出品 | 深度學習這件小事公眾號
計算機視覺（7月7日更新版）
[1] MCMI: Multi-Cycle Image Translation with Mutual Information Constraints作者 | Xiang Xu, Megha Nawhal, Greg Mori, Manolis Savva連結 | https://arxiv.org/abs/2007.02919 [2] Are Labels Necessary for Classifier Accuracy Evaluation?作者 | Weijian Deng, Liang Zheng連結 | https://arxiv.org/abs/2007.02915 [3] Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation作者 | Fangyun Wei, Xiao Sun, Hongyang Li, Jingdong Wang, Stephen Lin連結 | https://arxiv.org/abs/2007.02846 備註 | To appear in ECCV 2020[4] Exploration of Optimized Semantic Segmentation Architectures for edge-Deployment on Drones作者 | Vivek Parmar, Narayani Bhatia, Shubham Negi, Manan Suri連結 | https://arxiv.org/abs/2007.02839 [5] Eliminating Catastrophic Interference with Biased Competition作者 | Amelia Elizabeth Pollard, Jonathan L. Shapiro連結 | https://arxiv.org/abs/2007.02833 [6] Complex Human Action Recognition in Live Videos Using Hybrid FR-DL Method作者 | Fatemeh Serpush, Mahdi Rezaei連結 | https://arxiv.org/abs/2007.02811 [7] Novel-View Human Action Synthesis作者 | Mohamed Ilyes Lakhal, Davide Boscaini, Fabio Poiesi, Oswald Lanz, Andrea Cavallaro連結 | https://arxiv.org/abs/2007.02808 [8] Gradient Origin Networks作者 | Sam Bond-Taylor, Chris G. Willcocks連結 | https://arxiv.org/abs/2007.02798 [9] Multi-Objective Neural Architecture Search Based on Diverse Structures and Adaptive Recommendation作者 | Chunnan Wang, Hongzhi Wang, Guocheng Feng, Fei Geng連結 | https://arxiv.org/abs/2007.02749 [10] Image Stitching Based on Planar Region Consensus作者 | Aocheng Li, Jie Guo, Yanwen Guo連結 | https://arxiv.org/abs/2007.02722 [11] Do Not Mask What You Do Not Need to Mask: a Parser-Free Virtual Try-On作者 | Thibaut Issenhuth, Jérémie Mary, Clément Calauzènes連結 | https://arxiv.org/abs/2007.02721 備註 | Accepted at ECCV 2020. [12] BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network作者 | Fan Deng-Ping, Zhai Yingjie, Borji Ali, Yang Jufeng, Shao Ling連結 | https://arxiv.org/abs/2007.02713 項目連結 | https://github.com/DengPingFan/BBS-Net備註 | Accepted in ECCV2020. [13] Auxiliary Learning by Implicit Differentiation作者 | Aviv Navon, Idan Achituve, Haggai Maron, Gal Chechik, Ethan Fetaya連結 | https://arxiv.org/abs/2007.02693 [14] On the Influence of Ageing on Face Morph Attacks: Vulnerability and Detection作者 | Sushma Venkatesh, Kiran Raja, Raghavendra Ramachandra, Christoph Busch連結 | https://arxiv.org/abs/2007.02684 備註 | Accepted in IJCB 2020[15] Toward unsupervised, multi-object discovery in large-scale image collections作者 | Huy V. Vo, Patrick Pérez, Jean Ponce連結 | https://arxiv.org/abs/2007.02662 備註 | Accepted for publication in ECCV 2020[16] Joint learning of Social Groups, Individuals Action and Sub-group Activities in Videos作者 | Mahsa Ehsanpour, Alireza Abedin, Fatemeh Saleh, Javen Shi, Ian Reid, Hamid Rezatofighi連結 | https://arxiv.org/abs/2007.02632 備註 | Accepted in the European Conference On Computer Vision (ECCV) 2020[17] NAPPO: Modular and scalable reinforcement learning in pytorch作者 | Albert Bou, Gianni De Fabritiis連結 | https://arxiv.org/abs/2007.02622 [18] Learning a Domain Classifier Bank for Unsupervised Adaptive Object Detection作者 | Sanli Tang, Zhanzhan Cheng, Shiliang Pu, Dashan Guo, Yi Niu, Fei Wu連結 | https://arxiv.org/abs/2007.02595 [19] Learning Graph-Convolutional Representations for Point Cloud Denoising作者 | Francesca Pistilli, Giulia Fracastoro, Diego Valsesia, Enrico Magli連結 | https://arxiv.org/abs/2007.02578 備註 | European Conference on Computer Vision (ECCV) 2020[20] Progressive Cluster Purification for Unsupervised Feature Learning作者 | Yifei Zhang, Chang Liu, Yu Zhou, Wei Wang, Weiping Wang, Qixiang Ye連結 | https://arxiv.org/abs/2007.02577 [21] Geometric Attention for Prediction of Differential Properties in 3D Point Clouds作者 | Albert Matveev, Alexey Artemov, Evgeny Burnaev連結 | https://arxiv.org/abs/2007.02571 [22] In the Wild: From ML Models to Pragmatic ML Systems作者 | Matthew Wallingford, Aditya Kusupati, Keivan Alizadeh-Vahid, Aaron Walsman, Aniruddha Kembhavi, Ali Farhadi連結 | https://arxiv.org/abs/2007.02519 項目連結 | https://github.com/RAIVNLab/InTheWild[23] EDSL: An Encoder-Decoder Architecture with Symbol-Level Features for Printed Mathematical Expression Recognition作者 | Yingnan Fu, Tingting Liu, Ming Gao, Aoying Zhou連結 | https://arxiv.org/abs/2007.02517 [24] Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrieval作者 | Xun Yang, Jianfeng Dong, Yixin Cao, Xun Wang, Meng Wang, Tat-Seng Chua連結 | https://arxiv.org/abs/2007.02503 備註 | Accepted For 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2020)[25] Learning Motion Flows for Semi-supervised Instrument Segmentation from Robotic Surgical Video作者 | Zixu Zhao, Yueming Jin, Xiaojie Gao, Qi Dou, Pheng-Ann Heng連結 | https://arxiv.org/abs/2007.02501 備註 | Accepted for MICCAI 2020[26] EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning作者 | Bailin Li, Bowen Wu, Jiang Su, Guangrun Wang, Liang Lin連結 | https://arxiv.org/abs/2007.02491 項目連結 | https://github.com/anonymous47823493/EagleEye備註 | Accepted in ECCV 2020(Oral). [27] Self-Challenging Improves Cross-Domain Generalization作者 | Zeyi Huang, Haohan Wang, Eric P. Xing, Dong Huang連結 | https://arxiv.org/abs/2007.02454 備註 | to appear at ECCV2020 as an oral paper[28] Anatomical Data Augmentation via Fluid-based Image Registration作者 | Zhengyang Shen, Zhenlin Xu, Sahin Olut, Marc Niethammer連結 | https://arxiv.org/abs/2007.02447 [29] GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis作者 | Katja Schwarz, Yiyi Liao, Michael Niemeyer, Andreas Geiger連結 | https://arxiv.org/abs/2007.02442 [30] Estimation of Ground Contacts from Human Gait by a Wearable Inertial Measurement Unit using machine learning作者 | Muhammad Junaid Umer, Qaiser Riaz連結 | https://arxiv.org/abs/2007.02433 [31] Contextual-Relation Consistent Domain Adaptation for Semantic Segmentation作者 | Jiaxing Huang, Shijian Lu, Dayan Guan, Xiaobing Zhang連結 | https://arxiv.org/abs/2007.02424 備註 | Accepted to ECCV 2020[32] Attention-based Joint Detection of Object and Semantic Part作者 | Keval Morabia, Jatin Arora, Tara Vijaykumar連結 | https://arxiv.org/abs/2007.02419 [33] Learning Color Compatibility in Fashion Outfits作者 | Heming Zhang, Xuewen Yang, Jianchao Tan, Chi-Hao Wu, Jue Wang, C.