeoNet_用于点云分析的深度测地网 | |
| 342.GFrames_ Gradient-Based Local Reference Frame for 3D Shape Matching 用于3D形状匹配的GFrames_基于渐变的本地参考系 | |
| 343.GIF2Video_ Color Dequantization and Temporal Interpolation of GIF Images GIF2Video_ GIF图像的色彩消除和时间插值 | |
| 344.Global Second-Order Pooling Convolutional Networks 全局二阶池化卷积网络 | |
| 345.Good News, Everyone! Context Driven Entity-Aware Captioning for News Images 大家好！新闻图像的上下文驱动的实体感知字幕 | |
| 346.GPSfM_ Global Projective SFM Using Algebraic Constraints on Multi-View Fundamental Matrices GPSfM_在多视图基本矩阵上使用代数约束的全局投影SFM | |
| 347.GQA_ A New Dataset for Real-World Visual Reasoning and Compositional Question Answering GQA_用于现实世界中视觉推理和作文问答的新数据集 | |
| 348.Gradient Matching Generative Networks for Zero-Shot Learning 零匹配学习的梯度匹配生成网络 | |
| 349.Graph Attention Convolution for Point Cloud Semantic Segmentation 图注意力卷积用于点云语义分割 | |
| 350.Graph-Based Global Reasoning Networks 基于图的全局推理网络 |
| 论文 | 概要 |
|---|---|
| 351.Graph Convolutional Label Noise Cleaner_ Train a Plug-And-Play Action Classifier for Anomaly Detection 图卷积标签噪声清除器_训练即插即用动作分类器以进行异常检测 | |
| 352.Graph Convolutional Tracking 图卷积跟踪 | |
| 353.Graphical Contrastive Losses for Scene Graph Parsing 场景图解析的图形对比损失 | |
| 354.Greedy Structure Learning of Hierarchical Compositional Models 层次组成模型的贪婪结构学习 | |
| 355.Grid R-CNN 网格R-CNN | |
| 356.Grounded Video Description 接地视频说明 | |
| 357.Group Sampling for Scale Invariant Face Detection 组采样用于尺度不变面部检测 | |
| 358.Group-Wise Correlation Stereo Network 群智相关立体声网络 | |
| 359.GS3D_ An Efficient 3D Object Detection Framework for Autonomous Driving GS3D_用于自动驾驶的高效3D对象检测框架 | |
| 360.Guaranteed Matrix Completion Under Multiple Linear Transformations 多个线性变换下的保证矩阵完成 | |
| 361.Guided Stereo Matching 引导立体声匹配 | |
| 362.Handwriting Recognition in Low-Resource Scripts Using Adversarial Learning 使用对抗学习的低资源脚本中的手写识别 | |
| 363.HAQ_ Hardware-Aware Automated Quantization With Mixed Precision HAQ_具有混合精度的硬件感知自动量化 | |
| 364.HetConv_ Heterogeneous Kernel-Based Convolutions for Deep CNNs HetConv_用于深CNN的基于异构内核的卷积 | |
| 365.Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering 视频提问的异构记忆增强多模式注意力模型 | |
| 366.Hierarchical Cross-Modal Talking Face Generation With Dynamic Pixel-Wise Loss 具有动态像素明智损失的分层跨模态说话人脸生成 | |
| 367.Hierarchical Deep Stereo Matching on High-Resolution Images 高分辨率图像上的分层深度立体匹配 | |
| 368.Hierarchical Disentanglement of Discriminative Latent Features for Zero-Shot Learning 零射击学习的判别性潜在特征的层次分解 | |
| 369.High Flux Passive Imaging With Single-Photon Sensors 单光子传感器的高通量无源成像 | |
| 370.High-Level Semantic Feature Detection_ A New Perspective for Pedestrian Detection 高级语义特征检测-行人检测的新视角 | |
| 371.Holistic and Comprehensive Annotation of Clinically Significant Findings on Diverse CT Images_ Learning From Radiology Reports and Label Ontology 多种CT图像的临床重要发现的整体和综合注释_从放射学报告和标签本体学中学习 | |
| 372.HoloPose_ Holistic 3D Human Reconstruction In-The-Wild HoloPose_全面的3D野外人类重建 | |
| 373.Homomorphic Latent Space Interpolation for Unpaired Image-To-Image Translation 用于不成对的图像到图像转换的同态潜在空间插值 | |
| 374.H+O_ Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions H + O_ 3D手形姿势和相互作用的统一自我中心识别 | |
| 375.How to Make a Pizza_ Learning a Compositional Layer-Based GAN Model 如何制作披萨_学习基于组合层的GAN模型 | |
| 376.Hybrid Scene Compression for Visual Localization 用于视觉本地化的混合场景压缩 | |
| 377.Hybrid Task Cascade for Instance Segmentation 用于实例细分的混合任务级联 | |
| 378.Hyperspectral Image Reconstruction Using a Deep Spatial-Spectral Prior 使用深空间光谱先验的高光谱图像重建 | |
| 379.Hyperspectral Imaging With Random Printed Mask 随机印刷掩模的高光谱成像 | |
| 380.IGE-Net_ Inverse Graphics Energy Networks for Human Pose Estimation and Single-View Reconstruction IGE-Net_用于人体姿势估计和单视图重构的逆向图形能源网络 | |
| 381.Image Generation From Layout 从布局生成图像 | |
| 382.Image-Question-Answer Synergistic Network for Visual Dialog 视觉对话的图像问题-答案协同网络 | |
| 383.Image Super-Resolution by Neural Texture Transfer 神经纹理转移的图像超分辨率 | |
| 384.Image-To-Image Translation via Group-Wise Deep Whitening-And-Coloring Transformation 通过明智的深度增白和着色转换实现图像到图像的转换 | |
| 385.Importance Estimation for Neural Network Pruning 神经网络修剪的重要性估计 | |
| 386.Improving Action Localization by Progressive Cross-Stream Cooperation 通过渐进式跨流合作改善行动本地化 | |
| 387.Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis 通过注视重定向综合改善用户特定的少量注视适应性 | |
| 388.Improving Semantic Segmentation via Video Propagation and Label Relaxation 通过视频传播和标签松弛改善语义分割 | |
| 389.In Defense of Pre-Trained ImageNet Architectures for Real-Time Semantic Segmentation of Road-Driving Images 防御预训练的ImageNet架构，对道路行驶图像进行实时语义分割 | |
| 390.Information Maximizing Visual Question Generation 信息最大化视觉问题生成 | |
| 391.Informative Object Annotations_ Tell Me Something I Don’t Know 信息对象注释_告诉我一些我不知道的东西 | |
| 392.Inserting Videos Into Videos 将视频插入视频 | |
| 393.Instance-Level Meta Normalization 实例级元规范化 | |
| 394.Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth 通过联合优化空间嵌入和聚类带宽进行实例分割 | |
| 395.Intention Oriented Image Captions With Guiding Objects 具有导向对象的面向意图的图像标题 | |
| 396.Interaction-And-Aggregation Network for Person Re-Identification 交互聚集网络，用于人员重新识别 | |
| 397.Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks 卷积神经网络的可解释且细粒度的视觉解释 | |
| 398.In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations 在使用显式2D特征和中间3D表示的野生人类姿势估计中 | |
| 399.Invariance Matters_ Exemplar Memory for Domain Adaptive Person Re-Identification 不变性_用于领域自适应人重新识别的样本记忆 | |
| 400.Inverse Cooking_ Recipe Generation From Food Images 逆烹饪_从食物图像生成食谱 |
| 论文 | 概要 |
|---|---|
| 401.Inverse Procedural Modeling of Knitwear 针织品的逆过程建模 | |
| 402.InverseRenderNet_ Learning Single Image Inverse Rendering InverseRenderNet_学习单图像逆向渲染 | |
| 403.IP102_ A Large-Scale Benchmark Dataset for Insect Pest Recognition IP102_害虫识别的大规模基准数据集 | |
| 404.IRLAS_ Inverse Reinforcement Learning for Architecture Search IRLAS_用于架构搜索的逆向强化学习 | |
| 405.Isospectralization, or How to Hear Shape, Style, and Correspondence 等光谱化，或如何听到形状，样式和对应关系 | |
| 406.Iterative Alignment Network for Continuous Sign Language Recognition 迭代比对网络用于连续手语识别 | |
| 407.Iterative Normalization_ Beyond Standardization Towards Efficient Whitening 迭代归一化_超越标准化，实现高效美白 | |
| 408.Iterative Projection and Matching_ Finding Structure-Preserving Representatives and Its Application to Computer Vision 迭代投影与匹配_保结构代表及其在计算机视觉中的应用 | |
| 409.Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation 迭代残差细化用于联合光流和遮挡估计 | |
| 410.It’s Not About the Journey; It’s About the Destination_ Following Soft Paths Under Question-Guidance for Visual Reasoning 这与旅程无关；关于目的地_在视觉推理的问题指导下遵循软路径 | |
| 411.Joint Face Detection and Facial Motion Retargeting for Multiple Faces 多人脸的联合面部检测和面部运动重定目标 | |
| 412.Joint Manifold Diffusion for Combining Predictions on Decoupled Observations 联合流形扩散用于组合解耦观测值的预测 | |
