出品 | 深度學習這件小事公眾號
計算機視覺（7月19日更新版）
[1] Representation Consolidation for Training Expert Students作者 | Zhizhong Li, Avinash Ravichandran, Charless Fowlkes, Marzia Polito, Rahul Bhotika, Stefano Soatto連結 | https://arxiv.org/abs/2107.08039 [2] CCVS: Context-aware Controllable Video Synthesis作者 | Guillaume Le Moing, Jean Ponce, Cordelia Schmid連結 | https://arxiv.org/abs/2107.08037 [3] Is attention to bounding boxes all you need for pedestrian action prediction?作者 | Lina Achaji, Julien Moreau, Thibault Fouqueray, Francois Aioun, Francois Charpillet連結 | https://arxiv.org/abs/2107.08031 [4] All the attention you need: Global-local, spatial-channel attention for image retrieval作者 | Chull Hwan Song, Hye Joo Han, Yannis Avrithis連結 | https://arxiv.org/abs/2107.08000 [5] Controlled AutoEncoders to Generate Faces from Voices作者 | Hao Liang, Lulan Yu, Guikang Xu, Bhiksha Raj, Rita Singh連結 | https://arxiv.org/abs/2107.07988 [6] Deep Learning to Ternary Hash Codes by Continuation作者 | Mingrui Chen, Weiyu Li, Weizhi Lu連結 | https://arxiv.org/abs/2107.07987 [7] Painting Style-Aware Manga Colorization Based on Generative Adversarial Networks作者 | Yugo Shimizu, Ryosuke Furuta, Delong Ouyang, Yukinobu Taniguchi, Ryota Hinami, Shonosuke Ishiwatari連結 | https://arxiv.org/abs/2107.07943 備註 | Accepted to ICIP 2021[8] Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks作者 | Vivien Sainte Fare Garnot, Loic Landrieu連結 | https://arxiv.org/abs/2107.07933 項目連結 | https://github.com/VSainteuf/utae-paps[9] A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets作者 | Muhammed Muzammul, Xi Li連結 | https://arxiv.org/abs/2107.07927 [10] A Survey on Bias in Visual Datasets作者 | Simone Fabbrizzi, Symeon Papadopoulos, Eirini Ntoutsi, Ioannis Kompatsiaris連結 | https://arxiv.org/abs/2107.07919 [11] Unsupervised Discovery of Object Radiance Fields作者 | Hong-Xing Yu, Leonidas J. Guibas, Jiajun Wu連結 | https://arxiv.org/abs/2107.07905 項目連結 | https://kovenyu.com/uorf/[12] Progressive Deep Video Dehazing without Explicit Alignment Estimation連結 | https://arxiv.org/abs/2107.07837 [13] A Theoretical Analysis of Granulometry-based Roughness Measures on Cartosat DEMs作者 | Nagajothi Kannan, Sravan Danda, Aditya Challa, Daya Sagar B S連結 | https://arxiv.org/abs/2107.07827 備註 | Under review at IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing[14] Efficient automated U-Net based tree crown delineation using UAV multi-spectral imagery on embedded devices作者 | Kostas Blekos, Stavros Nousias, Aris S Lalos連結 | https://arxiv.org/abs/2107.07826 備註 | 6 pages, 7 figures, 2 tables[15] Contrastive Predictive Coding for Anomaly Detection作者 | Puck de Haan, Sindy Löwe連結 | https://arxiv.org/abs/2107.07820 備註 | 7 pages, ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning[16] Multiple Instance Learning with Auxiliary Task Weighting for Multiple Myeloma Classification作者 | Talha Qaiser, Stefan Winzeck, Theodore Barfoot, Tara Barwick, Simon J. Doran, Martin F. Kaiser, Linda Wedlake, Nina Tunariu, Dow-Mu Koh, Christina Messiou, Andrea Rockall, Ben Glocker連結 | https://arxiv.org/abs/2107.07805 備註 | Accepted at MICCAI 2021[17] Conditional