出品 | 深度學習這件小事公眾號
計算機視覺（12月18日更新版）
[1] Reconstructing Hand-Object Interactions in the Wild作者 | Zhe Cao, Ilija Radosavovic, Angjoo Kanazawa, Jitendra Malik連結 | https://arxiv.org/abs/2012.09856 項目連結 | https://people.eecs.berkeley.edu/~zhecao/rhoi/[2] Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image作者 | Andrew Liu, Richard Tucker, Varun Jampani, Ameesh Makadia, Noah Snavely, Angjoo Kanazawa連結 | https://arxiv.org/abs/2012.09855 [3] Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis from a Single Image作者 | Ronghang Hu, Deepak Pathak連結 | https://arxiv.org/abs/2012.09854 項目連結 | https://worldsheet.github.io/[4] Human Mesh Recovery from Multiple Shots作者 | Georgios Pavlakos, Jitendra Malik, Angjoo Kanazawa連結 | https://arxiv.org/abs/2012.09843 [5] XResolution Correspondence Networks作者 | Georgi Tinchev, Shuda Li, Kai Han, David Mitchell, Rigas Kouskouridas連結 | https://arxiv.org/abs/2012.09842 項目連結 | https://xyz-r-d.github.io/xrcnet/[6] Taming Transformers for High-Resolution Image Synthesis作者 | Patrick Esser, Robin Rombach, Björn Ommer連結 | https://arxiv.org/abs/2012.09841 [7] Transformer Interpretability Beyond Attention Visualization作者 | Hila Chefer, Shir Gur, Lior Wolf連結 | https://arxiv.org/abs/2012.09838 [8] SceneFormer: Indoor Scene Generation with Transformers作者 | Xinpeng Wang, Chandan Yeshwanth, Matthias Nießner連結 | https://arxiv.org/abs/2012.09793 [9] Neural Radiance Flow for 4D View Synthesis and Video Processing作者 | Yilun Du, Yinan Zhang, Hong-Xing Yu, Joshua B. Tenenbaum, Jiajun Wu連結 | https://arxiv.org/abs/2012.09790 項目連結 | https://yilundu.github.io/nerflow/[10] End-to-end Deep Object Tracking with Circular Loss Function for Rotated Bounding Box作者 | Vladislav Belyaev, Aleksandra Malysheva, Aleksei Shpilman連結 | https://arxiv.org/abs/2012.09771 [11] End-to-End Human Pose and Mesh Reconstruction with Transformers作者 | Kevin Lin, Lijuan Wang, Zicheng Liu連結 | https://arxiv.org/abs/2012.09760 [12] Interpretable Image Clustering via Diffeomorphism-Aware K-Means作者 | Romain Cosentino, Randall Balestriero, Yanis Bahroun, Anirvan Sengupta, Richard Baraniuk, Behnaam Aazhang連結 | https://arxiv.org/abs/2012.09743 [13] AutoCaption: Image Captioning with Neural Architecture Search作者 | Xinxin Zhu, Weining Wang, Longteng Guo, Jing Liu連結 | https://arxiv.org/abs/2012.09742 [14] Robust Image Captioning作者 | Daniel Yarnell, Xian Wang連結 | https://arxiv.org/abs/2012.09732 [15] Efficient CNN-LSTM based Image Captioning using Neural Network Compression作者 | Harshit Rampal, Aman Mohanty連結 | https://arxiv.org/abs/2012.09708 [16] RainNet: A Large-Scale Dataset for Spatial Precipitation Downscaling作者 | Xuanhong Chen, Kairui Feng, Naiyuan Liu, Naiyuan Liu, Zhengyan Tong, Bingbing Ni, Ziang Liu, Ning Lin連結 | https://arxiv.org/abs/2012.09700 [17] PCT: Point Cloud Transformer作者 | Meng-Hao Guo, Jun-Xiong Cai, Zheng-Ning Liu, Tai-Jiang Mu, Ralph R. Martin, Shi-Min Hu連結 | https://arxiv.org/abs/2012.09688 [18] Multi-Modal Depth Estimation Using Convolutional Neural Networks作者 | Sadique Adnan Siddiqui, Axel Vierling, Karsten Berns連結 | https://arxiv.org/abs/2012.09667 備註 | submitted to IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)[19] A fully pipelined FPGA accelerator for scale invariant feature transform keypoint descriptor matching,作者 | Luka Daoud, Muhammad Kamran Latif, H S. Jacinto, Nader Rafla連結 | https://arxiv.org/abs/2012.09666 [20] Firearm Detection via Convolutional Neural Networks: Comparing a Semantic Segmentation Model Against End-to-End Solutions作者 | Alexander Egiazarov, Fabio Massimo Zennaro, Vasileios