sqlserv已生成用于更新的结果集。_今日论文|OCNLI：首个大规模中文自然语言推理数据集&AWS：在集群上小批量训练GNN&强化学习W自然梯度优化新策略&MORE...

10月13日人工智能领域新增论文 545篇，AI日读精选其中 120篇推荐给大家。这些论文主要来自AAAI，COLING，CVPR，ECML，EMNLP，ICASSP，ICLR，ICML，ICPR，INTERSPEECH，ISMIR，MICCAI，Natural Computing，NeurIPS，TPAMI，WACV等会议与期刊。其中包含 计算机视觉论文12篇[1-12]， 自然语言处理论文58篇[13-70]， 方法论论文20篇[76-95]， 神经网络原理论文5篇[96-100]， 语音技术论文3篇[104-106]， 知识图谱论文4篇[107-110]， 强化学习论文5篇[111-115]， 推荐系统论文1篇[116]， 医疗与健康论文3篇[117-119]， 应用论文1篇[120]，点击文末

计算机视觉

Computer Vision

[1]

Towards Hardware-Agnostic Gaze-Trackers

Jatin Sharma, Jon Campbell, Pete Ansell, Jay Beavers, Christopher O'Dowd

摘 要：

原 文：http://arxiv.org/pdf/2010.05123v1

---

[2]

Shape-aware Generative Adversarial Networks for Attribute Transfer

Lei Luo, William Hsu, Shangxian Wang

摘 要：

原 文：http://arxiv.org/pdf/2010.05259v1

---

[3]

Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification

Yulin Wang, Kangchen Lv, Rui Huang, Shiji Song, Le Yang, Gao Huang

摘 要：

原 文：http://arxiv.org/pdf/2010.05300v1

资 源：github.com/blackfeather-wang/GFNet-Pytorch

---

[4]

PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation

Wen Guo, Enric Corona, Francesc Moreno-Noguer, Xavier Alameda-Pineda

摘 要：

原 文：http://arxiv.org/pdf/2010.05302v1

---

[5]

Top-DB-Net: Top DropBlock for Activation Enhancement in Person Re-Identification

Rodolfo Quispe, Helio Pedrini

摘 要：

原 文：http://arxiv.org/pdf/2010.05435v1

资 源：github.com/RQuispeC/top-dropblock

---

[6]

H2O-Net: Self-Supervised Flood Segmentation via Adversarial Domain Adaptation and Label Refinement

Peri Akiva, Matthew Purri, Kristin Dana, Beth Tellman, Tyler Anderson

摘 要：

原 文：http://arxiv.org/pdf/2010.05309v1

---

[7]

Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching

Di Hu, Rui Qian, Minyue Jiang, Xiao Tan, Shilei Wen, Errui Ding, Weiyao Lin, Dejing Dou

摘 要：

原 文：http://arxiv.org/pdf/2010.05466v1

---

[8]

Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detection

Nian Liu, Ni Zhang, Ling Shao, Junwei Han

摘 要：

原 文：http://arxiv.org/pdf/2010.05537v1

---

[9]

TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation

Dongxu Li, Chenchen Xu, Xin Yu, Kaihao Zhang, Ben Swift, Hanna Suominen, Hongdong Li

摘 要：

原 文：http://arxiv.org/pdf/2010.05468v1

资 源：github.com/verashira/TSPNet

---

[10]

Viewpoint-Aware Channel-Wise Attentive Network for Vehicle Re-Identification

Tsai-Shien Chen, Man-Yu Lee, Chih-Ting Liu, Shao-Yi Chien

摘 要：

原 文：http://arxiv.org/pdf/2010.05810v1

---

[11]

On the Minimal Recognizable Image Patch

Mark Fonaryov, Michael Lindenbaum

摘 要：

原 文：http://arxiv.org/pdf/2010.05858v1

---

[12]

Generalized Few-Shot Semantic Segmentation

Zhuotao Tian, Xin Lai, Li Jiang, Michelle Shu, Hengshuang Zhao, Jiaya Jia

摘 要：

原 文：http://arxiv.org/pdf/2010.05210v1

---

自然语言处理

Natural Language Processing

[13]

Incremental Processing in the Age of Non-Incremental Encoders: An Empirical Assessment of Bidirectional Models for Incremental NLU

Brielen Madureira, David Schlangen

摘 要：

原 文：http://arxiv.org/pdf/2010.05330v1

---

[14]

Structural Knowledge Distillation

Xinyu Wang, Yong Jiang, Zhaohui Yan, Zixia Jia, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

摘 要：

原 文：http://arxiv.org/pdf/2010.05010v1

---

[15]

End to End Binarized Neural Networks for Text Classification

Harshil Jain, Akshat Agarwal, Kumar Shridhar, Denis Kleyko

摘 要：

原 文：http://arxiv.org/pdf/2010.05223v1

---

[16]

OCNLI: Original Chinese Natural Language Inference

Hai Hu, Kyle Richardson, Liang Xu, Lu Li, Sandra Kuebler, Lawrence S. Moss

摘 要：

原 文：http://arxiv.org/pdf/2010.05444v1

资 源：github.com/CLUEbenchmark/CLUE, github.com/NYU-MLL/multiNLI, github.com/ymcui/Chinese-BERT-wwm, github.com/Embedding/Chinese-Word-Vectors

---

[17]

Adversarial Self-Supervised Data-Free Distillation for Text Classification

Xinyin Ma, Yongliang Shen, Gongfan Fang, Chen Chen, Chenghao Jia, Weiming Lu

摘 要：

原 文：http://arxiv.org/pdf/2010.04883v1

---

[18]

FIND: Human-in-the-Loop Debugging Deep Text Classifiers

Piyawat Lertvittayakumjorn, Lucia Specia, Francesca Toni

摘 要：

原 文：http://arxiv.org/pdf/2010.04987v1

资 源：github.com/Microsoft/biosbias, github.com/plkumjorn/FIND

---

[19]

On Long-Tailed Phenomena in Neural Machine Translation

Vikas Raunak, Siddharth Dalmia, Vivek Gupta, Florian Metze

摘 要：

原 文：http://arxiv.org/pdf/2010.04924v1

资 源：github.com/vyraun/long-tailed

---

[20]

Beyond Language: Learning Commonsense from Images for Reasoning

Wanqing Cui, Yanyan Lan, Liang Pang, Jiafeng Guo, Xueqi Cheng

摘 要：

原 文：http://arxiv.org/pdf/2010.05001v1

资 源：github.com/VickiCui/Loire

---

[21]

PHICON: Improving Generalization of Clinical Text De-identification Models via Data Augmentation

Xiang Yue, Shuang Zhou

摘 要：

原 文：http://arxiv.org/pdf/2010.05143v1

资 源：github.com/Franck-Dernoncourt/NeuroNER

---

[22]

Connecting the Dots Between Fact Verification and Fake News Detection

Qifei Li, Wangchunshu Zhou

摘 要：

原 文：http://arxiv.org/pdf/2010.05202v1

资 源：github.com/dmmiller612/bert-extractive-summarizer

---

[23]

Multilingual Offensive Language Identification with Cross-lingual Embeddings

Tharindu Ranasinghe, Marcos Zampieri

摘 要：

<