| 413.JSIS3D_ Joint Semantic-Instance Segmentation of 3D Point Clouds With Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields JSIS3D_具有多任务点向网络和多值条件随机场的3D点云的联合语义实例分割 | |
| 414.Jumping Manifolds_ Geometry Aware Dense Non-Rigid Structure From Motion 跳跃的流形_动作可感知几何密集的非刚性结构 | |
| 415.Kernel Transformer Networks for Compact Spherical Convolution 紧凑球形卷积的核变压器网络 | |
| 416.Kervolutional Neural Networks 进化神经网络 | |
| 417.K-Nearest Neighbors Hashing K最近邻居散列 | |
| 418.Knockoff Nets_ Stealing Functionality of Black-Box Models 仿制网_黑盒模型的窃取功能 | |
| 419.Knowledge Adaptation for Efficient Semantic Segmentation 知识自适应以实现有效的语义分割 | |
| 420.Knowledge-Embedded Routing Network for Scene Graph Generation 用于场景图生成的知识嵌入式路由网络 | |
| 421.L3-Net_ Towards Learning Based LiDAR Localization for Autonomous Driving L3-Net_面向基于学习的自动驾驶LiDAR定位 | |
| 422.Label Propagation for Deep Semi-Supervised Learning 深度半监督学习的标签传播 | |
| 423.Language-Driven Temporal Activity Localization_ A Semantic Matching Reinforcement Learning Model 语言驱动的时间活动本地化_语义匹配强化学习模型 | |
| 424.Large-Scale Few-Shot Learning_ Knowledge Transfer With Class Hierarchy 大规模少量学习_具有班级层次结构的知识转移 | |
| 425.Large Scale Incremental Learning 大规模增量学习 | |
| 426.Large-Scale Interactive Object Segmentation With Human Annotators 带有人类注释器的大规模交互式对象分割 | |
| 427.Large-Scale Long-Tailed Recognition in an Open World 开放世界中的大规模长尾识别 | |
| 428.Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition 用于视频动作识别的大规模弱监督预训练 | |
| 429.LaserNet_ An Efficient Probabilistic 3D Object Detector for Autonomous Driving LaserNet_用于自动驾驶的高效概率3D对象检测器 | |
| 430.LaSO_ Label-Set Operations Networks for Multi-Label Few-Shot Learning LaSO_标签集操作网络，用于多标签少学 | |
| 431.Latent Filter Scaling for Multimodal Unsupervised Image-To-Image Translation 潜在滤波器缩放用于多模式无监督图像间转换 | |
| 432.Latent Space Autoregression for Novelty Detection 潜在空间自回归用于新颖性检测 | |
| 433.LBS Autoencoder_ Self-Supervised Fitting of Articulated Meshes to Point Clouds LBS Autoencoder_铰接式网格到点云的自监督拟合 | |
| 434.Learning Active Contour Models for Medical Image Segmentation 学习用于医学图像分割的主动轮廓模型 | |
| 435.Learning Actor Relation Graphs for Group Activity Recognition 学习演员关系图以进行团体活动识别 | |
| 436.Learning a Deep ConvNet for Multi-Label Classification With Partial Labels 学习带有部分标签的Deep ConvNet进行多标签分类 | |
| 437.Learning Attraction Field Representation for Robust Line Segment Detection 学习吸引力场表示，用于鲁棒线段检测 | |
| 438.Learning Channel-Wise Interactions for Binary Convolutional Neural Networks 二元卷积神经网络的智能通道交互学习 | |
| 439.Learning Cross-Modal Embeddings With Adversarial Networks for Cooking Recipes and Food Images 使用对抗性网络学习跨模态嵌入来烹饪食谱和食物图像 | |
| 440.Learning for Single-Shot Confidence Calibration in Deep Neural Networks Through Stochastic Inferences 通过随机推断学习深度神经网络中的单发置信度校准。 | |
| 441.Learning From Noisy Labels by Regularized Estimation of Annotator Confusion 通过注释者混淆的正则估计从嘈杂的标签中学习 | |
| 442.Learning Image and Video Compression Through Spatial-Temporal Energy Compaction 通过时空能量压缩学习图像和视频压缩 | |
| 443.Learning Implicit Fields for Generative Shape Modeling 学习隐式字段以进行生成形状建模 | |
| 444.Learning Independent Object Motion From Unlabelled Stereoscopic Videos 从未贴标签的立体视频中学习独立的物体运动 | |
| 445.Learning Individual Styles of Conversational Gesture 学习会话式手势的个人风格 | |
| 446.Learning Joint Gait Representation via Quintuplet Loss Minimization 通过五重损失最小化学习联合步态表示 | |
| 447.Learning Joint Reconstruction of Hands and Manipulated Objects 学习手和操纵对象的联合重建 | |
| 448.Learning Linear Transformations for Fast Image and Video Style Transfer 学习线性变换以快速传输图像和视频样式 | |
| 449.Learning Loss for Active Learning 主动学习的学习损失 | |
| 450.Learning Monocular Depth Estimation Infusing Traditional Stereo Knowledge 融合传统立体知识的单眼深度估计学习 |
| 论文 | 概要 |
|---|---|
| 451.Learning Multi-Class Segmentations From Single-Class Datasets 从单类数据集学习多类细分 | |
| 452.Learning Non-Volumetric Depth Fusion Using Successive Reprojections 使用连续投影学习非体积深度融合 | |
| 453.Learning Not to Learn_ Training Deep Neural Networks With Biased Data 学会不学习_用有偏数据训练深度神经网络 | |
| 454.Learning Parallax Attention for Stereo Image Super-Resolution 学习视差注意以实现立体图像超分辨率 | |
| 455.Learning Personalized Modular Network Guided by Structured Knowledge 以结构化知识为指导学习个性化模块化网络 | |
| 456.Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting 学习金字塔上下文编码器网络以进行高质量的图像修复 | |
| 457.Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos 学习用于视频异常检测的骨架轨迹的规律性 | |
| 458.Learning Semantic Segmentation From Synthetic Data_ A Geometrically Guided Input-Output Adaptation Approach 从合成数据中学习语义分割_一种几何引导的输入输出自适应方法 | |
| 459.Learning Spatio-Temporal Representation With Local and Global Diffusion 通过局部和全局扩散学习时空表示 | |
| 460.Learning Structure-And-Motion-Aware Rolling Shutter Correction 学习结构和运动感知的卷帘快门校正 | |
| 461.Learning the Depths of Moving People by Watching Frozen People 通过观看冻结的人来学习移动人的深度 | |
| 462.Learning to Adapt for Stereo 学习适应立体声 | |
| 463.Learning to Cluster Faces on an Affinity Graph 学习在相似性图上聚类人脸 | |
| 464.Learning to Compose Dynamic Tree Structures for Visual Contexts 学习为视觉上下文编写动态树结构 | |
| 465.Learning to Detect Human-Object Interactions With Knowledge 学习检测人与知识之间的相互作用 | |
| 466.Learning to Explain With Complemental Examples 学习用补充示例进行解释 | |
| 467.Learning to Explore Intrinsic Saliency for Stereoscopic Video 学习探索立体视频的内在显着性 | |
| 468.Learning to Extract Flawless Slow Motion From Blurry Videos 学习从模糊视频中提取完美的慢动作 | |
| 469.Learning to Film From Professional Human Motion Videos 学习从专业的人类动作视频拍摄 | |
| 470.Learning to Learn From Noisy Labeled Data 学会从嘈杂的标签数据中学习 | |
| 471.Learning to Learn How to Learn_ Self-Adaptive Visual Navigation Using Meta-Learning 学习学习如何使用元学习进行自适应视觉导航 | |
| 472.Learning to Learn Image Classifiers With Visual Analogy 通过视觉类比学习学习图像分类器 | |
| 473.Learning to Learn Relation for Important People Detection in Still Images 学习学习关系以检测静止图像中的重要人物 | |
| 474.Learning to Localize Through Compressed Binary Maps 学习通过压缩二进制映射进行本地化 | |
| 475.Learning to Minify Photometric Stereo 学习最小化测光立体 | |
| 476.Learning to Quantize Deep Networks by Optimizing Quantization Intervals With Task Loss 通过优化具有任务丢失的量化间隔来学习量化深度网络 | |
| 477.Learning to Reconstruct People in Clothing From a Single RGB Camera 通过单个RGB相机学习如何重建服装中的人物 | |
| 478.Learning to Regress 3D Face Shape and Expression From an Image Without 3D Supervision 在没有3D监督的情况下学习从图像中回归3D人脸形状和表情 | |
| 479.Learning to Remember_ A Synaptic Plasticity Driven Framework for Continual Learning 学习记忆_突触可塑性驱动的持续学习框架 | |
| 480.Learning to Transfer Examples for Partial Domain Adaptation 学习转让部分域适配的示例 | |
| 481.Learning View Priors for Single-View 3D Reconstruction 学习视图先验以进行单视图3D重建 | |
| 482.Learning With Batch-Wise Optimal Transport Loss for 3D Shape Recognition 借助批处理明智的最佳运输损失进行学习，以实现3D形状识别 | |
| 483.Learning Without Memorizing 无需记忆即可学习 | |
| 484.Learning Words by Drawing Images 通过绘制图像学习单词 | |
| 485.Led3D_ A Lightweight and Efficient Deep Approach to Recognizing Low-Quality 3D Faces Led3D_一种轻量且高效的深度方法，可识别低质量的3D人脸 | |