Mavroeidis連結 | https://arxiv.org/abs/2012.09662 備註 | presented at CyberHunt workshop at IEEE Big Data Conference[21] Detection and Prediction of Nutrient Deficiency Stress using Longitudinal Aerial Imagery作者 | Saba Dadsetan, Gisele Rose, Naira Hovakimyan, Jennifer Hobbs連結 | https://arxiv.org/abs/2012.09654 [22] Trajectory saliency detection using consistency-oriented latent codes from a recurrent auto-encoder作者 | L. Maczyta, P. Bouthemy, O. Le Meur連結 | https://arxiv.org/abs/2012.09573 [23] Incremental Learning from Low-labelled Stream Data in Open-Set Video Face Recognition作者 | Eric Lopez-Lopez, Carlos V. Regueiro, Xose M. Pardo連結 | https://arxiv.org/abs/2012.09571 [24] Weakly-Supervised Action Localization and Action Recognition using Global-Local Attention of 3D CNN作者 | Novanto Yudistira, Muthu Subash Kavitha, Takio Kurita連結 | https://arxiv.org/abs/2012.09542 [25] Embodied Visual Active Learning for Semantic Segmentation作者 | David Nilsson, Aleksis Pirinen, et al.連結 | https://arxiv.org/abs/2012.09503 備註 | Accepted to AAAI 2021[26] A Hierarchical Feature Constraint to Camouflage Medical Adversarial Attacks作者 | Qingsong Yao, Zecheng He, Yi Lin, Kai Ma, Yefeng Zheng, S. Kevin Zhou連結 | https://arxiv.org/abs/2012.09501 [27] Exploiting Learnable Joint Groups for Hand Pose Estimation作者 | Moran Li, Yuan Gao, Nong Sang連結 | https://arxiv.org/abs/2012.09496 備註 | Accepted by AAAI2021[28] CT Film Recovery via Disentangling Geometric Deformation and Illumination Variation: Simulated Datasets and Deep Models作者 | Quan Quan, Qiyuan Wang, Liu Li, Yuanqi Du, S. Kevin Zhou連結 | https://arxiv.org/abs/2012.09491 [29] Learning to Share: A Multitasking Genetic Programming Approach to Image Feature Learning作者 | Ying Bi, Bing Xue, Mengjie Zhang連結 | https://arxiv.org/abs/2012.09444 備註 | will submit to IEEE Transactions on Evolutionary Computation soon[30] FG-Net: Fast Large-Scale LiDAR Point CloudsUnderstanding Network Leveraging CorrelatedFeature Mining and Geometric-Aware Modelling作者 | Kangcheng Liu, Zhi Gao, Feng Lin, Ben M. Chen連結 | https://arxiv.org/abs/2012.09439 [31] Multi-shot Temporal Event Localization: a Benchmark作者 | Xiaolong Liu (1), Yao Hu (2), Song Bai (2,3), Fei Ding (2), Xiang Bai (1), Philip H.S. Torr (3) ((1) Huazhong University of Science and Technology, (2) Alibaba Group, (3) University of Oxford)連結 | https://arxiv.org/abs/2012.09434 項目連結 | https://songbai.site/muses/[32] PanoNet3D: Combining Semantic and Geometric Understanding for LiDARPoint Cloud Detection作者 | Xia Chen, Jianren Wang, David Held, Martial Hebert連結 | https://arxiv.org/abs/2012.09418 [33] Computation-Efficient Knowledge Distillation via Uncertainty-Aware Mixup作者 | Guodong Xu, Ziwei Liu, Chen Change Loy連結 | https://arxiv.org/abs/2012.09413 項目連結 | https://github.com/xuguodong03/UNIXKD[34] Temporal LiDAR Frame Prediction for Autonomous Driving作者 | David Deng, Avideh Zakhor連結 | https://arxiv.org/abs/2012.09409 [35] LIGHTEN: Learning Interactions with Graph and Hierarchical TEmporal Networks for HOI in videos作者 | Sai Praneeth Reddy Sunkesula, Rishabh Dabral, Ganesh Ramakrishnan連結 | https://arxiv.org/abs/2012.09402 備註 | ACM Multimedia Conference 2020[36] Zoom-to-Inpaint: Image Inpainting with High Frequency Details作者 | Soo Ye Kim, Kfir Aberman, Nori Kanazawa, Rahul Garg, Neal Wadhwa, Huiwen Chang, Nikhil Karnad, Munchurl Kim, Orly Liba連結 | https://arxiv.org/abs/2012.09401 [37] Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimation作者 | Chenxin Xu, Siheng Chen, Maosen Li, Ya Zhang連結 | https://arxiv.org/abs/2012.09398 備註 | Accepted in AAAI 