公眾號關注 「ML-CVer」
設為 「星標」，DLCV消息即可送達！
出品 | 深度學習這件小事公眾號
計算機視覺（12月15日更新版）
[1] Real-Time High-Resolution Background Matting作者 | Shanchuan Lin, Andrey Ryabtsev, Soumyadip Sengupta, Brian Curless, Steve Seitz, Ira Kemelmacher-Shlizerman連結 | https://arxiv.org/abs/2012.07810 [2] img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation作者 | Vitor Albiero, Xingyu Chen, Xi Yin, Guan Pang, Tal Hassner連結 | https://arxiv.org/abs/2012.07791 備註 | Joint first authorship: Vitor Albiero and Xingyu Chen[3] PePScenes: A Novel Dataset and Baseline for Pedestrian Action Prediction in 3D作者 | Amir Rasouli, Tiffany Yau, Peter Lakner, Saber Malekmohammadi, Mohsen Rohani, Jun Luo連結 | https://arxiv.org/abs/2012.07773 備註 | ML4AD at NeurIPS, 2020[4] Digital rock reconstruction with user-defined properties using conditional generative adversarial networks作者 | Qiang Zheng, Dongxiao Zhang連結 | https://arxiv.org/abs/2012.07719 [5] Improving Panoptic Segmentation at All Scales作者 | Lorenzo Porzi, Samuel Rota Bulò, Peter Kontschieder連結 | https://arxiv.org/abs/2012.07717 [6] High-resolution global irrigation prediction with Sentinel-2 30m data作者 | Weixin (Angela)Wu, Sonal Thakkar, Will Hawkins, Puya Vahabi, Alberto Todeschini連結 | https://arxiv.org/abs/2012.07658 [7] Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection作者 | Alexandros Haliassos, Konstantinos Vougioukas, Stavros Petridis, Maja Pantic連結 | https://arxiv.org/abs/2012.07657 [8] Deep Neural Networks for COVID-19 Detection and Diagnosis using Images and Acoustic-based Techniques: A Recent Review作者 | Walid Hariri, Ali Narin連結 | https://arxiv.org/abs/2012.07655 [9] ProLab: perceptually uniform projective colour coordinate system作者 | Ivan A. Konovalenko, Anna A. Smagina, Dmitry P. Nikolaev, Petr P. Nikolaev連結 | https://arxiv.org/abs/2012.07653 [10] Decoupled Self Attention for Accurate One Stage Object Detection作者 | Kehe WUa, Zuge Chena, Qi MAb, Xiaoliang Zhanga, Wei Lia連結 | https://arxiv.org/abs/2012.07630 [11] Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective作者 | Xuanmeng Zhang, Minyue Jiang, Zhedong Zheng, Xiao Tan, Errui Ding, Yi Yang連結 | https://arxiv.org/abs/2012.07620 [12] WDNet: Watermark-Decomposition Network for Visible Watermark Removal作者 | Yang Liu, Zhen Zhu, Xiang Bai連結 | https://arxiv.org/abs/2012.07616 [13] Agglomerative Clustering of Handwritten Numerals to Determine Similarity of Different Languages作者 | Md. Rahat-uz-Zaman, Shadmaan Hye連結 | https://arxiv.org/abs/2012.07599 備註 | Submitted to the 22nd International Conference on Computer and Information Technology (ICCIT), 18-20 December, 2019[14] FlowMOT: 3D Multi-Object Tracking by Scene Flow Association作者 | Guangyao Zhai, Xin Kong, Jinhao Cui1, Yong Liu1, Zhen Yang連結 | https://arxiv.org/abs/2012.07541 [15] Temporal Relational Modeling with Self-Supervision for Action Segmentation作者 | Dong Wang, Di Hu, Xingjian Li, Dejing Dou連結 | https://arxiv.org/abs/2012.07508 備註 | Accepted by the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21)[16] Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates作者 | Kira Maag, Matthias Rottmann, Fabian Hüger, Peter Schlicht, Hanno Gottschalk連結 | https://arxiv.org/abs/2012.07504 [17] Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Clouds作者 | Wenbin Zhao, Jiabao Lei, Yuxin Wen, Jianguo Zhang, Kui Jia連結 | https://arxiv.org/abs/2012.07498 [18] Deep Learning for Material