| 486.Lending Orientation to Neural Networks for Cross-View Geo-Localization 面向神经网络的借阅方向以实现跨视图地理定位 | |
| 487.Leveraging Heterogeneous Auxiliary Tasks to Assist Crowd Counting 利用异构辅助任务协助人群计数 | |
| 488.Leveraging Shape Completion for 3D Siamese Tracking 利用形状完成功能进行3D连体跟踪 | |
| 489.Libra R-CNN_ Towards Balanced Learning for Object Detection 天秤座R-CNN_面向目标学习的平衡学习 | |
| 490.Lifting Vectorial Variational Problems_ A Natural Formulation Based on Geometric Measure Theory and Discrete Exterior Calculus 提升矢量变分问题_基于几何测度理论和离散外部演算的自然公式 | |
| 491.Linkage Based Face Clustering via Graph Convolution Network 通过图卷积网络进行基于链接的人脸聚类 | |
| 492.Listen to the Image 听图片 | |
| 493.LiveSketch_ Query Perturbations for Guided Sketch-Based Visual Search 引导式基于草图的视觉搜索的LiveSketch_查询扰动 | |
| 494.Local Relationship Learning With Person-Specific Shape Regularization for Facial Action Unit Detection 局部关系学习与特定于人的形状规则化的面部动作单元检测 | |
| 495.Local Temporal Bilinear Pooling for Fine-Grained Action Parsing 局部时间双线性池用于细粒度动作解析 | |
| 496.Local to Global Learning_ Gradually Adding Classes for Training Deep Neural Networks 从本地到全球学习_逐步增加培训深度神经网络的课程 | |
| 497.Locating Objects Without Bounding Boxes 定位没有边界框的对象 | |
| 498.LO-Net_ Deep Real-Time Lidar Odometry LO-Net_实时激光雷达里程表 | |
| 499.Long-Term Feature Banks for Detailed Video Understanding 长期功能库，用于详细了解视频 | |
| 500.Look Back and Predict Forward in Image Captioning 回顾和预测图像字幕 |
| 论文 | 概要 |
|---|---|
| 501.Low-Rank Laplacian-Uniform Mixed Model for Robust Face Recognition 鲁棒人脸识别的低秩拉普拉斯均匀混合模型 | |
| 502.Low-Rank Tensor Completion With a New Tensor Nuclear Norm Induced by Invertible Linear Transforms 可逆线性变换引起的具有新张量核范数的低秩张量完成 | |
| 503.LP-3DCNN_ Unveiling Local Phase in 3D Convolutional Neural Networks LP-3DCNN_在3D卷积神经网络中展现局部相位 | |
| 504.LSTA_ Long Short-Term Attention for Egocentric Action Recognition LSTA_长期关注自我中心行为识别 | |
| 505.MAGSAC_ Marginalizing Sample Consensus MAGSAC_边缘化样本共识 | |
| 506.MAN_ Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment MAN_ Moment Alignment Network用于通过迭代图调整进行自然语言矩检索 | |
| 507.ManTra-Net_ Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features ManTra-Net_具有异常特征的图像伪造的检测和定位操纵跟踪网络 | |
| 508.MAP Inference via Block-Coordinate Frank-Wolfe Algorithm 通过块坐标Frank-Wolfe算法进行MAP推理 | |
| 509.MARS_ Motion-Augmented RGB Stream for Action Recognition MARS_用于动作识别的运动增强RGB流 | |
| 510.Mask-Guided Portrait Editing With Conditional GANs 使用条件GAN进行蒙版引导的人像编辑 | |
| 511.MaxpoolNMS_ Getting Rid of NMS Bottlenecks in Two-Stage Object Detectors MaxpoolNMS_消除两阶段对象检测器中的NMS瓶颈 | |
| 512.MBS_ Macroblock Scaling for CNN Model Reduction MBS_用于减少CNN模型的宏块缩放 | |
| 513.Memory-Attended Recurrent Network for Video Captioning 用于视频字幕的内存专用循环网络 | |
| 514.Memory in Memory_ A Predictive Neural Network for Learning Higher-Order Non-Stationarity From Spatiotemporal Dynamics 记忆中的记忆_从时空动力学中学习高阶非平稳性的预测神经网络 | |
| 515.MetaCleaner_ Learning to Hallucinate Clean Representations for Noisy-Labeled Visual Recognition MetaCleaner_学习为噪声标记的视觉识别幻化干净的表示形式 | |
| 516.Meta-Learning With Differentiable Convex Optimization 具有可微凸优化的元学习 | |
| 517.Meta-SR_ A Magnification-Arbitrary Network for Super-Resolution Meta-SR_用于超分辨率的放大倍数任意网络 | |
| 518.Meta-Transfer Learning for Few-Shot Learning 元转移学习，少量学习 | |
| 519.Metric Learning for Image Registration 用于图像配准的度量学习 | |
| 520.MFAS_ Multimodal Fusion Architecture Search MFAS_多模式融合架构搜索 | |
| 521.Mind Your Neighbours_ Image Annotation With Metadata Neighbourhood Graph Co-Attention Networks 注意您的邻居_使用元数据邻居图共同注意网络进行图像注释 | |
| 522.Minimal Solvers for Mini-Loop Closures in 3D Multi-Scan Alignment 3D多扫描对准中的最小回路闭合的最小解算器 | |
| 523.Min-Max Statistical Alignment for Transfer Learning 迁移学习的最小-最大统计比对 | |
| 524.MirrorGAN_ Learning Text-To-Image Generation by Redescription MirrorGAN_通过重新定义学习文本到图像的生成 | |
| 525.Mixed Effects Neural Networks (MeNets) With Applications to Gaze Estimation 混合效应神经网络（MeNets）及其在凝视估计中的应用 | |
| 526.Mixture Density Generative Adversarial Networks 混合密度生成对抗网络 | |
| 527.MMFace_ A Multi-Metric Regression Network for Unconstrained Face Reconstruction MMFace_用于无约束人脸重建的多指标回归网络 | |
| 528.Model-Blind Video Denoising via Frame-To-Frame Training 通过逐帧训练进行模型盲视频降噪 | |
| 529.Modeling Local Geometric Structure of 3D Point Clouds Using Geo-CNN 使用Geo-CNN建模3D点云的局部几何结构 | |
| 530.Modeling Point Clouds With Self-Attention and Gumbel Subset Sampling 使用自注意力和Gumbel子集采样建模点云 | |
| 531.Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis 寻求模式对抗生成对抗网络进行多元图像合成 | |
| 532.Modularized Textual Grounding for Counterfactual Resilience 模块化的文本基础可增强反事实抵御能力 | |
| 533.Modulating Image Restoration With Continual Levels via Adaptive Feature Modification Layers 通过自适应特征修改层以连续级别调制图像恢复 | |
| 534.Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction 利用精确的提案和形状重构进行单眼3D对象检测 | |
| 535.MOTS_ Multi-Object Tracking and Segmentation MOTS_多对象跟踪和细分 | |
| 536.Moving Object Detection Under Discontinuous Change in Illumination Using Tensor Low-Rank and Invariant Sparse Decomposition 张量低秩和不变稀疏分解在光照不连续变化下的运动目标检测 | |
| 537.MSCap_ Multi-Style Image Captioning With Unpaired Stylized Text MSCap_带有未配对风格文本的多样式图像字幕 | |
| 538.MS-TCN_ Multi-Stage Temporal Convolutional Network for Action Segmentation MS-TCN_多阶段时间卷积网络用于动作分割 | |
| 539.Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection 人脸呈现攻击检测的多专业鉴别深度域综合 | |
| 540.Multi-Level Context Ultra-Aggregation for Stereo Matching 用于立体声匹配的多级上下文超聚合 | |
| 541.Multi-Level Multimodal Common Semantic Space for Image-Phrase Grounding 图像相接地的多级多模态公共语义空间 | |
| 542.Multimodal Explanations by Predicting Counterfactuality in Videos 通过预测视频中的反事实来进行多模式解释 | |
| 543.Multi-Scale Geometric Consistency Guided Multi-View Stereo 多尺度几何一致性引导的多视图立体 | |
| 544.Multi-Similarity Loss With General Pair Weighting for Deep Metric Learning 深度度量学习中具有通用对加权的多相似损失 | |
| 545.Multi-Source Weak Supervision for Saliency Detection 显着性检测的多源弱监督 | |
| 546.Multispectral Imaging for Fine-Grained Recognition of Powders on Complex Backgrounds 复杂背景下粉末的细粒度识别的多光谱成像 | |
| 547.Multi-Step Prediction of Occupancy Grid Maps With Recurrent Neural Networks 递归神经网络的占用网格图多步预测 | |
| 548.Multi-Target Embodied Question Answering 多目标体现式问答 | |
| 549.Multi-Task Learning of Hierarchical Vision-Language Representation 分层视觉语言表示的多任务学习 | |
| 550.Multi-Task Self-Supervised Object Detection via Recycling of Bounding Box Annotations 通过边界框注释的回收进行多任务自我监督对象检测 |
| 论文 | 概要 |
|---|---|
| 551.MUREL_ Multimodal Relational Reasoning for Visual Question Answering MUREL_视觉问题回答的多峰关系推理 | |
| 552.Mutual Learning of Complementary Networks via Residual Correction for Improving Semi-Supervised Classification 通过残差校正互补网络的相互学习，以改善半监督分类 | |
| 553.Natural and Realistic Single Image Super-Resolution With Explicit Natural Manifold Discrimination 自然和逼真的单图像超分辨率，具有明显的自然歧管区分 | |