-C. Jay Kuo連結 | https://arxiv.org/abs/2007.02388 [34] Simplicial Complex based Point Correspondence between Images warped onto Manifolds作者 | Charu Sharma, Manohar Kaul連結 | https://arxiv.org/abs/2007.02381 備註 | Accepted at ECCV 2020[35] MetaConcept: Learn to Abstract via Concept Graph for Weakly-Supervised Few-Shot Learning作者 | Baoquan Zhang, Ka-Cheong Leung, Yunming Ye, Xutao Li連結 | https://arxiv.org/abs/2007.02379 [36] Auto-captions on GIF: A Large-scale Video-sentence Dataset for Vision-language Pre-training作者 | Yingwei Pan, Yehao Li, Jianjie Luo, Jun Xu, Ting Yao, Tao Mei連結 | https://arxiv.org/abs/2007.02375 備註 | The Auto-captions on GIF dataset is available at http://www.auto-video-captions.top/2020/dataset[37] Detail Preserved Point Cloud Completion via Separated Feature Aggregation作者 | Wenxiao Zhang, Qingan Yan, Chunxia Xiao連結 | https://arxiv.org/abs/2007.02374 備註 | To be appeared in ECCV 2020[38] Aligning Partially Overlapping Point Sets: an Inner Approximation Algorithm作者 | Wei Lian, WangMeng Zuo, Lei Zhang連結 | https://arxiv.org/abs/2007.02363 [39] HoughNet: Integrating near and long-range evidence for bottom-up object detection作者 | Nermin Samet, Samet Hicsonmez, Emre Akbas連結 | https://arxiv.org/abs/2007.02355 備註 | to appear in ECCV 2020[40] Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks作者 | Yunfei Liu, Xingjun Ma, James Bailey, Feng Lu連結 | https://arxiv.org/abs/2007.02343 備註 | Accepted by ECCV-2020[41] Medical Imaging with Deep Learning: MIDL 2020 -- Short Paper Track作者 | Tal Arbel, Ismail Ben Ayed, Marleen de Bruijne, Maxime Descoteaux, Herve Lombaert, Chris Pal連結 | https://arxiv.org/abs/2007.02319 備註 | Accepted extended abstracts can also be found at https://openreview.net/group?id=MIDL.io/2020/Conference#abstract-accept-papers[42] Radial Intersection Count Image: a Clutter Resistant 3D Shape Descriptor作者 | Bart Iver van Blokland, Theoharis Theoharis連結 | https://arxiv.org/abs/2007.02306 備註 | to be published in Computers & Graphics[43] Multi view stereo with semantic priors作者 | Elisavet Konstantina Stathopoulou, Fabio Remondino連結 | https://arxiv.org/abs/2007.02295 [44] TilinGNN: Learning to Tile with Self-Supervised Graph Neural Network作者 | Hao Xu, Ka Hei Hui, Chi-Wing Fu, Hao Zhang連結 | https://arxiv.org/abs/2007.02278 項目連結 | https://appsrv.cse.cuhk.edu.hk/~haoxu/projects/TilinGnn/index.html備註 | SIGGRAPH 2020, Technical paper. ACM Trans. Graph., Vol. 39, No. 4, Article 129. [45] Weakly Supervised Domain Adaptation for Built-up Region Segmentation in Aerial and Satellite Imagery作者 | Javed Iqbal, Mohsen Ali連結 | https://arxiv.org/abs/2007.02277 備註 | Accepted at ISPRS Journal of Photogrammetry and Remote Sensing[46] Rethinking Bottleneck Structure for Efficient Mobile Network Design作者 | Zhou Daquan, Qibin Hou, Yunpeng Chen, Jiashi Feng, Shuicheng Yan連結 | https://arxiv.org/abs/2007.02269 備註 | 24 pages, published as a ECCV20 conference paper[47] Image Aesthetics Prediction Using Multiple Patches Preserving the Original Aspect Ratio of Contents作者 | Lijie Wang, Xueting Wang, Toshihiko Yamasaki連結 | https://arxiv.org/abs/2007.02268 [48] Deep Learning based Dimple Detection for Quantitative Fractography作者 | Ashish Sinha, KS Suresh連結 | https://arxiv.org/abs/2007.02267 [49] CIDMP: Completely Interpretable Detection of Malaria Parasite in Red Blood Cells using Lower-dimensional Feature Space作者 | Anik Khan, Kishor Datta Gupta, Deepak Venugopal, Nirman Kumar連結 | https://arxiv.org/abs/2007.02248 備註 | Accepted in The 2020 International