出品 | 深度學習這件小事公眾號
計算機視覺（5月13日更新版）
[1] Efficient and Interpretable Infrared and Visible Image Fusion Via Algorithm Unrolling作者 | Zixiang Zhao, Shuang Xu, Chunxia Zhang, Junmin Liu, Jiangshe Zhang連結 | https://arxiv.org/abs/2005.05896 [2] Latent Fingerprint Registration via Matching Densely Sampled Points作者 | Shan Gu, Jianjiang Feng, Jiwen Lu, Jie Zhou連結 | https://arxiv.org/abs/2005.05878 [3] Recurrent and Spiking Modeling of Sparse Surgical Kinematics作者 | Neil Getty, Zixuan Zhou, Stephan Gruessner, Liaohai Chen, Fangfang Xia連結 | https://arxiv.org/abs/2005.05868 [4] Neural Architecture Transfer作者 | Zhichao Lu, Gautam Sreekumar, Erik Goodman, Wolfgang Banzhaf, Kalyanmoy Deb, Vishnu Naresh Boddeti連結 | https://arxiv.org/abs/2005.05859 [5] Probabilistic Semantic Segmentation Refinement by Monte Carlo Region Growing作者 | Philipe A. Dias, Henry Medeiros連結 | https://arxiv.org/abs/2005.05856 備註 | Submitted to IEEE Transactions on Image Processing (April 2020)[6] Bayesian Fusion for Infrared and Visible Images作者 | Zixiang Zhao, Shuang Xu, Chunxia Zhang, Junmin Liu, Jiangshe Zhang連結 | https://arxiv.org/abs/2005.05839 [7] A Novel Distributed Approximate Nearest Neighbor Method for Real-time Face Recognition作者 | Aysan Aghazadeh, Maryam Amirmazlaghani連結 | https://arxiv.org/abs/2005.05824 [8] One-Shot Recognition of Manufacturing Defects in Steel Surfaces作者 | Aditya M. Deshpande, Ali A. Minai, Manish Kumar連結 | https://arxiv.org/abs/2005.05815 備註 | Accepted for publication in NAMRC 48[9] HDD-Net: Hybrid Detector Descriptor with Mutual Interactive Learning作者 | Axel Barroso-Laguna, Yannick Verdie, Benjamin Busam, Krystian Mikolajczyk連結 | https://arxiv.org/abs/2005.05777 [10] Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting作者 | Xiyang Liu, Jie Yang, Tieqiang Wang, Wenrui Ding連結 | https://arxiv.org/abs/2005.05776 [11] ReadNet:Towards Accurate ReID with Limited and Noisy Samples作者 | Yitian Li, Ruini Xue, Mengmeng Zhu, Qing Xu, Zenglin Xu連結 | https://arxiv.org/abs/2005.05740 [12] Skeleton-Aware Networks for Deep Motion Retargeting作者 | Kfir Aberman, Peizhuo Li, Dani Lischinski, Olga Sorkine-Hornung, Daniel Cohen-Or, Baoquan Chen連結 | https://arxiv.org/abs/2005.05732 項目連結 | https://deepmotionediting.github.io/retargeting[13] IterDet: Iterative Scheme for ObjectDetection in Crowded Environments作者 | Danila Rukhovich, Konstantin Sofiiuk, Danil Galeev, Olga Barinova, Anton Konushin連結 | https://arxiv.org/abs/2005.05708 [14] Automatic clustering of Celtic coins based on 3D point cloud pattern analysis作者 | Sofiane Horache, Jean-Emmanuel Deschaud, François Goulette, Katherine Gruel, Thierry Lejars連結 | https://arxiv.org/abs/2005.05705 [15] RetinotopicNet: An Iterative Attention Mechanism Using Local Descriptors with Global Context作者 | Thomas Kurbiel, Shahrzad Khaleghian連結 | https://arxiv.org/abs/2005.05701 [16] Stillleben: Realistic Scene Synthesis for Deep Learning in Robotics作者 | Max Schwarz, Sven Behnke連結 | https://arxiv.org/abs/2005.05659 備註 | Accepted for ICRA 2020[17] Detecting CNN-Generated Facial Images in Real-World Scenarios作者 | Nils Hulzebosch, Sarah Ibrahimi, Marcel Worring連結 | https://arxiv.org/abs/2005.05632 備註 | Accepted to the workshop on Media Forensics at