2021[38] Efficient Golf Ball Detection and Tracking Based on Convolutional Neural Networks and Kalman Filter作者 | Tianxiao Zhang, Xiaohan Zhang, Yiju Yang, Zongbo Wang, Guanghui Wang連結 | https://arxiv.org/abs/2012.09393 [39] Event Camera Calibration of Per-pixel Biased Contrast Threshold作者 | Ziwei Wang, Yonhon Ng, Pieter van Goor, Robert Mahony連結 | https://arxiv.org/abs/2012.09378 備註 | the paper has been accepted for publication at the Australian Conference on Robotics and Automation, 2019[40] Unlabeled Data Guided Semi-supervised Histopathology Image Segmentation作者 | Hongxiao Wang, Hao Zheng, Jianxu Chen, Lin Yang, Yizhe Zhang, Danny Z. Chen連結 | https://arxiv.org/abs/2012.09373 備註 | Accepted paper for the 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)[41] Semi-Global Shape-aware Network作者 | Pengju Zhang, Yihong Wu, Jiagang Zhu連結 | https://arxiv.org/abs/2012.09372 [42] Learning to Recover 3D Scene Shape from a Single Image作者 | Wei Yin, Jianming Zhang, Oliver Wang, Simon Niklaus, Long Mai, Simon Chen, Chunhua Shen連結 | https://arxiv.org/abs/2012.09365 [43] Roof-GAN: Learning to Generate Roof Geometry and Relations for Residential Houses作者 | Yiming Qian, Hao Zhang, Yasutaka Furukawa連結 | https://arxiv.org/abs/2012.09340 [44] Unsupervised Learning of Local Discriminative Representation for Medical Images作者 | Huai Chen, Jieyu Li, Renzhen Wang, Yijie Huang, Fanrui Meng, Deyu Meng, Qing Peng, Lisheng Wang連結 | https://arxiv.org/abs/2012.09333 [45] Polyblur: Removing mild blur by polynomial reblurring作者 | Mauricio Delbracio, Ignacio Garcia-Dorado, Sungjoon Choi, Damien Kelly, Peyman Milanfar連結 | https://arxiv.org/abs/2012.09322 [46] Learning to Recognize Patch-Wise Consistency for Deepfake Detection作者 | Tianchen Zhao, Xiang Xu, Mingze Xu, Hui Ding, Yuanjun Xiong, Wei Xia連結 | https://arxiv.org/abs/2012.09311 [47] Self-Supervised Sketch-to-Image Synthesis作者 | Bingchen Liu, Yizhe Zhu, Kunpeng Song, Ahmed Elgammal連結 | https://arxiv.org/abs/2012.09290 [48] Projected Distribution Loss for Image Enhancement作者 | Mauricio Delbracio, Hossein Talebi, Peyman Milanfar連結 | https://arxiv.org/abs/2012.09289 [49] Sparse Signal Models for Data Augmentation in Deep Learning ATR作者 | Tushar Agarwal, Nithin Sugavanam, Emre Ertin連結 | https://arxiv.org/abs/2012.09284 備註 | to be submitted to IEEE Transactions on Geoscience and Remote Sensing[50] ISD: Self-Supervised Learning by Iterative Similarity Distillation作者 | Ajinkya Tejankar, Soroush Abbasi Koohpayegani, Vipin Pillai, Paolo Favaro, Hamed Pirsiavash連結 | https://arxiv.org/abs/2012.09259 [51] Neural Pruning via Growing Regularization作者 | Huan Wang, Can Qin, Yulun Zhang, Yun Fu連結 | https://arxiv.org/abs/2012.09243 [52] S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds作者 | Ran Cheng, Christopher Agia, Yuan Ren, Xinhai Li, Liu Bingbing連結 | https://arxiv.org/abs/2012.09242 [53] uBAM: Unsupervised Behavior Analysis and Magnification using Deep Learning作者 | Biagio Brattoli, Uta Buechler, Michael Dorkenwald, Philipp Reiser, Linard Filli, Fritjof Helmchen, Anna-Sophia Wahl, Bjoern Ommer連結 | https://arxiv.org/abs/2012.09237 [54] Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation作者 | Mehdi Bahri, Eimear O' Sullivan, Shunwang Gong, Feng Liu, Xiaoming Liu, Michael M. Bronstein, Stefanos Zafeiriou連結 | https://arxiv.org/abs/2012.09235 備註 | In review with International Journal of Computer Vision (IJCV)[55] On Episodes, Prototypical Networks, and Few-shot Learning作者 | Steinar Laenen, Luca Bertinetto連結 | https://arxiv.org/abs/2012.09831 備註 | A preliminary version of this work appeared