| 554.NDDR-CNN_ Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction 通过神经判别维数减少多任务CNN中的NDDR-CNN_分层特征融合 | |
| 555.Neighbourhood Watch_ Referring Expression Comprehension via Language-Guided Graph Attention Networks 邻里观察_通过语言指导的图表注意网络引用表达理解 | |
| 556.Nesti-Net_ Normal Estimation for Unstructured 3D Point Clouds Using Convolutional Neural Networks 使用卷积神经网络的非结构化3D点云的Nesti-Net_法线估计 | |
| 557.NetTailor_ Tuning the Architecture, Not Just the Weights NetTailor_调整架构，而不仅仅是权重 | |
| 558.Networks for Joint Affine and Non-Parametric Image Registration 联合仿射和非参数图像配准网络 | |
| 559.Neural Rejuvenation_ Improving Deep Network Training by Enhancing Computational Resource Utilization 神经复兴_通过提高计算资源利用率来改善深度网络培训 | |
| 560.Neural Sequential Phrase Grounding (SeqGROUND) 神经顺序短语接地（SeqGROUND） | |
| 561.Neural Task Graphs_ Generalizing to Unseen Tasks From a Single Video Demonstration 神经任务图_从单个视频演示中推广到看不见的任务 | |
| 562.Noise-Aware Unsupervised Deep Lidar-Stereo Fusion 无噪声感知的深层激光雷达-立体声融合 | |
| 563.Noise-Tolerant Paradigm for Training Face Recognition CNNs 训练人脸识别CNN的耐噪范式 | |
| 564.Non-Adversarial Image Synthesis With Generative Latent Nearest Neighbors 生成潜在最近邻的非专业图像合成 | |
| 565.Normalized Diversification 标准化多元化 | |
| 566.Not All Areas Are Equal_ Transfer Learning for Semantic Segmentation via Hierarchical Region Selection 并非所有区域都是平等的-通过分层区域选择进行语义分割的转移学习 | |
| 567.Not All Frames Are Equal_ Weakly-Supervised Video Grounding With Contextual Similarity and Visual Clustering Losses 并非所有帧都是相等的_具有上下文相似性和视觉聚类损失的弱监督视频接地 | |
| 568.Not Using the Car to See the Sidewalk – Quantifying and Controlling the Effects of Context in Classification and Segmentation 不要用汽车看人行道-量化和控制上下文在分类和分割中的作用。 | |
| 569.Object Detection With Location-Aware Deformable Convolution and Backward Attention Filtering 具有位置感知的可变形卷积和后向注意过滤的对象检测 | |
| 570.Object Discovery in Videos as Foreground Motion Clustering 视频中的对象发现作为前景运动聚类 | |
| 571.Object-Driven Text-To-Image Synthesis via Adversarial Training 通过对抗训练进行对象驱动的文本到图像合成 | |
| 572.Object Instance Annotation With Deep Extreme Level Set Evolution 具有深度极限级别集演化的对象实例注释 | |
| 573.Occupancy Networks_ Learning 3D Reconstruction in Function Space 占用网络_在功能空间中学习3D重建 | |
| 574.OCGAN_ One-Class Novelty Detection Using GANs With Constrained Latent Representations OCGAN_使用受约束的潜在表示形式的GAN进行一类新颖性检测 | |
| 575.Octree Guided CNN With Spherical Kernels for 3D Point Clouds Octree引导的带球形核的CNN用于3D点云 | |
| 576.ODE-Inspired Network Design for Single Image Super-Resolution 受ODE启发的网络设计，可实现单图像超分辨率 | |
| 577.OICSR_ Out-In-Channel Sparsity Regularization for Compact Deep Neural Networks OICSR_紧凑型深度神经网络的通道外稀疏正则化 | |
| 578.OK-VQA_ A Visual Question Answering Benchmark Requiring External Knowledge OK-VQA_需要外部知识的视觉问题回答基准 | |
| 579.On Exploring Undetermined Relationships for Visual Relationship Detection 视觉关系检测中不确定关系的探索 | |
| 580.On Finding Gray Pixels 关于寻找灰色像素 | |
| 581.On Implicit Filter Level Sparsity in Convolutional Neural Networks 卷积神经网络中隐式滤波器级稀疏性 | |
| 582.On Learning Density Aware Embeddings 关于学习密度感知嵌入 | |
| 583.Online High Rank Matrix Completion 在线高等级矩阵完成 | |
| 584.On the Continuity of Rotation Representations in Neural Networks 神经网络中旋转表示的连续性 | |
| 585.On the Intrinsic Dimensionality of Image Representations 论图像表征的内在维度 | |
| 586.On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions 深卷积网络对傅立叶基函数方向的结构敏感性 | |
| 587.On Zero-Shot Recognition of Generic Objects 通用对象的零射识别 | |
| 588.Orthogonal Decomposition Network for Pixel-Wise Binary Classification 像素分解二进制分类的正交分解网络 | |
| 589.Out-Of-Distribution Detection for Generalized Zero-Shot Action Recognition 广义零发动作识别的分布外检测 | |
| 590.Overcoming Limitations of Mixture Density Networks_ A Sampling and Fitting Framework for Multimodal Future Prediction 克服混合密度网络的局限性_多峰未来预测的抽样和拟合框架 | |
| 591.P3SGD_ Patient Privacy Preserving SGD for Regularizing Deep CNNs in Pathological Image Classification P3SGD_保留患者隐私SGD以在病理图像分类中对深层CNN进行规则化 | |
| 592.PA3D_ Pose-Action 3D Machine for Video Recognition PA3D_用于视频识别的Pose-Action 3D机器 | |
| 593.Panoptic Segmentation 全景分割 | |
| 594.Parallel Optimal Transport GAN 并行最优传输 | |
| 595.Parametric Noise Injection_ Trainable Randomness to Improve Deep Neural Network Robustness Against Adversarial Attack 参数化噪声注入_可训练的随机性，以提高针对对抗攻击的深度神经网络的鲁棒性 | |
| 596.Parsing R-CNN for Instance-Level Human Analysis 解析R-CNN以进行实例级人员分析 | |
| 597.PartNet_ A Recursive Part Decomposition Network for Fine-Grained and Hierarchical Shape Segmentation PartNet_用于细粒度和分级形状分割的递归零件分解网络 | |
| 598.Part-Regularized Near-Duplicate Vehicle Re-Identification 部分规整的近乎重复的车辆重新识别 | |
| 599.Patch-Based Discriminative Feature Learning for Unsupervised Person Re-Identification 基于补丁的判别特征学习用于无监督人员的重新识别 | |
| 600.Patch-Based Progressive 3D Point Set Upsampling 基于补丁的渐进3D点设置向上采样 |
| 论文 | 概要 |
|---|---|
| 601.Path-Invariant Map Networks 路径不变地图网络 | |
| 602.Pattern-Affinitive Propagation Across Depth, Surface Normal and Semantic Segmentation 跨深度，表面法线和语义分割的模式相似性传播 | |
| 603.Pay Attention! - Robustifying a Deep Visuomotor Policy Through Task-Focused Visual Attention 请注意！ -通过以任务为中心的视觉注意力强化深层运动策略 | |
| 604.PCAN_ 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval 使用上下文信息进行基于点云的PCAN_ 3D注意图学习 | |
| 605.Pedestrian Detection With Autoregressive Network Phases 具有自回归网络阶段的行人检测 | |
| 606.Peeking Into the Future_ Predicting Future Person Activities and Locations in Videos 展望未来_在视频中预测未来人的活动和位置 | |
| 607.PEPSI _ Fast Image Inpainting With Parallel Decoding Network PEPSI _具有并行解码网络的快速图像修复 | |
| 608.Perceive Where to Focus_ Learning Visibility-Aware Part-Level Features for Partial Person Re-Identification 感知重点在哪里_学习可视性部分级功能以重新识别部分人员 | |
| 609.Perturbation Analysis of the 8-Point Algorithm_ A Case Study for Wide FoV Cameras 8点算法的摄动分析_以宽FoV摄像机为例 | |
| 610.PifPaf_ Composite Fields for Human Pose Estimation PifPaf_用于人体姿势估计的复合字段 | |
| 611.Pixel-Adaptive Convolutional Neural Networks 像素自适应卷积神经网络 | |
| 612.PMS-Net_ Robust Haze Removal Based on Patch Map for Single Images 基于补丁图的PMS-Net_雾霾鲁棒去除 | |
| 613.Point Cloud Oversegmentation With Graph-Structured Deep Metric Learning 图结构深度度量学习的点云超分割 | |
| 614.PointConv_ Deep Convolutional Networks on 3D Point Clouds PointConv_ 3D点云上的深度卷积网络 | |
| 615.PointFlowNet_ Learning Representations for Rigid Motion Estimation From Point Clouds PointFlowNet_从点云中学习用于刚性运动估计的表示形式 | |
| 616.Pointing Novel Objects in Image Captioning 在图像字幕中指向新对象 | |
| 617.PointNetLK_ Robust & Efficient Point Cloud Registration Using PointNet PointNetLK_使用PointNet进行可靠，高效的点云注册 | |
| 618.PointPillars_ Fast Encoders for Object Detection From Point Clouds PointPillars_用于从点云进行对象检测的快速编码器 | |
| 619.PointRCNN_ 3D Object Proposal Generation and Detection From Point Cloud PointRCNN_从点云生成和检测3D对象提案 | |
| 620.Point-To-Pose Voting Based Hand Pose Estimation Using Residual Permutation Equivariant Layer 使用残差置换等变层的基于点对点投票的手势估计 | |