Joint Conference on Neural Networks (IJCNN 2020) At Glasgow (UK)[50] A Systematic Evaluation of Object Detection Networks for Scientific Plots作者 | Pritha Ganguly, Nitesh Methani, Mitesh M. Khapra, Pratyush Kumar連結 | https://arxiv.org/abs/2007.02240 [51] Offline versus Online Triplet Mining based on Extreme Distances of Histopathology Patches作者 | Milad Sikaroudi, Benyamin Ghojogh, Amir Safarpoor, Fakhri Karray, Mark Crowley, H.R. Tizhoosh連結 | https://arxiv.org/abs/2007.02200 備註 | The first two authors contributed equally to this work[52] BézierSketch: A generative model for scalable vector sketches作者 | Ayan Das, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song連結 | https://arxiv.org/abs/2007.02190 備註 | To be appeared in ECCV 2020[53] Face Anti-Spoofing with Human Material Perception作者 | Zitong Yu, Xiaobai Li, Xuesong Niu, Jingang Shi, Guoying Zhao連結 | https://arxiv.org/abs/2007.02157 備註 | Accepted by ECCV2020[54] Human Assisted Artificial Intelligence Based Technique to Create Natural Features for OpenStreetMap作者 | Piyush Yadav, Dipto Sarkar Shailesh Deshpande, Edward Curry連結 | https://arxiv.org/abs/2007.02149 備註 | Submitted to FOSS4G Europe 2020 Academic Track (Postponed to 2021)[55] On Class Orderings for Incremental Learning作者 | Marc Masana, Bartłomiej Twardowski, Joost van de Weijer連結 | https://arxiv.org/abs/2007.02145 備註 | Accepted at CL-ICML 2020. First two authors contributed equally[56] SplitFusion: Simultaneous Tracking and Mapping for Non-Rigid Scenes作者 | Yang Li, Tianwei Zhang$, Yoshihiko Nakamura, Tatsuya Harada連結 | https://arxiv.org/abs/2007.02108 備註 | Accepted to IROS'2020[57] Automatic Target Recognition on Synthetic Aperture Radar Imagery: A Survey作者 | O. Kechagias-Stamatis連結 | https://arxiv.org/abs/2007.02106 [58] Local Grid Rendering Networks for 3D Object Detection in Point Clouds作者 | Jianan Li, Jiashi Feng連結 | https://arxiv.org/abs/2007.02099 [59] End-to-end Learning of a Fisher Vector Encoding for Part Features in Fine-grained Recognition作者 | Dimitri Korsch, Paul Bodesheim, Joachim Denzler連結 | https://arxiv.org/abs/2007.02080 [60] Quo Vadis, Skeleton Action Recognition ?作者 | Pranay Gupta, Anirudh Thatipelli, Aditya Aggarwal, Shubh Maheshwari, Neel Trivedi, Sourav Das, Ravi Kiran Sarvadevabhatla連結 | https://arxiv.org/abs/2007.02072 備註 | Reference video at https://www.youtube.com/watch?v=YKjQcV_2gLU[61] Weight-dependent Gates for Network Pruning作者 | Yun Li, Weiqun Wu, Zechun Liu, Chi Zhang, Xiangyu Zhang, Haotian Yao, Baoqun Yin連結 | https://arxiv.org/abs/2007.02066 [62] Efficient and accurate object detection with simultaneous classification and tracking作者 | Xuesong Li, Jose Guivant連結 | https://arxiv.org/abs/2007.02065 [63] Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation作者 | Jianfeng Zhang, Xuecheng Nie, Jiashi Feng連結 | https://arxiv.org/abs/2007.02054 [64] Self-Calibration Supported Robust Projective Structure-from-Motion作者 | Rui Gong, Danda Pani Paudel, Ajad Chhatkuli, Luc Van Gool連結 | https://arxiv.org/abs/2007.02045 [65] Single Image Brightening via Multi-Scale Exposure Fusion with Hybrid Learning作者 | Chaobing Zheng, Zhengguo Li, Yi Yang, Shiqian Wu連結 | https://arxiv.org/abs/2007.02042 [66] Jointly Modeling Motion and Appearance Cues for Robust