recognition: most recent advances and open challenges作者 | Alain Tremeau, Sixiang Xu, Damien Muselet連結 | https://arxiv.org/abs/2012.07495 備註 | Paper presented as Invited paper at the International Conference on Big Data, Machine Learning and Applications (BIGDML), Silchar, India, December 2019[19] Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU作者 | Shipra Jain, Danda Paudel Pani, Martin Danelljan, Luc Van Gool連結 | https://arxiv.org/abs/2012.07489 [20] Aggregative Self-Supervised Feature Learning作者 | Jiuwen Zhu, Yuexiang Li, S. Kevin Zhou連結 | https://arxiv.org/abs/2012.07477 [21] Learned Video Codec with Enriched Reconstruction for CLIC P-frame Coding作者 | David Alexandre, Hsueh-Ming Hang連結 | https://arxiv.org/abs/2012.07462 [22] Pyramid-Focus-Augmentation: Medical Image Segmentation with Step-Wise Focus作者 | Vajira Thambawita, Steven Hicks, P氓l Halvorsen, Michael A. Riegler連結 | https://arxiv.org/abs/2012.07430 [23] DSM Refinement with Deep Encoder-Decoder Networks連結 | https://arxiv.org/abs/2012.07427 [24] One-Shot Learning with Triplet Loss for Vegetation Classification Tasks作者 | Alexander Uzhinskiy (1), Gennady Ososkov (1), Pavel Goncharov (1), Andrey Nechaevskiy (1), Artem Smetanin (2) ((1) Joint Institute for Nuclear Research, 6 Joliot-Curie, Dubna, Moscow region, 141980, Russia, (2) ITMO University, Kronverkskiy pr. 49, Saint Petersburg, 197101, Russia)連結 | https://arxiv.org/abs/2012.07403 [25] HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation作者 | Xiaoyang Lyu, Liang Liu, Mengmeng Wang, Xin Kong, Lina Liu, Yong Liu, Xinxin Chen, Yi Yuan連結 | https://arxiv.org/abs/2012.07356 備註 | 9 pages, 5 figures. Accepted to 35th AAAI Conference on Artificial Intelligence (AAAI 2021)[26] The Open Brands Dataset: Unified brand detection and recognition at scale作者 | Xuan Jin, Wei Su, Rong Zhang, Yuan He, Hui Xue連結 | https://arxiv.org/abs/2012.07350 [27] Articulated Shape Matching Using Laplacian Eigenfunctions and Unsupervised Point Registration作者 | Diana Mateus, Radu Horaud, David Knossow, Fabio Cuzzolin, Edmond Boyer連結 | https://arxiv.org/abs/2012.07340 [28] Intrinsic Image Captioning Evaluation作者 | Chao Zeng, Sam Kwong連結 | https://arxiv.org/abs/2012.07333 [29] Combining Similarity and Adversarial Learning to Generate Visual Explanation: Application to Medical Image Classification作者 | Martin Charachon, Céline Hudelot, Paul-Henry Cournède, Camille Ruppli, Roberto Ardon連結 | https://arxiv.org/abs/2012.07332 備註 | To be published in ICPR 2020[30] Morphology on categorical distributions作者 | Silas Nyboe Ørting, Hans Jacob Teglbjærg Stephensen, Jon Sporring連結 | https://arxiv.org/abs/2012.07315 [31] Multi Modal Adaptive Normalization for Audio to Video Generation作者 | Neeraj Kumar, Srishti Goel, Ankur Narang, Brejesh Lall連結 | https://arxiv.org/abs/2012.07304 [32] Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer作者 | Jian Liang, Dapeng Hu, Yunbo Wang, Ran He, Jiashi Feng連結 | https://arxiv.org/abs/2012.07297 備註 | arXiv admin note: text overlap with arXiv:2002.08546[33] Learning Category-level Shape Saliency via Deep Implicit Surface Networks作者 | Chaozheng Wu, Lin Sun, Xun Xu, Kui Jia連結 | https://arxiv.org/abs/2012.07290 [34] Semantic Layout Manipulation with High-Resolution Sparse Attention作者 | Haitian Zheng, Zhe Lin, Jingwan Lu, Scott Cohen, Jianming Zhang, Ning Xu, Jiebo Luo連結 | https://arxiv.org/abs/2012.07288 [35] Information-Theoretic Segmentation by Inpainting Error Maximization作者 | Pedro Savarese, Sunnie S. Y. Kim, Michael Maire, Greg Shakhnarovich, David McAllester連結 | https://arxiv.org/abs/2012.07287 [36] TDAF: Top-Down Attention Framework for Vision Tasks作者 | Bo Pang, Yizhuo Li, Jiefeng Li, Muchen Li, Hanwen Cao, Cewu Lu連結 | https://arxiv.org/abs/2012.07248 備註 | Conference paper in AAAI 2021[37] Deep Optimized Priors for 3D Shape Modeling and Reconstruction作者 | Mingyue Yang, Yuxin Wen, Weikai Chen, Yongwei Chen, Kui Jia連結 | https://arxiv.org/abs/2012.07241 [38] INSPIRE: Intensity and Spatial Information-Based Deformable Image Registration作者 | Johan Öfverstedt, Joakim Lindblad, Nataša Sladoje連結 | https://arxiv.org/abs/2012.07208 [39] Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding作者 | Qingxing Cao, Bailin Li, Xiaodan Liang, Keze Wang, Liang Lin連結 | https://arxiv.org/abs/2012.07192 備註 | To appear in TNNLS 2021. Considering that a desirable VQA model should correctly perceive the image context, understand the question, and incorporate its learned knowledge, our proposed dataset aims to cutoff the shortcut learning exploited by the current deep embedding models and push the research boundary of the knowledge-based visual question reasoning[40] Meticulous Object Segmentation作者 | Chenglin Yang, Yilin Wang, Jianming Zhang, He Zhang, Zhe Lin, Alan Yuille連結 | https://arxiv.org/abs/2012.07181 [41] Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation作者 | Golnaz Ghiasi, Yin Cui, Aravind Srinivas, Rui Qian, Tsung-Yi Lin, Ekin D. Cubuk, Quoc V. Le, Barret Zoph連結 | https://arxiv.org/abs/2012.07177 [42] MSAF: Multimodal Split Attention Fusion作者 | Lang Su, Chuqing Hu, Guofa Li, Dongpu Cao連結 | https://arxiv.org/abs/2012.07175 [43] FSOCO: The Formula Student Objects in Context Dataset作者 | David Dodel, Michael Schötz, Niclas Vödisch連結 | https://arxiv.org/abs/2012.07139 [44] Location-aware Single Image Reflection Removal作者 | Zheng Dong, Ke Xu, Yin Yang, Hujun Bao, Weiwei Xu, Rynson W.H. Lau連結 | https://arxiv.org/abs/2012.07131 [45] Iterative Knowledge Exchange Between Deep Learning and Space-Time Spectral Clustering for Unsupervised Segmentation in Videos作者 | Emanuela Haller, Adina Magda Florea, Marius Leordeanu連結 | https://arxiv.org/abs/2012.07123 [46] DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation作者 | Jie Yang, Yong Shi, Zhiquan Qi連結 | https://arxiv.org/abs/2012.07122 [47] Learning Heatmap-Style Jigsaw Puzzles Provides Good Pretraining for 2D Human Pose Estimation作者 | Kun Zhang, Rui Wu, Ping Yao, Kai Deng, Ding Li, Renbiao Liu, Chuanguang Yang, Ge Chen, Min Du, Tianyao Zheng連結 | https://arxiv.org/abs/2012.07101 [48] MSVD-Turkish: A Comprehensive Multimodal Dataset for Integrated Vision and Language Research in Turkish作者 | Begum Citamak, Ozan Caglayan, Menekse Kuyu, Erkut Erdem, Aykut Erdem, Pranava Madhyastha, Lucia Specia連結 | https://arxiv.org/abs/2012.07098 [49] EfficientPose: Efficient Human Pose Estimation with Neural Architecture Search作者 | Wenqiang Zhang, Jiemin Fang, Xinggang Wang, Wenyu Liu連結 | https://arxiv.org/abs/2012.07086 [50] Robust Real-Time Pedestrian Detection on Embedded Devices作者 | Mohamed Afifi, Yara Ali, Karim Amer, Mahmoud Shaker, Mohamed Elhelw連結 | https://arxiv.org/abs/2012.07072 [51] Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network作者 | Jiayi