| 621.PointWeb_ Enhancing Local Neighborhood Features for Point Cloud Processing PointWeb_增强点云处理的本地邻域功能 | |
| 622.Polarimetric Camera Calibration Using an LCD Monitor 使用LCD监视器的偏振相机校准 | |
| 623.Polynomial Representation for Persistence Diagram 持久图的多项式表示 | |
| 624.Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval 用于跨模态检索的多义视觉语义嵌入 | |
| 625.PoseFix_ Model-Agnostic General Human Pose Refinement Network PoseFix_与模型无关的通用人体姿势优化网络 | |
| 626.Practical Full Resolution Learned Lossless Image Compression 实用的全分辨率学习无损图像压缩 | |
| 627.Predicting Future Frames Using Retrospective Cycle GAN 使用追溯周期GAN预测未来框架 | |
| 628.Privacy Preserving Image-Based Localization 隐私保护基于图像的本地化 | |
| 629.Privacy Protection in Street-View Panoramas Using Depth and Multi-View Imagery 使用深度和多视图图像的街景全景图中的隐私保护 | |
| 630.Probabilistic End-To-End Noise Correction for Learning With Noisy Labels 带有噪声标签的学习的概率端到端噪声校正 | |
| 631.Probabilistic Permutation Synchronization Using the Riemannian Structure of the Birkhoff Polytope 使用Birkhoff多面体的黎曼结构的概率置换同步 | |
| 632.Progressive Attention Memory Network for Movie Story Question Answering 电影故事问答的渐进式注意力记忆网络 | |
| 633.Progressive Ensemble Networks for Zero-Shot Recognition 渐进集成网络用于零发芽识别 | |
| 634.Progressive Image Deraining Networks_ A Better and Simpler Baseline 渐进式图像排水网络_更好，更简单的基准 | |
| 635.Progressive Pose Attention Transfer for Person Image Generation 用于人像生成的渐进式姿态注意转移 | |
| 636.Propagation Mechanism for Deep and Wide Neural Networks 深度和广域神经网络的传播机制 | |
| 637.Pseudo-LiDAR From Visual Depth Estimation_ Bridging the Gap in 3D Object Detection for Autonomous Driving 视觉深度估计的伪LiDAR_弥合自动驾驶3D对象检测中的差距 | |
| 638.Pushing the Envelope for RGB-Based Dense 3D Hand Pose Estimation via Neural Rendering 通过神经渲染推动基于RGB的密集3D手姿势估计的信封 | |
| 639.PVNet_ Pixel-Wise Voting Network for 6DoF Pose Estimation PVNet_用于6DoF姿势估计的像素明智投票网络 | |
| 640.Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training 通过多损失动态训练对金字塔形人进行重新识别 | |
| 641.Pyramid Feature Attention Network for Saliency Detection 显着性检测的金字塔特征注意网络 | |
| 642.QATM_ Quality-Aware Template Matching for Deep Learning QATM_深度学习的质量感知模板匹配 | |
| 643.Quantization Networks 量化网络 | |
| 644.Query-Guided End-To-End Person Search 查询引导的端到端人员搜索 | |
| 645.R2GAN_ Cross-Modal Recipe Retrieval With Generative Adversarial Network R2GAN_带有生成对抗网络的跨模态食谱检索 | |
| 646.R3 Adversarial Network for Cross Model Face Recognition 用于跨模型人脸识别的R3对抗网络 | |
| 647.Radial Distortion Triangulation 径向变形三角剖分 | |
| 648.Ranked List Loss for Deep Metric Learning 深度度量学习的排名列表损失 | |
| 649.Rare Event Detection Using Disentangled Representation Learning 使用解缠表示学习进行稀有事件检测 | |
| 650.RAVEN_ A Dataset for Relational and Analogical Visual REasoNing RAVEN_关系和类比视觉识别的数据集 |
| 论文 | 概要 |
|---|---|
| 651.Real-Time Self-Adaptive Deep Stereo 实时自适应深度立体声 | |
| 652.Reasoning-RCNN_ Unifying Adaptive Global Reasoning Into Large-Scale Object Detection Reasoning-RCNN_将自适应全局推理统一到大规模目标检测中 | |
| 653.Recurrent Back-Projection Network for Video Super-Resolution 用于视频超分辨率的循环反投影网络 | |
| 654.Recurrent MVSNet for High-Resolution Multi-View Stereo Depth Inference 递归MVSNet用于高分辨率多视图立体声深度推断 | |
| 655.Recurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and Depth 循环神经网络用于（非）有监督的单眼视频视觉测程和深度学习 | |
| 656.Recurrent Neural Networks With Intra-Frame Iterations for Video Deblurring 具有帧内迭代的递归神经网络用于视频去模糊 | |
| 657.Recursive Visual Attention in Visual Dialog 视觉对话中的递归视觉注意 | |
| 658.Refine and Distill_ Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation 提炼和蒸馏_利用循环不一致和知识蒸馏进行无监督单眼深度估计 | |
| 659.Reflection Removal Using a Dual-Pixel Sensor 使用双像素传感器消除反射 | |
| 660.Reflective and Fluorescent Separation Under Narrow-Band Illumination 窄带照明下的反射和荧光分离 | |
| 661.Regularizing Activation Distribution for Training Binarized Deep Networks 规范化激活分布以训练二值化深度网络 | |
| 662.Re-Identification Supervised Texture Generation 重新识别监督纹理生成 | |
| 663.Re-Identification With Consistent Attentive Siamese Networks 使用一致的细心连体网络进行重新识别 | |
| 664.Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation 增强的跨模态匹配和自我监督的模仿学习，用于视觉语言导航 | |
| 665.Relational Action Forecasting 关系行动预测 | |
| 666.Relational Knowledge Distillation 关系知识提炼 | |
| 667.Relation-Shape Convolutional Neural Network for Point Cloud Analysis 关系形状卷积神经网络的点云分析 | |
| 668.Reliable and Efficient Image Cropping_ A Grid Anchor Based Approach 可靠高效的图像裁剪_基于网格锚点的方法 | |
| 669.RENAS_ Reinforced Evolutionary Neural Architecture Search RENAS_增强型进化神经架构搜索 | |
| 670.REPAIR_ Removing Representation Bias by Dataset Resampling REPAIR_通过数据集重采样消除表示偏差 | |
| 671.RepNet_ Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation RepNet_用于3D人体姿态估计的对抗性投影网络的弱监督训练 | |
| 672.Representation Flow for Action Recognition 动作识别的表示流程 | |
| 673.RePr_ Improved Training of Convolutional Filters RePr_卷积滤波器的改进训练 | |
| 674.Re-Ranking via Metric Fusion for Object Retrieval and Person Re-Identification 通过度量融合实现重新排名，以进行对象检索和人员重新识别 | |
| 675.Residual Networks for Light Field Image Super-Resolution 用于光场图像超分辨率的残差网络 | |
| 676.Residual Regression With Semantic Prior for Crowd Counting 带有语义先验的残差回归计算人群 | |
| 677.RES-PCA_ A Scalable Approach to Recovering Low-Rank Matrices RES-PCA_一种用于恢复低秩矩阵的可扩展方法 | |
| 678.Rethinking Knowledge Graph Propagation for Zero-Shot Learning 对零散学习的知识图传播的重新思考 | |
| 679.Rethinking the Evaluation of Video Summaries 重新思考视频摘要的评估 | |
| 680.Retrieval-Augmented Convolutional Neural Networks Against Adversarial Examples 对抗示例的检索增强卷积神经网络 | |
| 681.Reversible GANs for Memory-Efficient Image-To-Image Translation 可逆GAN，可实现内存高效的图像到图像转换 | |
| 682.Revisiting Local Descriptor Based Image-To-Class Measure for Few-Shot Learning 重新研究基于局部描述符的图像到类测量方法，以进行少量学习 | |
| 683.Revisiting Perspective Information for Efficient Crowd Counting 回顾透视信息以进行有效的人群计数 | |
| 684.Revisiting Self-Supervised Visual Representation Learning 回顾自我监督的视觉表示学习 | |
| 685.RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion 基于RGBD的3D语义场景完成维度分解残差网络。 | |
| 686.RL-GAN-Net_ A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion RL-GAN-Net_由增强学习代理控制的GAN网络，用于实时点云形状完成 | |
| 687.Rob-GAN_ Generator, Discriminator, and Adversarial Attacker Rob-GAN_生成器，鉴别器和对抗攻击者 | |
| 688.Robust Facial Landmark Detection via Occlusion-Adaptive Deep Networks 通过遮挡自适应深度网络进行鲁棒的面部地标检测 | |
| 689.Robust Histopathology Image Analysis_ To Label or to Synthesize_ 强大的组织病理学图像分析_标记或合成_ | |
| 690.Robustness of 3D Deep Learning in an Adversarial Setting 在对抗环境下3D深度学习的稳健性 | |
| 691.Robustness Verification of Classification Deep Neural Networks via Linear Programming 通过线性规划对分类深度神经网络进行鲁棒性验证 | |
| 692.Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes 基于鲁棒点云的大型室外场景重构 | |
| 693.Robust Subspace Clustering With Independent and Piecewise Identically Distributed Noise Modeling 具有独立和分段相同分布噪声模型的鲁棒子空间聚类 | |
