出品 | 深度學習這件小事公眾號
[1] Full-Body Awareness from Partial Observations作者 | Chris Rockwell, David F. Fouhey連結 | https://arxiv.org/abs/2008.06046 [2] DSDNet: Deep Structured self-Driving Network作者 | Wenyuan Zeng, Shenlong Wang, Renjie Liao, Yun Chen, Bin Yang, Raquel Urtasun連結 | https://arxiv.org/abs/2008.06041 [3] Towards Visually Explaining Similarity Models作者 | Meng Zheng, Srikrishna Karanam, Terrence Chen, Richard J. Radke, Ziyan Wu連結 | https://arxiv.org/abs/2008.06035 [4] BioMetricNet: deep unconstrained face verification through learning of metrics regularized onto Gaussian distributions作者 | Arslan Ali, Matteo Testa, Tiziano Bianchi, Enrico Magli連結 | https://arxiv.org/abs/2008.06021 [5] Testing the Safety of Self-driving Vehicles by Simulating Perception and Prediction作者 | Kelvin Wong, Qiang Zhang, Ming Liang, Bin Yang, Renjie Liao, Abbas Sadat, Raquel Urtasun連結 | https://arxiv.org/abs/2008.06020 [6] Black Magic in Deep Learning: How Human Skill Impacts Network Training作者 | Kanav Anand, Ziqi Wang, Marco Loog, Jan van Gemert連結 | https://arxiv.org/abs/2008.05981 備註 | presented at the British Machine Vision Conference, 2020[7] Hybrid Dynamic-static Context-aware Attention Network for Action Assessment in Long Videos作者 | Ling-An Zeng, Fa-Ting Hong, Wei-Shi Zheng, Qi-Zhi Yu, Wei Zeng, Yao-Wei Wang, Jian-Huang Lai連結 | https://arxiv.org/abs/2008.05977 備註 | ACM International Conference on Multimedia 2020[8] SIDOD: A Synthetic Image Dataset for 3D Object Pose Recognition with Distractors作者 | Mona Jalal, Josef Spjut, Ben Boudaoud, Margrit Betke連結 | https://arxiv.org/abs/2008.05955 備註 | 3 pages, 4 figures, 1 table, Accepted at CVPR 2019 Workshop[9] Estimating Magnitude and Phase of Automotive Radar Signals under Multiple Interference Sources with Fully Convolutional Networks作者 | Nicolae-Cătălin Ristea, Andrei Anghel, Radu Tudor Ionescu連結 | https://arxiv.org/abs/2008.05948 [10] On failures of RGB cameras and their effects in autonomous driving applications作者 | Francesco Secci, Andrea Ceccarelli連結 | https://arxiv.org/abs/2008.05938 備註 | preprint - accepted to the The 31st International Symposium on Software Reliability Engineering (ISSRE 2020)[11] End-to-end Contextual Perception and Prediction with Interaction Transformer作者 | Lingyun Luke Li, Bin Yang, Ming Liang, Wenyuan Zeng, Mengye Ren, Sean Segal, Raquel Urtasun連結 | https://arxiv.org/abs/2008.05927 [12] DFEW: A Large-Scale Database for Recognizing Dynamic Facial Expressions in the Wild作者 | Xingxun Jiang, Yuan Zong, Wenming Zheng, Chuangao Tang, Wanchuang Xia, Cheng Lu, Jiateng Liu連結 | https://arxiv.org/abs/2008.05924 [13] LGNN: a Context-aware Line Segment Detector作者 | Quan Meng, Jiakai Zhang, Qiang Hu, Xuming He, Jingyi Yu連結 | https://arxiv.org/abs/2008.05892 [14] DF-GAN: Deep Fusion Generative Adversarial Networks for Text-to-Image Synthesis作者 | Ming Tao, Hao Tang, Songsong Wu, Nicu Sebe, Fei Wu, Xiao-Yuan Jing連結 | https://arxiv.org/abs/2008.05865 [15] Self-supervised Video Representation Learning by Pace Prediction作者 | Jiangliu Wang, Jianbo Jiao, Yun-Hui Liu連結 | https://arxiv.org/abs/2008.05861 備註 | Accepted by ECCV 2020[16] Recurrent Deconvolutional Generative Adversarial Networks with Application to Text Guided Video Generation作者 | Hongyuan Yu, Yan Huang, Lihong