Ji, Yunpeng Luo, Xiaoshuai Sun, Fuhai Chen, Gen Luo, Yongjian Wu, Yue Gao, Rongrong Ji連結 | https://arxiv.org/abs/2012.07061 備註 | Accepted at AAAI 2021 (preprint version)[52] PoNA: Pose-guided Non-local Attention for Human Pose Transfer作者 | Kun Li, Jinsong Zhang, Yebin Liu, Yu-Kun Lai, Qionghai Dai連結 | https://arxiv.org/abs/2012.07049 [53] One-Shot Object Localization in Medical Images based on Relative Position Regression作者 | Wenhui Lei, Wei Xu, Ran Gu, Hao Fu, Shaoting Zhang, Guotai Wang連結 | https://arxiv.org/abs/2012.07043 [54] Semi-supervised Segmentation via Uncertainty Rectified Pyramid Consistency and Its Application to Gross Target Volume of Nasopharyngeal Carcinoma作者 | Xiangde Luo, Wenjun Liao, Jieneng Chen, Tao Song, Yinan Chen, Guotai Wang, Shaoting Zhang連結 | https://arxiv.org/abs/2012.07042 [55] Uncertainty Estimation in Deep Neural Networks for Point Cloud Segmentation in Factory Planning作者 | Christina Petschnigg, Juergen Pilz連結 | https://arxiv.org/abs/2012.07038 備註 | 17 pages, 5 figures, submitted to MDPI Modelling journal for review[56] Efficient Human Pose Estimation by Learning Deeply Aggregated Representations作者 | Zhengxiong Luo, Zhicheng Wang, Yuanhao Cai, Guanan Wang, Yan Huang, Liang Wang, Erjin Zhou, Jian Sun連結 | https://arxiv.org/abs/2012.07033 [57] Split then Refine: Stacked Attention-guided ResUNets for Blind Single Image Visible Watermark Removal作者 | Xiaodong Cun, Chi-Man Pun連結 | https://arxiv.org/abs/2012.07007 [58] Effective multi-view registration of point sets based on student's t mixture model作者 | Yanlin Ma, Jihua Zhu, Zhongyu Li, Zhiqiang Tian, Yaochen Li連結 | https://arxiv.org/abs/2012.07002 [59] Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation作者 | Shuang Li, Fangrui Lv, Binhui Xie, Chi Harold Liu, Jian Liang, Chen Qin連結 | https://arxiv.org/abs/2012.06995 項目連結 | https://github.com/BIT-DA/備註 | Accepted as AAAI 2021. [60] Contrastive Learning for Label-Efficient Semantic Segmentation作者 | Xiangyun Zhao, Raviteja Vemulapalli, Philip Mansfield, Boqing Gong, Bradley Green, Lior Shapira, Ying Wu連結 | https://arxiv.org/abs/2012.06985 [61] GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation作者 | Xiaojuan Qi, Zhengzhe Liu, Renjie Liao, Philip H.S. Torr, Raquel Urtasun, Jiaya Jia連結 | https://arxiv.org/abs/2012.06980 項目連結 | https://github.com/xjqi/GeoNet[62] MVFNet: Multi-View Fusion Network for Efficient Video Recognition作者 | Wenhao Wu, Dongliang He, Tianwei Lin, Fu Li, Chuang Gan, Errui Ding連結 | https://arxiv.org/abs/2012.06977 備註 | Accepted by AAAI2021[63] Spontaneous Emotion Recognition from Facial Thermal Images連結 | https://arxiv.org/abs/2012.06973 [64] Fully-Automated Liver Tumor Localization and Characterization from Multi-Phase MR Volumes Using Key-Slice ROI Parsing: A Physician-Inspired Approach作者 | Bolin Lai, Xiaoyu Bai, Yuhsuan Wu, Xiao-Yun Zhou, Jinzheng Cai, Yuankai Huo, Lingyun Huang, Peng Wang, Yong Xia, Le Lu, Adam Harrison, Heping Hu, Jing Xiao連結 | https://arxiv.org/abs/2012.06964 [65] Using Computer Vision to Automate Hand Detection and Tracking of Surgeon Movements in Videos of Open Surgery作者 | Michael Zhang, Xiaotian Cheng, Daniel Copeland, Arjun Desai, Melody Y. Guan, Gabriel A. Brat, Serena Yeung連結 | https://arxiv.org/abs/2012.06948 備註 | AMIA 2020 Annual Symposium[66] MiniVLM: A Smaller and Faster Vision-Language Model作者 | Jianfeng Wang, Xiaowei