1月8日人工智能领域新增论文 205篇，AI日读精选其中 42篇推荐给大家。这些论文主要来自Artificial Intelligence ，AAAI，CHI，ECIR，ECMLPKDD，ICRA，IJRR，NeurIPS，TACL等会议与期刊。其中包含 计算机视觉论文9篇[1-9]， 自然语言处理论文7篇[10-16]， 方法论论文14篇[18-31]， 神经网络原理论文1篇[32]， 知识图谱论文2篇[34-35]， 强化学习论文3篇[36-38]， 推荐系统论文1篇[39]， 医疗与健康论文1篇[40]。另外，本期还包含1个新构造的 数据集[17]，1篇 综述[33]，以及其他技术文章。点击文末

计算机视觉

Computer Vision

[1]

OAAE: Adversarial Autoencoders for Novelty Detection in Multi-modal Normality Case via Orthogonalized Latent Space

Sungkwon An, Jeonghoon Kim, Myungjoo Kang, Shahbaz Razaei, Xin Liu

摘 要：

原 文：http://arxiv.org/pdf/2101.02358v1

---

[2]

Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds

Jingyu Gong, Jiachen Xu, Xin Tan, Jie Zhou, Yanyun Qu, Yuan Xie, Lizhuang Ma

摘 要：

原 文：http://arxiv.org/pdf/2101.02381v1

---

[3]

Single Shot Multitask Pedestrian Detection and Behavior Prediction

Prateek Agrawal, Pratik Prabhanjan Brahma

摘 要：

原 文：http://arxiv.org/pdf/2101.02232v1

---

[4]

The Road to Ubiquitous Personal Fabrication: Modeling-Free Instead of Increasingly Simple

Evgeny Stemasov, Enrico Rukzio, Jan Gugenheimer

摘 要：

原 文：http://arxiv.org/pdf/2101.02467v1

---

[5]

Playing with Food: Learning Food Item Representations through Interactive Exploration

Amrita Sawhney, Steven Lee, Kevin Zhang, Manuela Veloso, Oliver Kroemer

摘 要：

原 文：http://arxiv.org/pdf/2101.02252v1

---

[6]

DeepPoison: Feature Transfer Based Stealthy Poisoning Attack

Jinyin Chen, Longyuan Zhang, Haibin Zheng, Xueke Wang, Zhaoyan Ming

摘 要：

原 文：http://arxiv.org/pdf/2101.02562v1

---

[7]

HAVANA: Hierarchical and Variation-Normalized Autoencoder for Person Re-identification

Jiawei Ren, Xiao Ma, Chen Xu, Haiyu Zhao, Shuai Yi

摘 要：

原 文：http://arxiv.org/pdf/2101.02568v1

---

[8]

L2PF -- Learning to Prune Faster

Manoj-Rohit Vemparala, Nael Fasfous, Alexander Frickenstein, Mhd Ali Moraly, Aquib Jamal, Lukas Frickenstein, Christian Unger, Naveen-Shankar Nagaraja, Walter Stechele

摘 要：

原 文：http://arxiv.org/pdf/2101.02663v1

---

[9]

TrackFormer: Multi-Object Tracking with Transformers

Tim Meinhardt, Alexander Kirillov, Laura Leal-Taixe, Christoph Feichtenhofer

摘 要：

原 文：http://arxiv.org/pdf/2101.02702v1

---

自然语言处理

Natural Language Processing

[10]

Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies

Mor Geva, Daniel Khashabi, Elad Segal, Tushar Khot, Dan Roth, Jonathan Berant

摘 要：

原 文：http://arxiv.org/pdf/2101.02235v1

---

[11]

Applying Transfer Learning for Improving Domain-Specific Search Experience Using Query to Question Similarity

Ankush Chopra, Shruti Agrawal, Sohom Ghosh

摘 要：

原 文：http://arxiv.org/pdf/2101.02351v1

---

[12]

Read, Retrospect, Select: An MRC Framework to Short Text Entity Linking

Yingjie Gu, Xiaoye Qu, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan, Xiaolin Gui

摘 要：

原 文：http://arxiv.org/pdf/2101.02394v1

---

[13]