as an oral presentation at NeurIPS 2020 meta-learning workshop[56] Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency作者 | Qiang Zhang, Tete Xiao, Alexei A. Efros, Lerrel Pinto, Xiaolong Wang連結 | https://arxiv.org/abs/2012.09811 項目連結 | https://sjtuzq.github.io/cycle_dynamics.html[57] Deep Learning Techniques for Super-Resolution in Video Games連結 | https://arxiv.org/abs/2012.09810 [58] Describing the Structural Phenotype of the Glaucomatous Optic Nerve Head Using Artificial Intelligence作者 | Satish K. Panda, Haris Cheong, Tin A. Tun, et al.連結 | https://arxiv.org/abs/2012.09755 [59] Image-Based Jet Analysis連結 | https://arxiv.org/abs/2012.09719 備註 | To appear in Artificial Intelligence for Particle Physics, World Scientific Publishing[60] Combating Mode Collapse in GAN training: An Empirical Analysis using Hessian Eigenvalues作者 | Ricard Durall, Avraam Chatzimichailidis, Peter Labus, Janis Keuper連結 | https://arxiv.org/abs/2012.09673 [61] Kernelized Classification in Deep Networks作者 | Sadeep Jayasumana, Srikumar Ramalingam, Sanjiv Kumar連結 | https://arxiv.org/abs/2012.09607 [62] Learned Block-based Hybrid Image Compression作者 | Yaojun Wu, Xin Li, Zhizheng Zhang, Xin Jin, Zhibo Chen連結 | https://arxiv.org/abs/2012.09550 [63] A new semi-supervised self-training method for lung cancer prediction作者 | Kelvin Shak, Mundher Al-Shabi, Andrea Liew, Boon Leong Lan, Wai Yee Chan, Kwan Hoong Ng, Maxine Tan連結 | https://arxiv.org/abs/2012.09472 [64] Joint Search of Data Augmentation Policies and Network Architectures作者 | Taiga Kashima, Yoshihiro Yamada, Shunta Saito連結 | https://arxiv.org/abs/2012.09407 [65] A Contrast Synthesized Thalamic Nuclei Segmentation Scheme using Convolutional Neural Networks作者 | Lavanya Umapathy, Mahesh Bharath Keerthivasan, Natalie M. Zahr, Ali Bilgin, Manojkumar Saranathan連結 | https://arxiv.org/abs/2012.09386 備註 | submitted to Neuroinformatics December 2020[66] On the Limitations of Denoising Strategies as Adversarial Defenses作者 | Zhonghan Niu, Zhaoxi Chen, Linyi Li, Yubin Yang, Bo Li, Jinfeng Yi連結 | https://arxiv.org/abs/2012.09384 [67] Clique: Spatiotemporal Object Re-identification at the City Scale作者 | Tiantu Xu, Kaiwen Shen, Yang Fu, Humphrey Shi, Felix Xiaozhu Lin連結 | https://arxiv.org/abs/2012.09329 [68] Simultaneous View and Feature Selection for Collaborative Multi-Robot Recognition作者 | Brian Reily, Hao Zhang連結 | https://arxiv.org/abs/2012.09328 [69] StarcNet: Machine Learning for Star Cluster Identification作者 | Gustavo Perez, Matteo Messa, Daniela Calzetti, Subhransu Maji, Dooseok Jung, Angela Adamo, Mattia Siressi連結 | https://arxiv.org/abs/2012.09327 [70] Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation作者 | Hao Tang, Xingwei Liu, Kun Han, Shanlin Sun, Narisu Bai, Xuming Chen, Huang Qian, Yong Liu, Xiaohui Xie連結 | https://arxiv.org/abs/2012.09279 [71] Reduction in the complexity of 1D 1H-NMR spectra by the use of Frequency to Information Transformation作者 | Homayoun Valafar, Faramarz Valafar連結 | https://arxiv.org/abs/2012.09267 [72] Transfer Learning Through Weighted Loss Function and Group Normalization for Vessel Segmentation from Retinal Images作者 | Abdullah Sarhan, Jon Rokne, Reda Alhajj, Andrew Crichton連結 | https://arxiv.org/abs/2012.09250 備註 | Accepted by ICPR. arXiv admin note: text overlap with arXiv:2010.00583[73] MELINDA: A Multimodal Dataset for Biomedical Experiment Method Classification作者 | Te-Lin Wu, Shikhar Singh, Sayan Paul, Gully Burns, Nanyun Peng連結 | https://arxiv.org/abs/2012.09216 備註 | In The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), 2021