正则多关键字_今日论文|清华：多视图远程关系抽取&谷歌：深度核分类层&NLP领域持续学习综述&用于可靠文本分类的掩码关键字正则化&MORE...

12月18日人工智能领域新增论文 267篇，AI日读精选其中 79篇推荐给大家。这些论文主要来自AAAI，BIBM，COLING，CVPR，Computational Intelligence，ECIR，EMNLP，Evolutionary Computation，ICRA，IJCV，Information Systems，NeurIPS，WACV等会议与期刊。其中包含 计算机视觉论文28篇[1-28]， 自然语言处理论文9篇[29-37]， 方法论论文17篇[41-57]， 语音技术论文5篇[63-67]， 强化学习论文4篇[68-71]， 推荐系统论文2篇[72-73]， 医疗与健康论文2篇[74-75]， 应用论文3篇[76-78]。另外，本期还包含3个新构造的 数据集[38-40]，5篇 综述[58-62]，以及其他技术文章。点击文末

计算机视觉

Computer Vision

[1]

Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimation

Chenxin Xu, Siheng Chen, Maosen Li, Ya Zhang

摘 要：

原 文：http://arxiv.org/pdf/2012.09398v1

资 源：github.com/sjtuxcx/ITES

---

[2]

Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation

Hao Tang, Xingwei Liu, Kun Han, Shanlin Sun, Narisu Bai, Xuming Chen, Huang Qian, Yong Liu, Xiaohui Xie

摘 要：

原 文：http://arxiv.org/pdf/2012.09279v1

---

[3]

Unlabeled Data Guided Semi-supervised Histopathology Image Segmentation

Hongxiao Wang, Hao Zheng, Jianxu Chen, Lin Yang, Yizhe Zhang, Danny Z. Chen

摘 要：

原 文：http://arxiv.org/pdf/2012.09373v1

---

[4]

Exploiting Learnable Joint Groups for Hand Pose Estimation

Moran Li, Yuan Gao, Nong Sang

摘 要：

原 文：http://arxiv.org/pdf/2012.09496v1

---

[5]

Embodied Visual Active Learning for Semantic Segmentation

David Nilsson, Aleksis Pirinen, Erik Gärtner, Cristian Sminchisescu

摘 要：

原 文：http://arxiv.org/pdf/2012.09503v1

---

[6]

Learning to Share: A Multitasking Genetic Programming Approach to Image Feature Learning

Ying Bi, Bing Xue, Mengjie Zhang

摘 要：

原 文：http://arxiv.org/pdf/2012.09444v1

---

[7]

Multi-FinGAN: Generative Coarse-To-Fine Sampling of Multi-Finger Grasps

Jens Lundell, Enric Corona, Tran Nguyen Le, Francesco Verdoja, Philippe Weinzaepfel, Gregory Rogez, Francesc Moreno-Noguer, Ville Kyrki

摘 要：

原 文：http://arxiv.org/pdf/2012.09696v1

---

[8]

Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation

Mehdi Bahri, Eimear O' Sullivan, Shunwang Gong, Feng Liu, Xiaoming Liu, Michael M. Bronstein, Stefanos Zafeiriou

摘 要：

原 文：http://arxiv.org/pdf/2012.09235v1

---

[9]

Self-Supervised Sketch-to-Image Synthesis

Bingchen Liu, Yizhe Zhu, Kunpeng Song, Ahmed Elgammal

摘 要：

原 文：http://arxiv.org/pdf/2012.09290v1

---

[10]

Transfer Learning Through Weighted Loss Function and Group Normalization for Vessel Segmentation from Retinal Images

Abdullah Sarhan, Jon Rokne, Reda Alhajj, Andrew Crichton

摘 要：

原 文：http://arxiv.org/pdf/2012.09250v1

---

[11]

Sparse Signal Models for Data Augmentation in Deep Learning ATR

Tushar Agarwal, Nithin Sugavanam, Emre Ertin

摘 要：

原 文：http://arxiv.org/pdf/2012.09284v1

---

[12]

Multi-Modal Depth Estimation Using Convolutional Neural Networks

Sadique Adnan Siddiqui, Axel Vierling, Karsten Berns

摘 要：

原 文：http://arxiv.org/pdf/2012.09667v1

---

[13]

PanoNet3D: Combining Semantic and Geometric Understanding for LiDARPoint Cloud Detection

Xia Chen, Jianren Wang, David Held, Martial Hebert

摘 要：

原 文：http://arxiv.org/pdf/2012.09418v1

资 源：github.com/poodarchu/Det3D

---

[14]

Projected Distribution Loss for Image Enhancement

Mauricio Delbracio, Hossein Talebi, Peyman Milanfar

摘 要：

原 文：http://arxiv.org/pdf/2012.09289v1

---

[15]

Learning to Recognize Patch-Wise Consistency for Deepfake Detection

Tianchen Zhao, Xiang Xu, Mingze Xu, Hui Ding, Yuanju