| 694.Robust Video Stabilization by Optimization in CNN Weight Space 通过优化CNN权重空间实现鲁棒的视频稳定 | |
| 695.ROI Pooled Correlation Filters for Visual Tracking 用于视觉跟踪的ROI池相关过滤器 | |
| 696.Rules of the Road_ Predicting Driving Behavior With a Convolutional Model of Semantic Interactions 道路规则_语义交互卷积模型预测驾驶行为 | |
| 697.S4Net_ Single Stage Salient-Instance Segmentation S4Net_单阶段显着实例分割 | |
| 698.Salient Object Detection With Pyramid Attention and Salient Edges 具有金字塔注意和显着边缘的显着物体检测 | |
| 699.Sampling Techniques for Large-Scale Object Detection From Sparsely Annotated Objects 从稀疏注释对象中进行大规模对象检测的采样技术 | |
| 700.Scan2Mesh_ From Unstructured Range Scans to 3D Meshes Scan2Mesh_从非结构化范围扫描到3D网格 |
| 论文 | 概要 |
|---|---|
| 701.Scene Graph Generation With External Knowledge and Image Reconstruction 具有外部知识和图像重构的场景图生成 | |
| 702.Scene Parsing via Integrated Classification Model and Variance-Based Regularization 通过集成分类模型和基于方差的正则化进行场景解析 | |
| 703.Seamless Scene Segmentation 无缝场景分割 | |
| 704.Searching for a Robust Neural Architecture in Four GPU Hours 在四个GPU小时内搜索强大的神经架构 | |
| 705.Second-Order Attention Network for Single Image Super-Resolution 单图像超分辨率的二阶注意力网络 | |
| 706.SeerNet_ Predicting Convolutional Neural Network Feature-Map Sparsity Through Low-Bit Quantization SeerNet_通过低位量化预测卷积神经网络特征图稀疏性 | |
| 707.Selective Sensor Fusion for Neural Visual-Inertial Odometry 用于神经视觉惯性里程表的选择性传感器融合 | |
| 708.Self-Calibrating Deep Photometric Stereo Networks 自校准深光度立体网络 | |
| 709.Self-Critical N-Step Training for Image Captioning 图像字幕的自关键N步训练 | |
| 710.SelFlow_ Self-Supervised Learning of Optical Flow SelFlow_光流的自我监督学习 | |
| 711.Self-Supervised 3D Hand Pose Estimation Through Training by Fitting 通过拟合训练进行自我监督的3D手姿势估计 | |
| 712.Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Tracking 用于单眼性能跟踪的高保真人脸模型的自我监督自适应 | |
| 713.Self-Supervised Convolutional Subspace Clustering Network 自监督卷积子空间聚类网络 | |
| 714.Self-Supervised GANs via Auxiliary Rotation Loss 通过辅助旋转损失进行自我监督的GAN | |
| 715.Self-Supervised Learning of 3D Human Pose Using Multi-View Geometry 使用多视图几何进行3D人体姿势的自我监督学习 | |
| 716.Self-Supervised Learning via Conditional Motion Propagation 通过条件运动传播进行自我监督学习 | |
| 717.Self-Supervised Representation Learning by Rotation Feature Decoupling 旋转特征解耦的自我监督表示学习 | |
| 718.Self-Supervised Representation Learning From Videos for Facial Action Unit Detection 从视频中进行自我监督表示学习，以进行面部动作单元检测 | |
| 719.Self-Supervised Spatiotemporal Learning via Video Clip Order Prediction 通过视频剪辑顺序预测进行自我指导的时空学习 | |
| 720.Self-Supervised Spatio-Temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics 通过预测运动和外观统计信息进行视频的自监督时空表示学习 | |
| 721.Semantic Alignment_ Finding Semantically Consistent Ground-Truth for Facial Landmark Detection 语义对齐_寻找语义一致的地面真相以检测人脸地标 | |
| 722.Semantically Aligned Bias Reducing Zero Shot Learning 语义一致的偏差减少零击学习 | |
| 723.Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-Based Image Retrieval 语义为零的基于草图的图像检索的成对配对循环一致性 | |
| 724.Semantic Attribute Matching Networks 语义属性匹配网络 | |
| 725.Semantic Component Decomposition for Face Attribute Manipulation 人脸属性操纵的语义成分分解 | |
| 726.Semantic Correlation Promoted Shape-Variant Context for Segmentation 语义相关性促进了形状变异上下文的分割 | |
| 727.Semantic Projection Network for Zero- and Few-Label Semantic Segmentation 零和很少标签语义分割的语义投影网络 | |
| 728.Semantics Disentangling for Text-To-Image Generation 语义解开以生成文本到图像 | |
| 729.Semi-Supervised Learning With Graph Learning-Convolutional Networks 图学习卷积网络的半监督学习 | |
| 730.Semi-Supervised Transfer Learning for Image Rain Removal 半监督转移学习，用于图像除雨 | |
| 731.Sensitive-Sample Fingerprinting of Deep Neural Networks 深度神经网络的敏感样本指纹 | |
| 732.Sequence-To-Sequence Domain Adaptation Network for Robust Text Image Recognition 序列到序列域自适应网络，用于鲁棒的文本图像识别 | |
| 733.Shape2Motion_ Joint Analysis of Motion Parts and Attributes From 3D Shapes Shape2Motion_来自3D形状的运动零件和属性的联合分析 | |
| 734.Shape Robust Text Detection With Progressive Scale Expansion Network 渐进式规模扩展网络的形状鲁棒文本检测 | |
| 735.Shapes and Context_ In-The-Wild Image Synthesis & Manipulation 形状和上下文_野外图像合成与处理 | |
| 736.ShieldNets_ Defending Against Adversarial Attacks Using Probabilistic Adversarial Robustness ShieldNets_使用概率对抗性鲁棒性防御对抗性攻击 | |
| 737.Shifting More Attention to Video Salient Object Detection 将更多注意力转移到视频显着目标检测上 | |
| 738.Show, Control and Tell_ A Framework for Generating Controllable and Grounded Captions Show，Control和Tell_生成可控制字幕和接地字幕的框架 | |
| 739.Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking 用于实时视觉跟踪的暹罗级联区域投标网络 | |
| 740.SiCloPe_ Silhouette-Based Clothed People SiCloPe_基于轮廓的穿衣人 | |
| 741.Side Window Filtering 侧窗过滤 | |
| 742.Signal-To-Noise Ratio_ A Robust Distance Metric for Deep Metric Learning 信噪比_深度度量学习的鲁棒距离度量 | |
| 743.SIGNet_ Semantic Instance Aided Unsupervised 3D Geometry Perception SIGNet_语义实例辅助的无监督3D几何感知 | |
| 744.Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation 用于3D室内导航的Sim-Real联合钢筋转移 | |
| 745.Sim-To-Real via Sim-To-Sim_ Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks 通过Sim-To-Sim_实现Sim-To-Real_通过随机化至规范化的自适应网络实现数据有效的机器人抓取 | |
| 746.Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network Using Truncated Gaussian Approximation 使用截断的高斯近似同时优化三元神经网络的权重和量化器 | |
| 747.Single-Frame Regularization for Temporally Stable CNNs 暂时稳定的CNN的单帧正则化 | |
| 748.Single Image Depth Estimation Trained via Depth From Defocus Cues 通过Defocus线索的深度训练单图像深度估计 | |
| 749.Single Image Deraining_ A Comprehensive Benchmark Analysis 单图像排空_综合基准分析 | |
| 750.Single Image Reflection Removal Beyond Linearity 超出线性的单图像反射去除 |
| 论文 | 概要 |
|---|---|
| 751.Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements 去除单一图像反射，利用错误的训练数据和网络增强功能 | |
| 752.Skeleton-Based Action Recognition With Directed Graph Neural Networks 有向图神经网络的基于骨骼的动作识别 | |
| 753.SketchGAN_ Joint Sketch Completion and Recognition With Generative Adversarial Network SketchGAN_生成对抗网络的联合草图完成和识别 | |
| 754.Sliced Wasserstein Generative Models 切片的Wasserstein生成模型 | |
| 755.Snapshot Distillation_ Teacher-Student Optimization in One Generation 快照精馏_一代中师生的优化 | |
| 756.Social-IQ_ A Question Answering Benchmark for Artificial Social Intelligence Social-IQ_人工社会智能的问答基准 | |
| 757.SoDeep_ A Sorting Deep Net to Learn Ranking Loss Surrogates SoDeep_排序深度网络以学习排名损失替代 | |
| 758.Soft Labels for Ordinal Regression 序数回归的软标签 | |
| 759.SoPhie_ An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints SoPhie_细心的GAN，用于预测符合社会和身体约束的路径 | |
| 760.SOSNet_ Second Order Similarity Regularization for Local Descriptor Learning SOSNet_用于本地描述符学习的二阶相似性正则化 | |
| 761.Spatial Attentive Single-Image Deraining With a High Quality Real Rain Dataset 具有高质量真实降雨数据集的空间注意力单图像消除 | |
| 762.Spatial-Aware Graph Relation Network for Large-Scale Object Detection 用于大规模目标检测的空间感知图关系网络 | |
| 763.Spatial Fusion GAN for Image Synthesis 用于图像合成的空间融合GAN | |