Directed Graph Convolution for 3D Human Pose Estimation作者 | Wenbo Hu, Changgong Zhang, Fangneng Zhan, Lei Zhang, Tien-Tsin Wong連結 | https://arxiv.org/abs/2107.07797 [18] Attention-based Vehicle Self-Localization with HD Feature Maps作者 | Nico Engel, Vasileios Belagiannis, Klaus Dietmayer連結 | https://arxiv.org/abs/2107.07787 備註 | Accepted for publication at 24th IEEE International Conference on Intelligent Transportation Systems (ITSC 2021)[19] Pose Normalization of Indoor Mapping Datasets Partially Compliant to the Manhattan World Assumption作者 | Patrick Hübner, Martin Weinmann, Sven Wursthorn, Stefan Hinz連結 | https://arxiv.org/abs/2107.07778 [20] Rectifying the Shortcut Learning of Background: Shared Object Concentration for Few-Shot Image Recognition作者 | Xu Luo, Longhui Wei, Liangjian Wen, Jinrong Yang, Lingxi Xie, Zenglin Xu, Qi Tian連結 | https://arxiv.org/abs/2107.07746 備註 | 23 pages, 17 figures[21] DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference作者 | Chaojian Li, Wuyang Chen, Yuchen Gu, Tianlong Chen, Yonggan Fu, Zhangyang Wang, Yingyan Lin連結 | https://arxiv.org/abs/2107.07706 [22] A Comparison of Deep Learning Classification Methods on Small-scale Image Data set: from Converlutional Neural Networks to Visual Transformers作者 | Peng Zhao, Chen Li, Md Mamunur Rahaman, Hechen Yang, Tao Jiang, Marcin Grzegorzek連結 | https://arxiv.org/abs/2107.07699 [23] Self-Supervised Learning Framework for Remote Heart Rate Estimation Using Spatiotemporal Augmentation作者 | Hao Wang, Euijoon Ahn, Jinman Kim連結 | https://arxiv.org/abs/2107.07695 [24] CutDepth:Edge-aware Data Augmentation in Depth Estimation作者 | Yasunori Ishii, Takayoshi Yamashita連結 | https://arxiv.org/abs/2107.07684 [25] Semi-supervised 3D Hand-Object Pose Estimation via Pose Dictionary Learning作者 | Zida Cheng, Siheng Chen, Ya Zhang連結 | https://arxiv.org/abs/2107.07676 [26] Align before Fuse: Vision and Language Representation Learning with Momentum Distillation作者 | Junnan Li, Ramprasaath R. Selvaraju, Akhilesh Deepak Gotmare, Shafiq Joty, Caiming Xiong, Steven Hoi連結 | https://arxiv.org/abs/2107.07651 [27] An Energy-Efficient Edge Computing Paradigm for Convolution-based Image Upsampling作者 | Ian Colbert, Ken Kreutz-Delgado, Srinjoy Das連結 | https://arxiv.org/abs/2107.07647 [28] Multi-Level Contrastive Learning for Few-Shot Problems作者 | Qing Chen, Jian Zhang連結 | https://arxiv.org/abs/2107.07608 [29] Real-Time Violence Detection Using CNN-LSTM連結 | https://arxiv.org/abs/2107.07578 [30] Real-Time Face Recognition System for Remote Employee Tracking作者 | Mohammad Sabik Irbaz, MD Abdullah Al Nasim, Refat E Ferdous連結 | https://arxiv.org/abs/2107.07576 備註 | Accepted in International Conference on Big Data, IoT and Machine Learning (BIM 2021)[31] OdoViz: A 3D Odometry Visualization and Processing Tool作者 | Saravanabalagi Ramachandran, John McDonald連結 | https://arxiv.org/abs/2107.07557 [32] Unsupervised 3D Human Mesh Recovery from Noisy Point Clouds作者 | Xinxin Zuo, Sen Wang, Minglun Gong, Li Cheng連結 | https://arxiv.org/abs/2107.07539 [33] In-Bed Person Monitoring Using Thermal Infrared Sensors作者 | Elias Josse, Amanda