User Ex Machina : Simulation as a Design Probe in Human-in-the-Loop Text Analytics

Anamaria Crisan, Michael Correll

摘 要：

原 文：http://arxiv.org/pdf/2101.02244v1

---

[14]

Exploring Text-transformers in AAAI 2021 Shared Task: COVID-19 Fake News Detection in English

Xiangyang Li, Yu Xia, Xiang Long, Zheng Li, Sujian Li

摘 要：

原 文：http://arxiv.org/pdf/2101.02359v1

---

[15]

Towards Automating Code Review Activities

Rosalia Tufano, Luca Pascarella, Michele Tufano, Denys Poshyvanyk, Gabriele Bavota

摘 要：

原 文：http://arxiv.org/pdf/2101.02518v1

---

[16]

Ask2Transformers: Zero-Shot Domain labelling with Pre-trained Language Models

Oscar Sainz, German Rigau

摘 要：

原 文：http://arxiv.org/pdf/2101.02661v1

---

数据集

Dataset

[17]

A Large-Scale, Time-Synchronized Visible and Thermal Face Dataset

Domenick Poster, Matthew Thielke, Robert Nguyen, Srinivasan Rajaraman, Xing Di, Cedric Nimpa Fondje, Vishal M. Patel, Nathaniel J. Short, Benjamin S. Riggan, Nasser M. Nasrabadi, Shuowen Hu

摘 要：

原 文：http://arxiv.org/pdf/2101.02637v1

---

方法论

Methodology

[18]

Hyperboost: Hyperparameter Optimization by Gradient Boosting surrogate models

Jeroen van Hoof, Joaquin Vanschoren

摘 要：

原 文：http://arxiv.org/pdf/2101.02289v1

---

[19]

Using BART for Multiobjective Optimization of Noisy Multiple Objectives

Akira Horiguchi, Thomas J. Santner, Ying Sun, Matthew T. Pratola

摘 要：

原 文：http://arxiv.org/pdf/2101.02558v1

---

[20]

FLGUARD: Secure and Private Federated Learning

Thien Duc Nguyen, Phillip Rieger, Hossein Yalame, Helen Möllering, Hossein Fereidooni, Samuel Marchal, Markus Miettinen, Azalia Mirhoseini, Ahmad-Reza Sadeghi, Thomas Schneider, Shaza Zeitouni

摘 要：

原 文：http://arxiv.org/pdf/2101.02281v1

---

[21]

Handling many conversions per click in modeling delayed feedback

Ashwinkumar Badanidiyuru, Andrew Evdokimov, Vinodh Krishnan, Pan Li, Wynn Vonnegut, Jayden Wang

摘 要：

原 文：http://arxiv.org/pdf/2101.02284v1

---

[22]

Scale-free tree network with an ultra-large diameter

Fei Ma, Ping Wang

摘 要：

原 文：http://arxiv.org/pdf/2101.02320v1

---

[23]

Low-cost and high-performance data augmentation for deep-learning-based skin lesion classification

Shuwei Shen, Mengjuan Xu, Fan Zhang, Pengfei Shao, Honghong Liu, Liang Xu, Chi Zhang, Peng Liu, Zhihong Zhang, Peng Yao, Ronald X. Xu

摘 要：

原 文：http://arxiv.org/pdf/2101.02353v1

---

[24]

Simplified DOM Trees for Transferable Attribute Extraction from the Web

Yichao Zhou, Ying Sheng, Nguyen Vo, Nick Edmonds, Sandeep Tata

摘 要：

原 文：http://arxiv.org/pdf/2101.02415v1

---

[25]

Decision Support System for an Intelligent Operator of Utility Tunnel Boring Machines

Gabriel Rodriguez Garcia, Gabriel Michau, Olga Fink

摘 要：

原 文：http://arxiv.org/pdf/2101.02463v1

---

[26]

Robust Text CAPTCHAs Using Adversarial Examples

Rulin Shao, Zhouxing Shi, Jinfeng Yi, Pin-Yu Chen, Cho-Jui Hsieh

摘 要：

原 文：http://arxiv.org/pdf/2101.02483v1

---

[27]