| 764.Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning 时空动态和语义属性丰富的视频字幕视觉编码 | |
| 765.Spatio-Temporal Video Re-Localization by Warp LSTM 通过Warp LSTM进行时空视频重新定位 | |
| 766.Spectral Metric for Dataset Complexity Assessment 数据集复杂度评估的光谱指标 | |
| 767.Spectral Reconstruction From Dispersive Blur_ A Novel Light Efficient Spectral Imager 色散模糊的光谱重构_新型高效光光谱成像仪 | |
| 768.Speech2Face_ Learning the Face Behind a Voice Speech2Face_学习声音背后的面孔 | |
| 769.Sphere Generative Adversarial Network Based on Geometric Moment Matching 基于几何矩匹配的球体生成对抗网络 | |
| 770.Spherical Fractal Convolutional Neural Networks for Point Cloud Recognition 球面分形卷积神经网络的点云识别 | |
| 771.Spherical Regression_ Learning Viewpoints, Surface Normals and 3D Rotations on N-Spheres 球形回归_学习N球上的视点，表面法线和3D旋转 | |
| 772.SPM-Tracker_ Series-Parallel Matching for Real-Time Visual Object Tracking SPM-Tracker_系列-并行匹配，用于实时视觉对象跟踪 | |
| 773.SpotTune_ Transfer Learning Through Adaptive Fine-Tuning SpotTune_通过自适应微调进行转移学习 | |
| 774.SSN_ Learning Sparse Switchable Normalization via SparsestMax SSN_通过SparsestMax学习稀疏可切换规范化 | |
| 775.STEP_ Spatio-Temporal Progressive Learning for Video Action Detection STEP_时空渐进学习，用于视频动作检测 | |
| 776.StereoDRNet_ Dilated Residual StereoNet StereoDRNet_剩余残差StereoNet | |
| 777.Stereo R-CNN Based 3D Object Detection for Autonomous Driving 基于立体声R-CNN的3D目标检测自动驾驶 | |
| 778.STGAN_ A Unified Selective Transfer Network for Arbitrary Image Attribute Editing STGAN_用于任意图像属性编辑的统一选择性传输网络 | |
| 779.Stochastic Class-Based Hard Example Mining for Deep Metric Learning 用于深度度量学习的基于随机类的硬示例挖掘 | |
| 780.StoryGAN_ A Sequential Conditional GAN for Story Visualization StoryGAN_用于故事可视化的顺序条件GAN | |
| 781.Strike (With) a Pose_ Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects 罢工（带有姿势）_熟悉对象的奇怪姿势很容易使神经网络蒙混 | |
| 782.Striking the Right Balance With Uncertainty 不确定地达到正确的平衡 | |
| 783.Structural Relational Reasoning of Point Clouds 点云的结构关系推理 | |
| 784.Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation 结构化的二进制神经网络，用于准确的图像分类和语义分割 | |
| 785.Structured Pruning of Neural Networks With Budget-Aware Regularization 具有预算感知正则化的神经网络的结构化修剪 | |
| 786.Structure-Preserving Stereoscopic View Synthesis With Multi-Scale Adversarial Correlation Matching 具有多尺度对抗相关匹配的保结构立体视图合成 | |
| 787.Superquadrics Revisited_ Learning 3D Shape Parsing Beyond Cuboids 再探超二次元_学习超越长方体的3D形状解析 | |
| 788.Supervised Fitting of Geometric Primitives to 3D Point Clouds 几何图元在3D点云的监督下拟合 | |
| 789.Synthesizing 3D Shapes From Silhouette Image Collections Using Multi-Projection Generative Adversarial Networks 使用多投影生成对抗网络从轮廓图像集合中合成3D形状 | |
| 790.Synthesizing Environment-Aware Activities via Activity Sketches 通过活动草图合成环境意识活动 | |
| 791.TACNet_ Transition-Aware Context Network for Spatio-Temporal Action Detection TACNet_用于时空动作检测的过渡感知上下文网络 | |
| 792.Tactical Rewind_ Self-Correction via Backtracking in Vision-And-Language Navigation 战术倒带_通过视觉和语言导航中的回溯进行自我纠正 | |
| 793.Taking a Closer Look at Domain Shift_ Category-Level Adversaries for Semantics Consistent Domain Adaptation 仔细研究域Shift_类别语义一致的域匹配对手 | |
| 794.Taking a Deeper Look at the Inverse Compositional Algorithm 深入了解逆合成算法 | |
| 795.Task Agnostic Meta-Learning for Few-Shot Learning 面向任务的不可知元学习 | |
| 796.Task-Free Continual Learning 无任务持续学习 | |
| 797.Tell Me Where I Am_ Object-Level Scene Context Prediction 告诉我我在哪里_对象级场景上下文预测 | |
| 798.Temporal Transformer Networks_ Joint Learning of Invariant and Discriminative Time Warping 时间变压器网络_不变和判别时间扭曲的联合学习 | |
| 799.Text2Scene_ Generating Compositional Scenes From Textual Descriptions Text2Scene_根据文本描述生成合成场景 | |
| 800.Text Guided Person Image Synthesis 文本指导人图像合成 |
| 论文 | 概要 |
|---|---|
| 801.Texture Mixer_ A Network for Controllable Synthesis and Interpolation of Texture Texture Mixer_一个可控制的纹理合成和插值网络 | |
| 802.The Pros and Cons_ Rank-Aware Temporal Attention for Skill Determination in Long Videos 长视频中技能确定的优缺点 | |
| 803.The Regretful Agent_ Heuristic-Aided Navigation Through Progress Estimation 遗憾的Agent_通过进度估计进行启发式导航 | |
| 804.The Visual Centrifuge_ Model-Free Layered Video Representations Visual Centrifuge_无模型分层视频表示 | |
| 805.Thinking Outside the Pool_ Active Training Image Creation for Relative Attributes 在池外思考_为相对属性创建主动训练图像 | |
| 806.Tightness-Aware Evaluation Protocol for Scene Text Detection 用于场景文本检测的紧密度评估协议 | |
| 807.Timeception for Complex Action Recognition 复杂动作识别的时间接收 | |
| 808.T-Net_ Parametrizing Fully Convolutional Nets With a Single High-Order Tensor T-Net_用单个高阶张量参数化全卷积网络 | |
| 809.ToothNet_ Automatic Tooth Instance Segmentation and Identification From Cone Beam CT Images ToothNet_从锥束CT图像自动进行牙齿实例分割和识别 | |
| 810.TopNet_ Structural Point Cloud Decoder TopNet_结构点云解码器 | |
| 811.Topology Reconstruction of Tree-Like Structure in Images via Structural Similarity Measure and Dominant Set Clustering 基于结构相似性度量和支配集聚类的图像类树形结构拓扑重构 | |
| 812.TOUCHDOWN_ Natural Language Navigation and Spatial Reasoning in Visual Street Environments TOUCHDOWN_视觉街道环境中的自然语言导航和空间推理 | |
| 813.Toward Realistic Image Compositing With Adversarial Learning 通过对抗学习实现逼真的图像合成 | |
| 814.Towards Accurate One-Stage Object Detection With AP-Loss 借助AP损耗实现精确的一阶段目标检测 | |
| 815.Towards Natural and Accurate Future Motion Prediction of Humans and Animals 走向人类和动物自然，准确的未来运动预测 | |
| 816.Towards Optimal Structured CNN Pruning via Generative Adversarial Learning 通过生成对抗性学习来优化结构化CNN修剪 | |
| 817.Towards Scene Understanding_ Unsupervised Monocular Depth Estimation With Semantic-Aware Representation 走向场景理解_具有语义感知表示的无监督单眼深度估计 | |
| 818.Towards Social Artificial Intelligence_ Nonverbal Social Signal Prediction in a Triadic Interaction 迈向社会人工智能_三元互动中的非语言社会信号预测 | |
| 819.Towards VQA Models That Can Read 走向可以阅读的VQA模型 | |
| 820.Training Deep Learning Based Image Denoisers From Undersampled Measurements Without Ground Truth and Without Image Prior 在没有地面真理和没有图像先验的情况下从欠采样测量中训练基于深度学习的图像降噪器 | |
| 821.Transferable AutoML by Model Sharing Over Grouped Datasets 通过分组数据集上的模型共享来传输AutoML | |
| 822.Transfer Learning via Unsupervised Task Discovery for Visual Question Answering 通过无监督任务发现转移学习以进行视觉问答 | |
| 823.TransGaGa_ Geometry-Aware Unsupervised Image-To-Image Translation TransGaGa_几何感知无监督的图像到图像转换 | |
| 824.Translate-to-Recognize Networks for RGB-D Scene Recognition 转换为识别网络以进行RGB-D场景识别 | |
| 825.TraPHic_ Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactions 使用加权交互预测密集和异构交通中的TraPHic_轨迹 | |
| 826.TraVeLGAN_ Image-To-Image Translation by Transformation Vector Learning TraVeLGAN_通过转换向量学习进行图像到图像的翻译 | |
| 827.Triply Supervised Decoder Networks for Joint Detection and Segmentation 用于联合检测和分段的三重监督解码器网络 | |
| 828.Trust Region Based Adversarial Attack on Neural Networks 基于信任区域的神经网络对抗攻击 | |
| 829.Turn a Silicon Camera Into an InGaAs Camera 将硅相机变成InGaAs相机 | |
| 830.Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition 基于骨架的动作识别的两流自适应图卷积网络 | |