Nerborg, Kevin Hernandez-Diaz, Fernando Alonso-Fernandez連結 | https://arxiv.org/abs/2107.07986 備註 | Accepted for publication at FedCSIS 2021[34] Unpaired cross-modality educed distillation (CMEDL) applied to CT lung tumor segmentation作者 | Jue Jiang, Andreas Rimner, Joseph O. Deasy, Harini Veeraraghavan連結 | https://arxiv.org/abs/2107.07985 備註 | This manuscript is current under review at IEEE Transactions on Medical Imaging[35] Joint Semi-supervised 3D Super-Resolution and Segmentation with Mixed Adversarial Gaussian Domain Adaptation作者 | Nicolo Savioli, Antonio de Marvao, Wenjia Bai, Shuo Wang, Stuart A. Cook, Calvin W.L. Chin, Daniel Rueckert, Declan P. O'Regan連結 | https://arxiv.org/abs/2107.07975 [36] Lightness Modulated Deep Inverse Tone Mapping作者 | Kanglin Liu, Gaofeng Cao, Jiang Duan, Guoping Qiu連結 | https://arxiv.org/abs/2107.07907 備註 | 11 pages, 10 figures[37] Measuring and Explaining the Inter-Cluster Reliability of Multidimensional Projections作者 | Hyeon Jeon, Hyung-Kwon Ko, Jaemin Jo, Youngtaek Kim, Jinwook Seo連結 | https://arxiv.org/abs/2107.07859 備註 | IEEE Transactions of Visualization and Computer Graphics (TVCG, Proc. VIS 2021), to appear[38] Graph Representation Learning for Road Type Classification作者 | Zahra Gharaee, Shreyas Kowshik, Oliver Stromann, Michael Felsberg連結 | https://arxiv.org/abs/2107.07791 [39] Wasserstein Distances, Geodesics and Barycenters of Merge Trees作者 | Mathieu Pont, Jules Vidal, Julie Delon, Julien Tierny連結 | https://arxiv.org/abs/2107.07789 [40] DoReMi: First glance at a universal OMR dataset作者 | Elona Shatri, György Fazekas連結 | https://arxiv.org/abs/2107.07786 備註 | 7 pages, including 2 pages appendix. Accepted for publishing at the 3rd International Workshop on Reading Music Systems 2021[41] Exploiting generative self-supervised learning for the assessment of biological images with lack of annotations: a COVID-19 case-study作者 | Alessio Mascolini, Dario Cardamone, Francesco Ponzio, Santa Di Cataldo, Elisa Ficarra連結 | https://arxiv.org/abs/2107.07761 [42] NeXtQSM -- A complete deep learning pipeline for data-consistent quantitative susceptibility mapping trained with hybrid data作者 | Francesco Cognolato, Kieran O'Brien, Jin Jin, Simon Robinson, Frederik B. Laun, Markus Barth, Steffen Bollmann連結 | https://arxiv.org/abs/2107.07752 [43] Optical Inspection of the Silicon Micro-strip Sensors for the CBM Experiment employing Artificial Intelligence作者 | E. Lavrik, M. Shiroya, H.R. Schmidt, A. Toia, J.M. Heuser連結 | https://arxiv.org/abs/2107.07714 [44] Probabilistic Appearance-Invariant Topometric Localization with New Place Awareness作者 | Ming Xu, Tobias Fischer, Niko Sünderhauf, Michael Milford連結 | https://arxiv.org/abs/2107.07707 [45] Depth Estimation from Monocular Images and Sparse radar using Deep Ordinal Regression Network作者 | Chen-Chou Lo, Patrick Vandewalle連結 | https://arxiv.org/abs/2107.07596 備註 | Accepted to ICIP2021[46] The Benchmark Lottery作者 | Mostafa Dehghani, Yi Tay, Alexey A. Gritsenko, Zhe Zhao, Neil Houlsby, Fernando Diaz, Donald Metzler, Oriol Vinyals連結 | https://arxiv.org/abs/2107.07002掃描二維碼添加小助手微信（ID : HIT_NLP）