RGB-T Tracking作者 | Pengyu Zhang, Jie Zhao, Dong Wang, Huchuan Lu, Xiaoyun Yang連結 | https://arxiv.org/abs/2007.02041 [67] Modality Shifting Attention Network for Multi-modal Video Question Answering作者 | Junyeong Kim, Minuk Ma, Trung Pham, Kyungsu Kim, Chang D. Yoo連結 | https://arxiv.org/abs/2007.02036 備註 | CVPR2020 accepted; poster[68] Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains作者 | Quande Liu, Qi Dou, Pheng-Ann Heng連結 | https://arxiv.org/abs/2007.02035 項目連結 | https://github.com/liuquande/SAML備註 | Early accepted by MICCAI 2020; [69] DRDr: Automatic Masking of Exudates and Microaneurysms Caused By Diabetic Retinopathy Using Mask R-CNN and Transfer Learning作者 | Farzan Shenavarmasouleh, Hamid R. Arabnia連結 | https://arxiv.org/abs/2007.02026 備註 | The 6th International Conference on Health Informatics & Medical Systems (HIMS'20: July 27-30, 2020, USA)[70] Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation作者 | Bin Yan, Dong Wang, Huchuan Lu, Xiaoyun Yang連結 | https://arxiv.org/abs/2007.02024 [71] FracBits: Mixed Precision Quantization via Fractional Bit-Widths作者 | Linjie Yang, Qing Jin連結 | https://arxiv.org/abs/2007.02017 [72] DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths作者 | Yanwei Fu, Chen Liu, Donghao Li, Xinwei Sun, Jinshan Zeng, Yuan Yao連結 | https://arxiv.org/abs/2007.02010 項目連結 | https://github.com/corwinliu9669/dS2LBI[73] A Survey on Sensor Technologies for Unmanned Ground Vehicles作者 | Qi Liu, Shihua Yuan, Zirui Li連結 | https://arxiv.org/abs/2007.01992 [74] Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation作者 | Liwei Wang, Jing Huang, Yin Li, Kun Xu, Zhengyuan Yang, Dong Yu連結 | https://arxiv.org/abs/2007.01951 [75] Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation作者 | Guolei Sun, Wenguan Wang, Jifeng Dai, Luc Van Gool連結 | https://arxiv.org/abs/2007.01947 項目連結 | https://github.com/GuoleiSun/MCIS_wsss備註 | Full version of ECCV2020 Oral, CVPR2020 LID workshop Best Paper and LID challenge Track1 winner;[76] Multigrid for Bundle Adjustment作者 | Tristan Konolige, Jed Brown連結 | https://arxiv.org/abs/2007.01941 [77] Feedback Neural Network based Super-resolution of DEM for generating high fidelity features作者 | Ashish Kubade, Avinash Sharma, K S Rajan連結 | https://arxiv.org/abs/2007.01940 備註 | Accepted for publication in IEEE IGARSS 2020 conference[78] Graph2Kernel Grid-LSTM: A Multi-Cued Model for Pedestrian Trajectory Prediction by Learning Adaptive Neighborhoods作者 | Sirin Haddad, Siew Kei Lam連結 | https://arxiv.org/abs/2007.01915 [79] A Few-Shot Sequential Approach for Object Counting作者 | Negin Sokhandan, Pegah Kamousi, Alejandro Posada, Eniola Alese, Negar Rostamzadeh連結 | https://arxiv.org/abs/2007.01899 [80] Egocentric Action Recognition by Video Attention and Temporal Context作者 | Juan-Manuel Perez-Rua, Antoine Toisoul, Brais Martinez, Victor Escorcia, Li Zhang, Xiatian Zhu, Tao Xiang連結 | https://arxiv.org/abs/2007.01883 備註 | EPIC-Kitchens challenges@CVPR 2020[81] Accurate Bounding-box Regression with Distance-IoU Loss for Visual Tracking作者 | Di Yuan, Xiaojun Chang, Zhenyu He連結 | https://arxiv.org/abs/2007.01864 備註 | Submitted to ACM Multimedia 2020. [82] Deep Learning Models for Visual Inspection on Automotive Assembling Line作者 | Muriel