出品 | 深度学习这件小事公众号
计算机视觉（12月21日更新版）
[1] PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection作者 | Yanan Zhang, Di Huang, Yunhong Wang链接 | https://arxiv.org/abs/2012.10412 [2] Learning Complex 3D Human Self-Contact作者 | Mihai Fieraru, Mihai Zanfir, Elisabeta Oneata, Alin-Ionut Popa, Vlad Olaru, Cristian Sminchisescu链接 | https://arxiv.org/abs/2012.10366 备注 | To be published in the Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI-2021)[3] Assessing Pattern Recognition Performance of Neuronal Cultures through Accurate Simulation作者 | Gabriele Lagani, Raffaele Mazziotti, Fabrizio Falchi, Claudio Gennaro, Guido Marco Cicchini, Tommaso Pizzorusso, Federico Cremisi, Giuseppe Amato链接 | https://arxiv.org/abs/2012.10355 备注 | Submitted to NER 2021 conference[4] Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion作者 | Lam Huynh, Phong Nguyen, Jiri Matas, Esa Rahtu, Janne Heikkila链接 | https://arxiv.org/abs/2012.10296 [5] Trying Bilinear Pooling in Video-QA作者 | Thomas Winterbottom, Sarah Xiao, Alistair McLean, Noura Al Moubayed链接 | https://arxiv.org/abs/2012.10285 [6] Temporal Bilinear Encoding Network of Audio-Visual Features at Low Sampling Rates作者 | Feiyan Hu, Eva Mohedano, Noel O'Connor, Kevin McGuinness链接 | https://arxiv.org/abs/2012.10283 [7] SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation作者 | An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou链接 | https://arxiv.org/abs/2012.10217 [8] On Modality Bias in the TVQA Dataset作者 | Thomas Winterbottom, Sarah Xiao, Alistair McLean, Noura Al Moubayed链接 | https://arxiv.org/abs/2012.10210 [9] LGENet: Local and Global Encoder Network for Semantic Segmentation of Airborne Laser Scanning Point Clouds作者 | Yaping Lin, George Vosselman, Yanpeng Cao, Michael Ying Yang链接 | https://arxiv.org/abs/2012.10192 备注 | Submitted to ISPRS Journal of Photogrammetry and Remote Sensing[10] STNet: Scale Tree Network with Multi-level Auxiliator for Crowd Counting作者 | Mingjie Wang, Hao Cai, Xianfeng Han, Jun Zhou, Minglun Gong链接 | https://arxiv.org/abs/2012.10189 [11] A Holistically-Guided Decoder for Deep Representation Learning with Applications to Semantic Segmentation and Object Detection作者 | Jianbo Liu, Sijie Ren, Yuanjie Zheng, Xiaogang Wang, Hongsheng Li链接 | https://arxiv.org/abs/2012.10162 备注 | arXiv admin note: substantial text overlap with arXiv:2008.10487[12] SCNet: Training Inference Sample Consistency for Instance Segmentation作者 | Thang Vu, Haeyong Kang, Chang D. Yoo链接 | https://arxiv.org/abs/2012.10150 备注 | To appear in AAAI 2021[13] CodeVIO: Visual-Inertial Odometry with Learned Optimizable Dense Depth作者 | Xingxing Zuo, Nathaniel Merrill, Wei Li, Yong Liu, Marc Pollefeys, Guoquan Huang链接 | https://arxiv.org/abs/2012.10133 [14] Hyperspectral Image Semantic Segmentation in Cityscapes作者 | Yuxing Huang, Erqi Huang, Linsen Chen, Shaodi You, Ying Fu, Qiu Shen链接 | https://arxiv.org/abs/2012.10122 [15] Frequency Consistent Adaptation for Real World Super Resolution作者 | Xiaozhong Ji, Guangpin Tao, Yun Cao, Ying Tai, Tong Lu, Chengjie Wang, Jilin Li, Feiyue Huang链接 | https://arxiv.org/abs/2012.10102 [16] AU-Guided Unsupervised Domain Adaptive Facial Expression Recognition作者 | Kai Wang, Yuxin Gu, Xiaojiang Peng, Baigui Sun, Hao Li链接 | https://arxiv.org/abs/2012.10078 备注 | This is a very simple CD-FER framework[17] TDN: Temporal Difference Networks for Efficient Action Recognition作者 | Limin Wang, Zhan Tong, Bin Ji, Gangshan Wu链接 | https://arxiv.org/abs/2012.10071 [18] PointINet: Point Cloud Frame Interpolation Network作者 | Fan Lu, Guang Chen, Sanqing Qu, Zhijun Li, Yinlong Liu, Alois Knoll链接 | https://arxiv.org/abs/2012.10066 备注 | Accepted to AAAI 2021[19] Content Masked Loss: Human-Like Brush Stroke Planning in a Reinforcement Learning Painting Agent作者 | Peter Schaldenbrand, Jean