CVPR 2020[18] Unsupervised Multi-label Dataset Generation from Web Data作者 | Carlos Roig, David Varas, Issey Masuda, Juan Carlos Riveiro, Elisenda Bou-Balust連結 | https://arxiv.org/abs/2005.05623 備註 | The 3rd Workshop on Visual Understanding by Learning from Web Data 2019[19] Discriminative Multi-modality Speech Recognition作者 | Bo Xu, Cheng Lu, Yandong Guo, Jacob Wang連結 | https://arxiv.org/abs/2005.05592 備註 | Accepted to CVPR 2020[20] Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients作者 | Chengcheng Ma, Baoyuan Wu, Shibiao Xu, Yanbo Fan, Yong Zhang, Xiaopeng Zhang, Zhifeng Li連結 | https://arxiv.org/abs/2005.05552 [21] DeepFaceLab: A simple, flexible and extensible face swapping framework作者 | Ivan Petrov, Daiheng Gao, Nikolay Chervoniy, Kunlin Liu, Sugasa Marangonda, Chris Ume, Jian Jiang, Luis RP, Sheng Zhang, Pingyu Wu, Weiming Zhang連結 | https://arxiv.org/abs/2005.05535 [22] PSDet: Efficient and Universal Parking Slot Detection作者 | Zizhang Wu, Weiwei Sun, Man Wang, Xiaoquan Wang, Lizhu Ding, Fan Wang連結 | https://arxiv.org/abs/2005.05528 備註 | Accpeted to IV 2020, i.e., the 31st IEEE Intelligent Vehicles Symposium[23] A Novel Granular-Based Bi-Clustering Method of Deep Mining the Co-Expressed Genes作者 | Kaijie Xu, Witold Pedrycz, Zhiwu Li, Yinghui Quan, Weike Nie連結 | https://arxiv.org/abs/2005.05519 [24] Real-time Facial Expression Recognition "In The Wild'' by Disentangling 3D Expression from Identity作者 | Mohammad Rami Koujan, Luma Alharbawee, Giorgos Giannakakis, Nicolas Pugeault, Anastasios Roussos連結 | https://arxiv.org/abs/2005.05509 備註 | to be published in 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)[25] 3DV: 3D Dynamic Voxel for Action Recognition in Depth Video作者 | Yancheng Wang, Yang Xiao, Fu Xiong, Wenxiang Jiang, Zhiguo Cao, Joey Tianyi Zhou, Junsong Yuan連結 | https://arxiv.org/abs/2005.05501 備註 | Accepted by CVPR2020[26] Train and Deploy an Image Classifier for Disaster Response作者 | Jianyu Mao, Kiana Harris, Nae-Rong Chang, Caleb Pennell, Yiming Ren連結 | https://arxiv.org/abs/2005.05495 [27] Combining Deep Learning with Geometric Features for Image based Localization in the Gastrointestinal Tract作者 | Jingwei Song, Mitesh Patel, Andreas Girgensohn, Chelhwon Kim連結 | https://arxiv.org/abs/2005.05481 [28] VIDIT: Virtual Image Dataset for Illumination Transfer作者 | Majed El Helou, Ruofan Zhou, Johan Barthas, Sabine Susstrunk連結 | https://arxiv.org/abs/2005.05460 項目連結 | https://github.com/majedelhelou/VIDIT[29] Online Monitoring for Neural Network Based Monocular Pedestrian Pose Estimation作者 | Arjun Gupta, Luca Carlone連結 | https://arxiv.org/abs/2005.05451 備註 | Accepted to ITSC 2020[30] Target-Independent Domain Adaptation for WBC Classification using Generative Latent Search作者 | Prashant Pandey, Prathosh AP, Vinay Kyatham, Deepak Mishra, Tathagato Rai Dastidar連結 | https://arxiv.org/abs/2005.05432 [31] Optimizing Vessel Trajectory Compression作者 | Giannis Fikioris, Kostas Patroumpas, Alexander Artikis連結 | https://arxiv.org/abs/2005.05418 [32] A Parallel Hybrid Technique for Multi-Noise Removal from Grayscale Medical Images作者 | Nora Youssef, Abeer M. Mahmoud, El-Sayed M. El-Horbaty連結 | https://arxiv.org/abs/2005.05371 [33] Planning to