Attitudes toward Open Access, Open Peer Review, and Altmetrics among Contributors to Spanish Scholarly Journals

Francisco Segado-Boj, Juan Martin-Quevedo, Juan Jose Prieto-Gutierrez

摘 要：

原 文：http://arxiv.org/pdf/2101.02488v1

---

[28]

Merging with unknown reliability

Paolo Liberatore

摘 要：

原 文：http://arxiv.org/pdf/2101.02516v1

---

[29]

Few-Shot Learning with Class Imbalance

Mateusz Ochal, Massimiliano Patacchiola, Amos Storkey, Jose Vazquez, Sen Wang

摘 要：

原 文：http://arxiv.org/pdf/2101.02523v1

---

[30]

Open Set Domain Adaptation by Extreme Value Theory

Yiming Xu, Diego Klabjan

摘 要：

原 文：http://arxiv.org/pdf/2101.02561v1

---

[31]

Theorem Proving and Algebra

Joseph A. Goguen

摘 要：

原 文：http://arxiv.org/pdf/2101.02690v1

---

神经网络原理

Neural Network Theory

[32]

GAN-Control: Explicitly Controllable GANs

Alon Shoshan, Nadav Bhonker, Igor Kviatkovsky, Gerard Medioni

摘 要：

原 文：http://arxiv.org/pdf/2101.02477v1

---

综述

Survey

[33]

A review of robotics taxonomies in terms of form and structure

Signe A. Redfield

摘 要：

原 文：http://arxiv.org/pdf/2101.02659v1

---

知识图谱

Knowledge Graph

[34]

Reinforced Imitative Graph Representation Learning for Mobile User Profiling: An Adversarial Training Perspective

Dongjie Wang, Pengyang Wang, Kunpeng Liu, Yuanchun Zhou, Charles Hughes, Yanjie Fu

摘 要：

原 文：http://arxiv.org/pdf/2101.02634v1

---

[35]

Controlling Entity Integrity with Key Sets

Miika Hannula, Xinyi Li, Sebastian Link

摘 要：

原 文：http://arxiv.org/pdf/2101.02472v1

---

强化学习

Reinforcement Learning

[36]

CoachNet: An Adversarial Sampling Approach for Reinforcement Learning

Elmira Amirloo Abolfathi, Jun Luo, Peyman Yadmellat, Kasra Rezaee

摘 要：

原 文：http://arxiv.org/pdf/2101.02649v1

---

[37]

Attention Actor-Critic algorithm for Multi-Agent Constrained Co-operative Reinforcement Learning

P.Parnika, Raghuram Bharadwaj Diddigi, Sai Koti Reddy Danda, Shalabh Bhatnagar

摘 要：

原 文：http://arxiv.org/pdf/2101.02349v1

---

[38]

Deep Reinforcement Learning for Black-Box Testing of Android Apps

Andrea Romdhana, Alessio Merlo, Mariano Ceccato, Paolo Tonella

摘 要：

原 文：http://arxiv.org/pdf/2101.02636v1

---

推荐系统

Recommendation System

[39]

Metric Learning for Session-based Recommendations

Bartłomiej Twardowski, Paweł Zawistowski, Szymon Zaborowski

摘 要：

原 文：http://arxiv.org/pdf/2101.02655v1

---

医疗与健康

Medical Science & Health Care

[40]

MSED: a multi-modal sleep event detection model for clinical sleep analysis

Alexander Neergaard Olesen, Poul Jennum, Emmanuel Mignot, Helge B. D. Sorensen

摘 要：

原 文：http://arxiv.org/pdf/2101.02530v1

---

其他技术

Others

[41]

A Novel Shaft-to-Tissue Force Model for Safer Motion Planning of Steerable Needles

Michael Bentley, Caleb Rucker, Chakravarthy Reddy, Oren Salzman, Alan Kuntz

摘 要：

原 文：http://arxiv.org/pdf/2101.02246v1

---

[42]

A design of human-like robust AI machines in object identification

Bao-Gang Hu, Wei-Ming Dong

摘 要：

原 文：http://arxiv.org/pdf/2101.02327v1

---

点个在看，再下论文~
(密码：6tvc)