Pi, Liang Wang連結 | https://arxiv.org/abs/2008.05856 [17] Localizing the Common Action Among a Few Videos作者 | Pengwan Yang, Vincent Tao Hu, Pascal Mettes, Cees G. M. Snoek連結 | https://arxiv.org/abs/2008.05826 [18] Shift Equivariance in Object Detection作者 | Marco Manfredi, Yu Wang連結 | https://arxiv.org/abs/2008.05787 備註 | Accepted at ECCV 2020 Workshop: Beyond mAP: Reassessing the Evaluation of Object Detectors[19] Predicting Visual Overlap of Images Through Interpretable Non-Metric Box Embeddings作者 | Anita Rau, Guillermo Garcia-Hernando, Danail Stoyanov, Gabriel J. Brostow, Daniyar Turmukhambetov連結 | https://arxiv.org/abs/2008.05785 [20] CycleMorph: Cycle Consistent Unsupervised Deformable Image Registration作者 | Boah Kim, Dong Hwan Kim, Seong Ho Park, Jieun Kim, June-Goo Lee, Jong Chul Ye連結 | https://arxiv.org/abs/2008.05772 [21] Weakly Supervised Generative Network for Multiple 3D Human Pose Hypotheses作者 | Chen Li, Gim Hee Lee連結 | https://arxiv.org/abs/2008.05770 備註 | Accepted to BMVC2020[22] Powers of layers for image-to-image translation作者 | Hugo Touvron, Matthijs Douze, Matthieu Cord, Hervé Jégou連結 | https://arxiv.org/abs/2008.05763 [23] Adversarial Knowledge Transfer from Unlabeled Data作者 | Akash Gupta, Rameswar Panda, Sujoy Paul, Jianming Zhang, Amit K. Roy-Chowdhury連結 | https://arxiv.org/abs/2008.05746 備註 | Accepted to ACM Multimedia 2020[24] Pose Estimation for Vehicle-mounted Cameras via Horizontal and Vertical Planes作者 | Istan Gergo Gal, Daniel Barath, Levente Hajder連結 | https://arxiv.org/abs/2008.05743 [25] SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images作者 | Jiapeng Tang, Xiaoguang Han, Mingkui Tan, Xin Tong, Kui Jia連結 | https://arxiv.org/abs/2008.05742 [26] Reliability of Decision Support in Cross-spectral Biometric-enabled Systems作者 | Kenneth Lai, Svetlana N. Yanushkevich, Vlad Shmerko連結 | https://arxiv.org/abs/2008.05735 備註 | submitted to IEEE International Conference on Systems, Man, and Cybernetics[27] An Ensemble of Knowledge Sharing Models for Dynamic Hand Gesture Recognition作者 | Kenneth Lai, Svetlana Yanushkevich連結 | https://arxiv.org/abs/2008.05732 備註 | Accepted at International Joint Conference on Neural Network[28] ExplAIn: Explanatory Artificial Intelligence for Diabetic Retinopathy Diagnosis作者 | Gwenolé Quellec, Hassan Al Hajj, Mathieu Lamard, Pierre-Henri Conze, Pascale Massin, Béatrice Cochener連結 | https://arxiv.org/abs/2008.05731 [29] Contextual Diversity for Active Learning作者 | Sharat Agarwal, Himanshu Arora, Saket Anand, Chetan Arora連結 | https://arxiv.org/abs/2008.05723 備註 | A variant of this report is accepted in ECCV 2020[30] Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition作者 | Taeoh Kim, Hyeongmin Lee, MyeongAh Cho, Ho Seong Lee, Dong Heon Cho, Sangyoun Lee連結 | https://arxiv.org/abs/2008.05721 備註 | European Conference on Computer Vision (ECCV) 2020, 1st Visual Inductive Priors for Data-Efficient Deep Learning Workshop (Oral)[31] Alleviating Human-level Shift : A Robust Domain Adaptation Method for Multi-person Pose Estimation作者 | Xixia Xu, Qi Zou, Xue Lin連結 | https://arxiv.org/abs/2008.05717 備註 | Accepted By ACM MM'2020[32] Modeling Caricature Expressions by 3D Blendshape and Dynamic Texture作者 | Keyu Chen, Jianmin Zheng, Jianfei Cai, Juyong Zhang連結 | https://arxiv.org/abs/2008.05714 備註 | Accepted by the 28th ACM International Conference on Multimedia (ACM MM 2020)[33] Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D作者 | Jonah Philion, Sanja Fidler連結 | https://arxiv.org/abs/2008.05711 [34] Robust Image Matching By Dynamic Feature Selection作者 | Hao Huang, Jianchun Chen, Xiang Li, Lingjing Wang, Yi Fang連結 | https://arxiv.org/abs/2008.05708 [35] Network Architecture Search for Domain Adaptation作者 | Yichen Li, Xingchao Peng連結 | https://arxiv.org/abs/2008.05706 [36] What leads to generalization of object proposals?作者 | Rui Wang, Dhruv Mahajan, Vignesh Ramanathan連結 | https://arxiv.org/abs/2008.05700 [37] Visual Localization for Autonomous Driving: Mapping the Accurate Location in the City Maze作者 | Dongfang Liu, Yiming Cui, Xiaolei Guo, Wei Ding, Baijian Yang, Yingjie Chen連結 | https://arxiv.org/abs/2008.05678 [38] Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation作者 | Jialian Wu, Liangchen Song, Tiancai Wang, Qian Zhang, Junsong Yuan連結 | https://arxiv.org/abs/2008.05676 備註 | Accepted to Proceedings of the 28th ACM International Conference on Multimedia (ACM MM'20), Seattle, WA, USA[39] Feature Binding with Category-Dependant MixUp for Semantic Segmentation and Adversarial Robustness作者 | Md Amirul Islam, Matthew Kowal, Konstantinos G. Derpanis, Neil D. B. Bruce連結 | https://arxiv.org/abs/2008.05667 備註 | Accepted to BMVC 2020 (Oral)[40] What Should Not Be Contrastive in Contrastive Learning作者 | Tete Xiao, Xiaolong Wang, Alexei A. Efros, Trevor Darrell連結 | https://arxiv.org/abs/2008.05659 [41] Sparse Coding Driven Deep Decision Tree Ensembles for Nuclear Segmentation in Digital Pathology Images作者 | Jie Song, Liang Xiao, Mohsen Molaei, Zhichao Lian連結 | https://arxiv.org/abs/2008.05657 備註 | Submitted to IEEE Transactions on Image Processing[42] ISIA Food-500: A Dataset for Large-Scale Food Recognition via Stacked Global-Local Attention Network作者 | Weiqing Min, Linhu Liu, Zhiling Wang, Zhengdong Luo, Xiaoming Wei, Xiaolin Wei, Shuqiang Jiang連結 | https://arxiv.org/abs/2008.05655 備註 | Accepted by ACM Multimedia 2020[43] Few shot clustering for indoor occupancy detection with extremely low-quality images from battery free cameras作者 | Homagni Saha, Sin Yon Tan, Ali Saffari, Mohamad Katanbaf, Joshua R. Smith, Soumik Sarkar連結 | https://arxiv.org/abs/2008.05654 [44] We Have So Much In Common: Modeling Semantic Relational Set Abstractions in Videos作者 | Alex Andonian, Camilo Fosco, Mathew Monfort, Allen Lee, Rogerio Feris, Carl Vondrick, Aude Oliva連結 | https://arxiv.org/abs/2008.05596 備註 | European Conference on Computer Vision (ECCV) 2020, accepted[45] Self-Path: Self-supervision for Classification of Pathology Images with Limited Annotations作者 | Navid Alemi Koohbanani, Balagopal Unnikrishnan, Syed Ali Khurram, Pavitra Krishnaswamy, Nasir Rajpoot連結 | https://arxiv.org/abs/2008.05571 [46] Generating Person-Scene Interactions in 3D Scenes作者 | Siwei Zhang, Yan Zhang, Qianli Ma, Michael J. Black, Siyu Tang連結 | https://arxiv.org/abs/2008.05570 [47] Facial Expression Recognition Under Partial Occlusion from Virtual Reality Headsets based on Transfer Learning作者 | Bita Houshmand, Naimul Khan連結 | https://arxiv.org/abs/2008.05563 備註 | To be presented at the IEEE BigMM 2020[48] Continual Class