Mazzetto, Marcelo Teixeira, Érick Oliveira Rodrigues, Dalcimar Casanova連結 | https://arxiv.org/abs/2007.01857 [83] Coronary Heart Disease Diagnosis Based on Improved Ensemble Learning作者 | Kuntoro Adi Nugroho, Noor Akhmad Setiawan, Teguh Bharata Adji連結 | https://arxiv.org/abs/2007.02895 [84] Augment Yourself: Mixed Reality Self-Augmentation Using Optical See-through Head-mounted Displays and Physical Mirrors作者 | Mathias Unberath, Kevin Yu, Roghayeh Barmaki, Alex Johnson, Nassir Navab連結 | https://arxiv.org/abs/2007.02884 備註 | This manuscript was initially submitted to IEEE VR TVCG 2018 on November 22, 2017[85] Adversarial Uni- and Multi-modal Stream Networks for Multimodal Image Registration作者 | Zhe Xu, Jie Luo, Jiangpeng Yan, Ritvik Pulya, Xiu Li, William Wells III, Jayender Jagadeesan連結 | https://arxiv.org/abs/2007.02790 備註 | accepted by MICCAI 2020[86] Black-box Adversarial Example Generation with Normalizing Flows作者 | Hadi M. Dolatabadi, Sarah Erfani, Christopher Leckie連結 | https://arxiv.org/abs/2007.02734 備註 | Accepted to the 2nd workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models (ICML 2020), Virtual Conference[87] Perceptually Optimizing Deep Image Compression作者 | Li-Heng Chen, Christos G. Bampis, Zhi Li, Andrey Norkin, Alan C. Bovik連結 | https://arxiv.org/abs/2007.02711 [88] An Elastic Interaction-Based Loss Function for Medical Image Segmentation作者 | Yuan Lan, Yang Xiang, Luchan Zhang連結 | https://arxiv.org/abs/2007.02663 [89] Dynamic memory to alleviate catastrophic forgetting in continuous learning settings作者 | Johannes Hofmanninger, Matthias Perkonigg, James A. Brink, Oleg Pianykh, Christian Herold, Georg Langs連結 | https://arxiv.org/abs/2007.02639 備註 | Accepted at MICCAI 2020[90] Understanding and Improving Fast Adversarial Training作者 | Maksym Andriushchenko, Nicolas Flammarion連結 | https://arxiv.org/abs/2007.02617 [91] A Convolutional Approach to Vertebrae Detection and Labelling in Whole Spine MRI作者 | Rhydian Windsor, Amir Jamaludin, Timor Kadir, Rhydian Windsor連結 | https://arxiv.org/abs/2007.02606 備註 | Accepted full paper to Medical Image Computing and Computer Assisted Intervention 2020. [92] On the Connection between Dynamical Optimal Transport and Functional Lifting作者 | Thomas Vogt, Roland Haase, Danielle Bednarski, Jan Lellmann連結 | https://arxiv.org/abs/2007.02587 [93] Probabilistic Multi-modal Trajectory Prediction with Lane Attention for Autonomous Vehicles作者 | Chenxu Luo, Lin Sun, Dariush Dabiri, Alan Yuille連結 | https://arxiv.org/abs/2007.02574 備註 | IROS 2020. 3rd place solution for the Argoverse motion forecasting challenge at NeurIPS 2019. A variation of the method also won the 1st place in the Nuscenes prediction challenge 2020[94] Traffic Agent Trajectory Prediction Using Social Convolution and Attention Mechanism作者 | Tao Yang, Zhixiong Nan, He Zhang, Shitao Chen, Nanning Zheng連結 | https://arxiv.org/abs/2007.02515 [95] Deep Learning for Anomaly Detection: A Review作者 | Guansong Pang, Chunhua Shen, Longbing Cao, Anton van den Hengel連結 | https://arxiv.org/abs/2007.02500 備註 | Survey paper, 36 pages, 180 references, 2 figures, 3 tables[96] Automatic semantic segmentation for prediction of tuberculosis using lens-free microscopy images作者 | Dennis Núñez-Fernández, Lamberto Ballan, Gabriel Jiménez-Avalos, Jorge Coronel, Mirko Zimic連結 | https://arxiv.org/abs/2007.02482 備註 | ML for Global Health Workshop at ICML 2020[97] Can Un-trained Neural Networks Compete with Trained Neural Networks at Image Reconstruction?