Hu, Pengchuan Zhang, Xiujun Li, Lijuan Wang, Lei Zhang, Jianfeng Gao, Zicheng Liu連結 | https://arxiv.org/abs/2012.06946 [67] Human Pose Transfer by Adaptive Hierarchical Deformation作者 | Jinsong Zhang, Xingzi Liu, Kun Li連結 | https://arxiv.org/abs/2012.06940 項目連結 | https://github.com/Zhangjinso/PINet_PG[68] Assessing The Importance Of Colours For CNNs In Object Recognition作者 | Aditya Singh, Alessandro Bay, Andrea Mirabile連結 | https://arxiv.org/abs/2012.06917 [69] PAIRS AutoGeo: an Automated Machine Learning Framework for Massive Geospatial Data作者 | Wang Zhou, Levente J. Klein, Siyuan Lu連結 | https://arxiv.org/abs/2012.06907 [70] AMINN: Autoencoder-based Multiple Instance Neural Network for Outcome Prediction of Multifocal Liver Metastases作者 | Jianan Chen, Helen M. C. Cheung, Laurent Milot, Anne L. Martel連結 | https://arxiv.org/abs/2012.06875 [71] Spectral Unmixing With Multinomial Mixture Kernel and Wasserstein Generative Adversarial Loss作者 | Savas Ozkan, Gozde Bozdagi Akar連結 | https://arxiv.org/abs/2012.06859 備註 | AI for Earth Sciences Workshop at NeurIPS 2020[72] LiveChess2FEN: a Framework for Classifying Chess Pieces based on CNNs作者 | David Mallasén Quintana, Alberto Antonio del Barrio García, Manuel Prieto Matías連結 | https://arxiv.org/abs/2012.06858 項目連結 | https://github.com/davidmallasen/LiveChess2FEN[73] Multi-Scale Cascading Network with Compact Feature Learning for RGB-Infrared Person Re-Identification作者 | Can Zhang, Hong Liu, Wei Guo, Mang Ye連結 | https://arxiv.org/abs/2012.06843 備註 | 8 pages, 5 figures, ICPR2020 conference[74] High Order Local Directional Pattern Based Pyramidal Multi-structure for Robust Face Recognition作者 | Almabrok Essa, Vijayan Asari連結 | https://arxiv.org/abs/2012.06838 [75] Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation作者 | Bin Yan, Xinyu Zhang, Dong Wang, Huchuan Lu, Xiaoyun Yang連結 | https://arxiv.org/abs/2012.06815 備註 | arXiv admin note: text overlap with arXiv:2007.02024[76] Fine-grained Classification via Categorical Memory Networks作者 | Weijian Deng, Joshua Marsh, Stephen Gould, Liang Zheng連結 | https://arxiv.org/abs/2012.06793 備註 | 10 pages, 9 figures, 7 tables; this version is not fully edited and will be updated soon[77] DETR for Pedestrian Detection作者 | Matthieu Lin, Chuming Li, Xingyuan Bu, Ming Sun, Chen Lin, Junjie Yan, Wanli Ouyang, Zhidong Deng連結 | https://arxiv.org/abs/2012.06785 [78] Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces作者 | Berk Kaya, Suryansh Kumar, Carlos Oliveira, Vittorio Ferrari, Luc Van Gool連結 | https://arxiv.org/abs/2012.06777 [79] An Overview of Depth Cameras and Range Scanners Based on Time-of-Flight Technologies作者 | Radu Horaud, Miles Hansard, Georgios Evangelidis, Clement Menier連結 | https://arxiv.org/abs/2012.06772 [80] Fusion of Range and Stereo Data for High-Resolution Scene-Modeling作者 | Georgios D. Evangelidis, Miles Hansard, Radu Horaud連結 | https://arxiv.org/abs/2012.06769 [81] Anomaly detection through latent space restoration using vector-quantized variational autoencoders作者 | Sergio Naval Marimont, Giacomo Tarroni連結 | https://arxiv.org/abs/2012.06765 備註 | 4 Pages, 4 Figures. Submitted to ISBI 2021[82] Periocular in the Wild Embedding Learning with Cross-Modal Consistent Knowledge Distillation作者 | Yoon Gyo Jung, Jaewoo Park, Cheng Yaw Low, Leslie Ching Ow Tiong, Andrew Beng Jin Teoh連結 | https://arxiv.org/abs/2012.06746 [83] Computer Vision and Normalizing Flow Based Defect Detection作者 | Zijian Kuang, Xinran Tie連結 | https://arxiv.org/abs/2012.06737 [84] Multimodal In-bed Pose and Shape Estimation under the Blankets作者 | Yu Yin, Joseph P. Robinson, Yun Fu連結 | https://arxiv.org/abs/2012.06735 [85] PoP-Net: Pose over Parts Network for Multi-Person 3D Pose Estimation from a Depth Image作者 | Yuliang Guo, Zhong Li, Zekun Li, Xiangyu Du, Shuxue Quan, Yi Xu連結 | https://arxiv.org/abs/2012.06734 [86] Mask Guided Matting via Progressive Refinement Network作者 | Qihang Yu, Jianming Zhang, He Zhang, Yilin Wang, Zhe Lin, Ning Xu, Yutong Bai, Alan Yuille連結 | https://arxiv.org/abs/2012.06722 [87] Teacher-Student Asynchronous Learning with Multi-Source Consistency for Facial Landmark Detection作者 | Rongye Meng, Sanping Zhou, Xingyu Wan, Mengliu Li, Jinjun Wang連結 | https://arxiv.org/abs/2012.06711 [88] D2IM-Net: Learning Detail Disentangled Implicit Fields from Single Images連結 | https://arxiv.org/abs/2012.06650 [89] Street-view Panoramic Video Synthesis from a Single Satellite Image作者 | Zuoyue Li, Zhaopeng Cui, Martin R. Oswald連結 | https://arxiv.org/abs/2012.06628 [90] Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memes連結 | https://arxiv.org/abs/2012.07788 備註 | Presented at NIPS 2020[91] Improving Adversarial Robustness via Probabilistically Compact Loss with Logit Constraints作者 | Xin Li, Xiangrui Li, Deng Pan, Dongxiao Zhu連結 | https://arxiv.org/abs/2012.07688 備註 | To appear in the proceedings of Thirty-Five AAAI Conference on Artificial Intelligence (AAAI-21)[92] Biomechanical modelling of brain atrophy through deep learning作者 | Mariana da Silva, Kara Garcia, Carole H. Sudre, Cher Bass, M. Jorge Cardoso, Emma Robinson連結 | https://arxiv.org/abs/2012.07596 備註 | Submitted to Medical Imaging Meets NeurIPS 2020[93] Movie Summarization via Sparse Graph Construction作者 | Pinelopi Papalampidi, Frank Keller, Mirella Lapata連結 | https://arxiv.org/abs/2012.07536 備註 | Accepted at AAAI 2021[94] Phase Retrieval with Holography and Untrained Priors: Tackling the Challenges of Low-Photon Nanoscale Imaging作者 | Hannah Lawrence, David Bramherzig, Henry Li, Michael Eickenberg, Marylou Gabrie連結 | https://arxiv.org/abs/2012.07386 [95] Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction作者 | Jiafa He, Chengwei Pan, Can Yang, Ming Zhang, Yang Wang, Xiaowei Zhou, Yizhou Yu連結 | https://arxiv.org/abs/2012.07262 [96] IPN-V2 and OCTA-500: Methodology and Dataset for Retinal Image Segmentation作者 | Mingchao Li, Yuhan Zhang, Zexuan Ji, Keren Xie, Songtao Yuan, Qinghuai Liu, Qiang Chen連結 | https://arxiv.org/abs/2012.07261 [97] Accurate Cell Segmentation in Digital Pathology Images via Attention Enforced Networks作者 | Muyi Sun, Zeyi Yao, Guanhong Zhang連結 | https://arxiv.org/abs/2012.07237 備註 | 6 pages. Accepted by ICPR2020 in the first round[98] Multi-Domain Multi-Task Rehearsal for Lifelong Learning作者 | Fan Lyu, Shuai Wang, Wei Feng, Zihan Ye, Fuyuan Hu, Song Wang連結 | https://arxiv.org/abs/2012.07236 備註 | Accepted by AAAI 2021[99] D-LEMA: Deep Learning Ensembles from Multiple Annotations -- Application to Skin Lesion Segmentation作者 | Zahra Mirikharaji, Kumar Abhishek, Saeed Izadi, Ghassan Hamarneh連結 | https://arxiv.org/abs/2012.07206 [100] Pseudo Shots: Few-Shot Learning with Auxiliary Data作者 | Reza Esfandiarpoor, Mohsen Hajabdollahi, Stephen H. Bach連結 | https://arxiv.org/abs/2012.07176 [101] Learning Contextual Causality from Time-consecutive Images作者 | Hongming Zhang, Yintong Huo, Xinran Zhao, Yangqiu Song, Dan Roth連結 | https://arxiv.org/abs/2012.07138 [102] Robust Segmentation of Optic Disc and Cup from Fundus Images Using Deep Neural Networks作者 | Aniketh Manjunath, Subramanya Jois, Chandra Sekhar Seelamantula連結 | https://arxiv.org/abs/2012.07128 備註 | 12 pages, 10 figures, 8 tables; Submitted To IEEE Transactions On Image Processing[103] Leaking Sensitive Financial Accounting Data in Plain Sight using Deep Autoencoder Neural Networks作者 | Marco Schreyer, Chistian Schulze, Damian Borth連結 | https://arxiv.org/abs/2012.07110 備註 | 8 pages (excl. appendix), 4 Figures, 2 Tables, AAAI-21 Workshop on Knowledge Discovery from Unstructured Data in Financial Services, this paper is the initial accepted version[104] CHS-Net: A Deep learning approach for hierarchical segmentation of COVID-19 infected CT images作者 | Narinder Singh Punn, Sonali Agarwal連結 | https://arxiv.org/abs/2012.07079 [105] LEARN++: Recurrent Dual-Domain Reconstruction Network for Compressed Sensing CT作者 | Yi Zhang, Hu Chen, Wenjun Xia, Yang Chen, Baodong Liu, Yan Liu, Huaiqiang Sun, Jiliu Zhou連結 | https://arxiv.org/abs/2012.06983 [106] Learn-Prune-Share for Lifelong Learning作者 | Zifeng Wang, Tong Jian, Kaushik Chowdhury, Yanzhi Wang, Jennifer Dy, Stratis Ioannidis連結 | https://arxiv.org/abs/2012.06956 備註 | Accepted to the IEEE International Conference on Data Mining 2020 (ICDM'20)[107] Attentional Biased Stochastic Gradient for Imbalanced Classification作者 | Qi Qi, Yi Xu, Rong Jin, Wotao Yin, Tianbao Yang連結 | https://arxiv.org/abs/2012.06951 [108] The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models作者 | Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Yang Zhang, Michael Carbin, Zhangyang Wang連結 | https://arxiv.org/abs/2012.06908 [109] Interactive Radiotherapy Target Delineation with 3D-Fused Context Propagation作者 | Chun-Hung Chao, Hsien-Tzu Cheng, Tsung-Ying Ho, Le Lu, Min Sun連結 | https://arxiv.org/abs/2012.06873 [110] Delay Differential Neural Networks作者 | Srinivas Anumasa, P.K. Srijith連結 | https://arxiv.org/abs/2012.06800 [111] Knowledge Capture and Replay for Continual Learning作者 | Saisubramaniam Gopalakrishnan, Pranshu Ranjan Singh, Haytham Fayek, Savitha Ramasamy, Arulmurugan Ambikapathi連結 | https://arxiv.org/abs/2012.06789 [112] Generative Adversarial Networks for Automatic Polyp Segmentation作者 | Awadelrahman M. A. Ali Ahmed (University of Oslo)連結 | https://arxiv.org/abs/2012.06771 備註 | MediaEval20, Multimedia Evaluation Workshop, December 14-15 2020, Online[113] HI-Net: Hyperdense Inception 3D UNet for Brain Tumor Segmentation作者 | Saqib Qamar, Parvez Ahmad, Linlin Shen連結 | https://arxiv.org/abs/2012.06760 備註 | Accepted for MICCAI BraTS 2020[114] Sampling Training Data for Continual Learning Between Robots and the Cloud作者 | Sandeep Chinchali, Evgenya Pergament, Manabu Nakanoya, Eyal Cidon, Edward Zhang, Dinesh Bharadia, Marco Pavone, Sachin Katti連結 | https://arxiv.org/abs/2012.06739 備註 | International Symposium on Experimental Robotics (ISER) 2020, Malta[115] Learning Consistent Deep Generative Models from Sparse Data via Prediction Constraints作者 | Gabriel Hope, Madina Abdrakhmanova, Xiaoyin Chen, Michael C. Hughes, Michael C. Hughes, Erik B. Sudderth連結 | https://arxiv.org/abs/2012.06718