Incremental Learning for CT Thoracic Segmentation作者 | Abdelrahman Elskhawy, Aneta Lisowska, Matthias Keicher, Josep Henry, Paul Thomson, Nassir Navab連結 | https://arxiv.org/abs/2008.05557 [49] Co-training for On-board Deep Object Detection作者 | Gabriel Villalonga, Antonio M. Lopez連結 | https://arxiv.org/abs/2008.05534 [50] Mitigating Dataset Imbalance via Joint Generation and Classification作者 | Aadarsh Sahoo, Ankit Singh, Rameswar Panda, Rogerio Feris, Abir Das連結 | https://arxiv.org/abs/2008.05524 備註 | Accepted in ECCV2020 Workshop on Imbalance Problems in Computer Vision (IPCV)作者 | Gernot Riegler, Vladlen Koltun連結 | https://arxiv.org/abs/2008.05511 備註 | published at ECCV 2020, https://youtu.be/JDJPn3ZtfZs[52] Multi-level Stress Assessment Using Multi-domain Fusion of ECG Signal作者 | Zeeshan Ahmad, Naimul Khan連結 | https://arxiv.org/abs/2008.05503 [53] Multi-Mask Self-Supervised Learning for Physics-Guided Neural Networks in Highly Accelerated MRI作者 | Burhaneddin Yaman, Seyed Amir Hossein Hosseini, Steen Moeller, Jutta Ellermann, Kâmil Uğurbil, Mehmet Akçakaya連結 | https://arxiv.org/abs/2008.06029 [54] Deep Learning to Quantify Pulmonary Edema in Chest Radiographs作者 | Steven Horng, Ruizhi Liao, Xin Wang, Sandeep Dalal, Polina Golland, Seth J Berkowitz連結 | https://arxiv.org/abs/2008.05975 備註 | The two first authors contributed equally[55] Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations作者 | Abbas Sadat, Sergio Casas, Mengye Ren, Xinyu Wu, Pranaab Dhawan, Raquel Urtasun連結 | https://arxiv.org/abs/2008.05930 備註 | European Conference on Computer Vision (ECCV) 2020[56] Motion Similarity Modeling -- A State of the Art Report作者 | Anna Sebernegg, Peter Kán, Hannes Kaufmann連結 | https://arxiv.org/abs/2008.05872 [57] Look, Listen, and Attend: Co-Attention Network for Self-Supervised Audio-Visual Representation Learning作者 | Ying Cheng, Ruize Wang, Zhihao Pan, Rui Feng, Yuejie Zhang連結 | https://arxiv.org/abs/2008.05789 備註 | Accepted by the 28th ACM International Conference on Multimedia (ACM MM 2020)[58] Multi-Modality Pathology Segmentation Framework: Application to Cardiac Magnetic Resonance Images作者 | Zhen Zhang, Chenyu Liu, Wangbin Ding, Sihan Wang, Chenhao Pei, Mingjing Yang, Liqin Huang連結 | https://arxiv.org/abs/2008.05780 [59] Weight Equalizing Shift Scaler-Coupled Post-training Quantization作者 | Jihun Oh, SangJeong Lee, Meejeong Park, Pooni Walagaurav, Kiseok Kwon連結 | https://arxiv.org/abs/2008.05767 [60] Revisiting Temporal Modeling for Video Super-resolution作者 | Takashi Isobe, Fang Zhu, Shengjin Wang連結 | https://arxiv.org/abs/2008.05765 [61] AdaIN-Switchable CycleGAN for Efficient Unsupervised Low-Dose CT Denoising作者 | Jawook Gu, Jong Chul Ye連結 | https://arxiv.org/abs/2008.05753 [62] Towards Modality Transferable Visual Information Representation with Optimal Model Compression作者 | Rongqun Lin, Linwei Zhu, Shiqi Wang, Sam Kwong連結 | https://arxiv.org/abs/2008.05642 備註 | Accepted in ACM Multimedia 2020[63] Procedural Urban Forestry作者 | Till Niese, Sören Pirk, Bedrich Benes, Oliver Deussen連結 | https://arxiv.org/abs/2008.05567 [64] DSM-Net: Disentangled Structured Mesh Net for Controllable Generation of Fine Geometry作者 | Jie Yang, Kaichun Mo, Yu-Kun Lai, Leonidas J. Guibas, Lin Gao連結 | https://arxiv.org/abs/2008.05440