Oh链接 | https://arxiv.org/abs/2012.10043 [20] 3D Object Classification on Partial Point Clouds: A Practical Perspective作者 | Zelin Xu, Ke Chen, Tong Zhang, C. L. Philip Chen, Kui Jia链接 | https://arxiv.org/abs/2012.10042 [21] Self-supervised Learning with Fully Convolutional Networks作者 | Zhengeng Yang, Hongshan Yu, Yong He, Zhi-Hong Mao, Ajmal Mian链接 | https://arxiv.org/abs/2012.10017 [22] Flow-based Generative Models for Learning Manifold to Manifold Mappings作者 | Xingjian Zhen, Rudrasis Chakraborty, Liu Yang, Vikas Singh链接 | https://arxiv.org/abs/2012.10013 备注 | This paper has been accepted by AAAI 2021[23] Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations作者 | Adel Ahmadyan, Liangkai Zhang, Jianing Wei, Artsiom Ablavatski, Matthias Grundmann链接 | https://arxiv.org/abs/2012.09988 项目链接 | https://github.com/google-research-datasets/Objectron[24] Relightable 3D Head Portraits from a Smartphone Video作者 | Artem Sevastopolsky, Savva Ignatiev, Gonzalo Ferrer, Evgeny Burnaev, Victor Lempitsky链接 | https://arxiv.org/abs/2012.09963 [25] Toward Transformer-Based Object Detection作者 | Josh Beal, Eric Kim, Eric Tzeng, Dong Huk Park, Andrew Zhai, Dmitry Kislyuk链接 | https://arxiv.org/abs/2012.09958 [26] Learning Compositional Radiance Fields of Dynamic Human Heads作者 | Ziyan Wang, Timur Bagautdinov, Stephen Lombardi, et al.链接 | https://arxiv.org/abs/2012.09955 [27] Attention-based Image Upsampling作者 | Souvik Kundu, Hesham Mostafa, Sharath Nittur Sridhar, Sairam Sundaresan链接 | https://arxiv.org/abs/2012.09904 [28] Exploring Motion Boundaries in an End-to-End Network for Vision-based Parkinson's Severity Assessment作者 | Amirhossein Dadashzadeh, Alan Whone, Michal Rolinski, Majid Mirmehdi链接 | https://arxiv.org/abs/2012.09890 [29] Object Detection based on OcSaFPN in Aerial Images with Noise作者 | Chengyuan Li, Jun Liu, Hailong Hong, Wenju Mao, Chenjie Wang, Chudi Hu, Xin Su, Bin Luo链接 | https://arxiv.org/abs/2012.09859 [30] Separation and Concentration in Deep Networks作者 | John Zarka, Florentin Guth, Stéphane Mallat链接 | https://arxiv.org/abs/2012.10424 [31] Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: Evaluation in Alzheimer's disease作者 | Martin Dyrba, Moritz Hanzig, Slawek Altenstein, et al.链接 | https://arxiv.org/abs/2012.10294 备注 | 19 pages, 9 figures/tables, source code available on GitHub[32] Multimodal Transfer Learning-based Approaches for Retinal Vascular Segmentation作者 | José Morano, Álvaro S. Hervella, Noelia Barreira, Jorge Novo, José Rouco链接 | https://arxiv.org/abs/2012.10160 [33] Spectral Reflectance Estimation Using Projector with Unknown Spectral Power Distribution作者 | Hironori Hidaka, Yusuke Monno, Masatoshi Okutomi链接 | https://arxiv.org/abs/2012.10083 备注 | Presented at CIC2020. Projector's SPD data is available at http://www.ok.sc.e.titech.ac.jp/res/PCSSfM/pro-cam_reflectance.html[34] A Surrogate Lagrangian Relaxation-based Model Compression for Deep Neural Networks作者 | Deniz Gurevin, Shanglin Zhou, Lynn Pepin, Bingbing Li, Mikhail Bragin, Caiwen Ding, Fei Miao链接 | https://arxiv.org/abs/2012.10079 [35] Information-Preserving Contrastive Learning for Self-Supervised Representations作者 | Tianhong Li, Lijie Fan, Yuan Yuan, Hao He, Yonglong Tian, Dina Katabi链接 | https://arxiv.org/abs/2012.09962 备注 | The first two authors contributed equally to this paper[36] Treadmill Assisted Gait Spoofing (TAGS): An Emerging Threat to wearable Sensor-based Gait Authentication作者 | Rajesh Kumar, Can Isik, Vir V Phoha链接 | https://arxiv.org/abs/2012.09950 [37] Fast 3-dimensional estimation of the Foveal Avascular Zone from OCTA作者 | Giovanni Ometto, Giovanni Montesano, Usha Chakravarthy, Frank Kee, Ruth E. Hogg, David P. Crabb链接 | https://arxiv.org/abs/2012.09945 备注 | 6 pages, 3 figures, submitted to IEEE I2MTC 2021 conference