Explore via Self-Supervised World Models作者 | Ramanan Sekar, Oleh Rybkin, Kostas Daniilidis, Pieter Abbeel, Danijar Hafner, Deepak Pathak連結 | https://arxiv.org/abs/2005.05960 項目連結 | https://ramanans1.github.io/plan2explore/[34] Localized convolutional neural networks for geospatial wind forecasting作者 | Arnas Uselis, Mantas Lukoševičius, Lukas Stasytis連結 | https://arxiv.org/abs/2005.05930 [35] Adipose Tissue Segmentation in Unlabeled Abdomen MRI using Cross Modality Domain Adaptation作者 | Samira Masoudi, Syed M. Anwar, Stephanie A. Harmon, Peter L. Choyke, Baris Turkbey, Ulas Bagci連結 | https://arxiv.org/abs/2005.05761 備註 | EMBC 2020 conference[36] Unpaired Motion Style Transfer from Video to Animation作者 | Kfir Aberman, Yijia Weng, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen連結 | https://arxiv.org/abs/2005.05751 項目連結 | https://deepmotionediting.github.io/style_transfer代碼 | https://github.com/DeepMotionEditing/deep-motion-editing[37] Very High Resolution Land Cover Mapping of Urban Areas at Global Scale with Convolutional Neural Networks作者 | Thomas Tilak (1), Arnaud Braun (1), David Chandler (1), Nicolas David (1), Sylvain Galopin (1), Amélie Lombard (2), Michaël Michaud (1), Camille Parisel (1), Matthieu Porte (1), Marjorie Robert (1) ((1) Institut National de l'Information Géographique et Forestière, (2) CEREMA)連結 | https://arxiv.org/abs/2005.05652 備註 | 8 pages, 14 figures, ISPRS Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences[38] Invertible Image Rescaling作者 | Mingqing Xiao, Shuxin Zheng, Chang Liu, Yaolong Wang, Di He, Guolin Ke, Jiang Bian, Zhouchen Lin, Tie-Yan Liu連結 | https://arxiv.org/abs/2005.05650 [39] Understanding and Correcting Low-quality Retinal Fundus Images for Clinical Analysis作者 | Ziyi Shen, Huazhu Fu, Jianbing Shen, Ling Shao連結 | https://arxiv.org/abs/2005.05594 [40] Multi-Channel Transfer Learning of Chest X-ray Images for Screening of COVID-19作者 | Sampa Misra, Seungwan Jeon, Seiyon Lee, Ravi Managuli, Chulhong Kim連結 | https://arxiv.org/abs/2005.05576 [41] High-Fidelity Accelerated MRI Reconstruction by Scan-Specific Fine-Tuning of Physics-Based Neural Networks作者 | Seyed Amir Hossein Hosseini, Burhaneddin Yaman, Steen Moeller, Mehmet Akçakaya連結 | https://arxiv.org/abs/2005.05550 [42] Making Robots Draw A Vivid Portrait In Two Minutes作者 | Fei Gao, Jingjie Zhu, Zeyuan Yu, Peng Li, Tao Wang連結 | https://arxiv.org/abs/2005.05526 [43] Jigsaw-VAE: Towards Balancing Features in Variational Autoencoders作者 | Saeid Asgari Taghanaki, Mohammad Havaei, Alex Lamb, Aditya Sanghi, Ara Danielyan, Tonya Custis連結 | https://arxiv.org/abs/2005.05496 [44] Deep Medical Image Analysis with Representation Learning and Neuromorphic Computing作者 | Neil Getty, Thomas Brettin, Dong Jin, Rick Stevens, Fangfang Xia連結 | https://arxiv.org/abs/2005.05431 [45] Identifying Mechanical Models through Differentiable Simulations作者 | Changkyu Song, Abdeslam Boularias連結 | https://arxiv.org/abs/2005.05410 備註 | to be published in Learning for DynamIcs & Control (L4DC), June 10-11th, 2020[46] MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning作者 | Jie Lei, Liwei Wang, Yelong Shen, Dong Yu, Tamara L. Berg, Mohit Bansal連結 | https://arxiv.org/abs/2005.05402