| 831.Typography With Decor_ Intelligent Text Style Transfer 带Decor_的排版_智能文本样式传输 | |
| 832.Uncertainty Guided Multi-Scale Residual Learning-Using a Cycle Spinning CNN for Single Image De-Raining 不确定度指导的多尺度残差学习-使用循环旋转CNN进行单幅图像降噪 | |
| 833.Understanding and Visualizing Deep Visual Saliency Models 了解和可视化深度视觉显着性模型 | |
| 834.Understanding the Disharmony Between Dropout and Batch Normalization by Variance Shift 通过方差移位了解辍学和批处理规范化之间的不和谐 | |
| 835.Unequal-Training for Deep Face Recognition With Long-Tailed Noisy Data 带有长尾噪声数据的不等式训练用于深脸识别 | |
| 836.Universal Domain Adaptation 通用域适应 | |
| 837.UnOS_ Unified Unsupervised Optical-Flow and Stereo-Depth Estimation by Watching Videos UnOS_通过观看视频实现统一的无监督光流和立体声深度估计 | |
| 838.Unprocessing Images for Learned Raw Denoising 未处理图像以学习原始降噪 | |
| 839.Unsupervised 3D Pose Estimation With Geometric Self-Supervision 具有几何自监督的无监督3D姿势估计 | |
| 840.Unsupervised Disentangling of Appearance and Geometry by Deformable Generator Network 变形发生器网络无监督地分解外观和几何形状 | |
| 841.Unsupervised Domain Adaptation for ToF Data Denoising With Adversarial Learning 利用对抗学习进行ToF数据去噪的无监督域自适应 | |
| 842.Unsupervised Domain Adaptation Using Feature-Whitening and Consensus Loss 使用特征白化和共识损失的无监督域自适应 | |
| 843.Unsupervised Domain-Specific Deblurring via Disentangled Representations 通过解缠表示形式进行无监督的特定领域去模糊 | |
| 844.Unsupervised Embedding Learning via Invariant and Spreading Instance Feature 通过不变和扩展实例特征进行无监督的嵌入学习 | |
| 845.Unsupervised Event-Based Learning of Optical Flow, Depth, and Egomotion 基于无监督事件的光流，深度和自我运动学习 | |
| 846.Unsupervised Face Normalization With Extreme Pose and Expression in the Wild 无监督的人脸标准化与极端姿势和野外表达 | |
| 847.Unsupervised Image Captioning 无监督图像字幕 | |
| 848.Unsupervised Image Matching and Object Discovery as Optimization 无监督图像匹配和对象发现优化 | |
| 849.Unsupervised Learning of Dense Shape Correspondence 密集形状对应的无监督学习 | |
| 850.Unsupervised Multi-Modal Neural Machine Translation 无监督的多模态神经机器翻译 |
| 论文 | 概要 |
|---|---|
| 851.Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization 语义差异最小化的无监督开放域识别 | |
| 852.Unsupervised Part-Based Disentangling of Object Shape and Appearance 基于无监督基于零件的对象形状和外观分解 | |
| 853.Unsupervised Primitive Discovery for Improved 3D Generative Modeling 用于改进3D生成建模的无监督原始发现 | |
| 854.Unsupervised Visual Domain Adaptation_ A Deep Max-Margin Gaussian Process Approach 无人监督的视觉域适应_深度最大余量高斯过程方法 | |
| 855.UPSNet_ A Unified Panoptic Segmentation Network UPSNet_统一的全景分割网络 | |
| 856.Using Unknown Occluders to Recover Hidden Scenes 使用未知遮挡物恢复隐藏的场景 | |
| 857.Variational Bayesian Dropout With a Hierarchical Prior 具有分层先验的变分贝叶斯辍学 | |
| 858.Variational Convolutional Neural Network Pruning 变分卷积神经网络修剪 | |
| 859.Variational Information Distillation for Knowledge Transfer 知识转移的变分蒸馏 | |
| 860.Variational Prototyping-Encoder_ One-Shot Learning With Prototypical Images 可变原型编码器_带有原型图像的一键式学习 | |
| 861.Versatile Multiple Choice Learning and Its Application to Vision Computing 多种选择学习及其在视觉计算中的应用 | |
| 862.Video Generation From Single Semantic Label Map 从单个语义标签图生成视频 | |
| 863.Video Summarization by Learning From Unpaired Data 通过学习未配对的数据进行视频汇总 | |
| 864.Viewport Proposal CNN for 360deg Video Quality Assessment 用于360度视频质量评估的视口提案CNN | |
| 865.Vision-Based Navigation With Language-Based Assistance via Imitation Learning With Indirect Intervention 通过基于间接干预的模仿学习的基于语言的导航和基于视觉的导航 | |
| 866.Visual Attention Consistency Under Image Transforms for Multi-Label Image Classification 多标签图像分类在图像变换下的视觉注意一致性 | |
| 867.Visual Localization by Learning Objects-Of-Interest Dense Match Regression 通过学习兴趣对象密集匹配回归进行视觉本地化 | |
| 868.Visual Query Answering by Entity-Attribute Graph Matching and Reasoning 实体属性图匹配与推理的可视化查询回答 | |
| 869.Visual Question Answering as Reading Comprehension 视觉问答作为阅读理解 | |
| 870.VITAMIN-E_ VIsual Tracking and MappINg With Extremely Dense Feature Points VITAMIN-E_具有极致密特征点的可视跟踪和映射 | |
| 871.VizWiz-Priv_ A Dataset for Recognizing the Presence and Purpose of Private Visual Information in Images Taken by Blind People VizWiz-Priv_用于识别盲人拍摄的图像中私人视觉信息的存在和目的的数据集 | |
| 872.Volumetric Capture of Humans With a Single RGBD Camera via Semi-Parametric Learning 通过半参数学习，使用单个RGBD相机对人体进行体积捕获 | |
| 873.VRSTC_ Occlusion-Free Video Person Re-Identification VRSTC_无遮挡的视频人重新识别 | |
| 874.WarpGAN_ Automatic Caricature Generation WarpGAN_自动漫画生成 | |
| 875.Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification From the Bottom Up 自底向上的细粒度图像分类的弱监督互补零件模型 | |
| 876.Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation 弱监督的3D人类姿势估计的几何感知表示的发现 | |
| 877.Weakly Supervised Image Classification Through Noise Regularization 通过噪声正则化的弱监督图像分类 | |
| 878.Weakly Supervised Open-Set Domain Adaptation by Dual-Domain Collaboration 通过双域协作对开放集域进行弱监督 | |
| 879.Weakly Supervised Person Re-Identification 弱者重新识别 | |
| 880.Weakly Supervised Video Moment Retrieval From Text Queries 从文本查询中弱监督视频瞬间的检索 | |
| 881.What and How Well You Performed_ A Multitask Learning Approach to Action Quality Assessment 您的表现和表现如何_行动质量评估的多任务学习方法 | |
| 882.What Do Single-View 3D Reconstruction Networks Learn_ 单视图3D重建网络能学到什么_ | |
| 883.What Object Should I Use_ - Task Driven Object Detection 我应该使用什么对象_-任务驱动的对象检测 | |
| 884.What’s to Know_ Uncertainty as a Guide to Asking Goal-Oriented Questions 知道什么_不确定性作为提出针对目标的问题的指南 | |
| 885.Where’s Wally Now_ Deep Generative and Discriminative Embeddings for Novelty Detection Wally Now在哪里_用于新颖性检测的深度生成和判别式嵌入 | |
| 886.Which Way Are You Going_ Imitative Decision Learning for Path Forecasting in Dynamic Scenes 您要走的路_动态场景中路径预测的模仿决策学习 | |
| 887.Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem 为什么ReLU Networks远离训练数据就产生了高可信度预测以及如何缓解问题 | |
| 888.Wide-Area Crowd Counting via Ground-Plane Density Maps and Multi-View Fusion CNNs 通过地面密度图和多视图融合CNN进行广域人群计数 | |
| 889.Wide-Context Semantic Image Extrapolation 广域语义图像外推 | |
| 890.World From Blur 模糊世界 | |
| 891.X2CT-GAN_ Reconstructing CT From Biplanar X-Rays With Generative Adversarial Networks X2CT-GAN_利用生成的对抗网络从双平面X射线重建CT | |
| 892.You Look Twice_ GaterNet for Dynamic Filter Selection in CNNs 您可以在TWN_ GaterNet中查找CNN中的动态过滤器选择 | |
| 893.You Reap What You Sow_ Using Videos to Generate High Precision Object Proposals for Weakly-Supervised Object Detection 您所收获的_使用视频生成用于弱监督对象检测的高精度对象建议 | |
| 894.Zero-Shot Task Transfer 零任务转移 | |
| 895.ZigZagNet_ Fusing Top-Down and Bottom-Up Context for Object Segmentation ZigZagNet_融合自上而下和自下而上的上下文进行对象细分 | |
| 896.Zoom-In-To-Check_ Boosting Video Interpolation via Instance-Level Discrimination 放大检查_通过实例级区分提升视频插值 |
Process finished with exit code 0
最后
以上就是忧伤抽屉为你收集整理的（九：2020.08.27）CVPR 2019 追踪之论文纲要（译）讲在前面论文目录的全部内容，希望文章能够帮你解决（九：2020.08.27）CVPR 2019 追踪之论文纲要（译）讲在前面论文目录所遇到的程序开发问题。
如果觉得靠谱客网站的内容还不错，欢迎将靠谱客网站推荐给程序员好友。
本图文内容来源于网友提供，作为学习参考使用，或来自网络收集整理，版权属于原作者所有。
发表评论 取消回复