作者 | Mohammad Zalbagi Darestani, Reinhard Heckel連結 | https://arxiv.org/abs/2007.02471 [98] Using Capsule Neural Network to predict Tuberculosis in lens-free microscopic images作者 | Dennis Núñez-Fernández, Lamberto Ballan, Gabriel Jiménez-Avalos, Jorge Coronel, Mirko Zimic連結 | https://arxiv.org/abs/2007.02457 備註 | HSYS Workshop at ICML 2020[99] Pseudo-Rehearsal for Continual Learning with Normalizing Flows作者 | Jary Pomponi, Simone Scardapane, Aurelio Uncini連結 | https://arxiv.org/abs/2007.02443 [100] Meta-Semi: A Meta-learning Approach for Semi-supervised Learning作者 | Yulin Wang, Jiayi Guo, Shiji Song, Gao Huang連結 | https://arxiv.org/abs/2007.02394 [101] Deep Convolutional Neural Network for Identifying Seam-Carving Forgery作者 | Seung-Hun Nam, Wonhyuk Ahn, In-Jae Yu, Myung-Joon Kwon, Minseok Son, Heung-Kyu Lee連結 | https://arxiv.org/abs/2007.02393 [102] GanglionNet: Objectively Assess the Density and Distribution of Ganglion Cells With NABLA-N Network作者 | Md Zahangir Alom (Member, IEEE), Raj P. Kapur, TJ Browen, Vijayan K. Asari (Senior Member, IEEE)連結 | https://arxiv.org/abs/2007.02367 [103] Self-supervised Depth Estimation to Regularise Semantic Segmentation in Knee Arthroscopy作者 | Fengbei Liu, Yaqub Jonmohamadi, Gabriel Maicas, Ajay K. Pandey, Gustavo Carneiro連結 | https://arxiv.org/abs/2007.02361 [104] Automatically Generating Codes from Graphical Screenshots Based on Deep Autocoder作者 | Xiaoling Huang, Feng Liao連結 | https://arxiv.org/abs/2007.02272 [105] Spatial-Angular Attention Network for Light Field Reconstruction作者 | Gaochang Wu, Yebin Liu, Lu Fang, Tianyou Chai連結 | https://arxiv.org/abs/2007.02252 [106] Stereo Visual Inertial Pose Estimation Based on Feedforward-Feedback Loops作者 | Shengyang Chen, Chih-Yung Wen, Yajing Zou, Wu Chen連結 | https://arxiv.org/abs/2007.02250 [107] Blind Inverse Gamma Correction with Maximized Differential Entropy作者 | Yong Lee, Shaohua Zhang, Miao Li, Xiaoyu He連結 | https://arxiv.org/abs/2007.02246 [108] An Integer Approximation Method for Discrete Sinusoidal Transforms連結 | https://arxiv.org/abs/2007.02232 [109] On Connections between Regularizations for Improving DNN Robustness作者 | Yiwen Guo, Long Chen, Yurong Chen, Changshui Zhang連結 | https://arxiv.org/abs/2007.02209 [110] A Weakly Supervised Consistency-based Learning Method for COVID-19 Segmentation in CT Images作者 | Issam Laradji, Pau Rodriguez, Oscar Manas, Keegan Lensink, Marco Law, Lironne Kurzman, William Parker, David Vazquez, Derek Nowrouzezahrai連結 | https://arxiv.org/abs/2007.02180 [111] Neuro-Symbolic Generative Art: A Preliminary Study作者 | Gunjan Aggarwal, Devi Parikh連結 | https://arxiv.org/abs/2007.02171 備註 | Accepted as a short paper at ICCC 2020[112] Multi-Site Infant Brain Segmentation Algorithms: The iSeg-2019 Challenge作者 | Yue Sun, Kun Gao, Zhengwang Wu, Zhihao Lei, et al.連結 | https://arxiv.org/abs/2007.02096 [113] Multi-Sensor Next-Best-View Planning as Matroid-Constrained Submodular Maximization作者 | Mikko Lauri, Joni Pajarinen, Jan Peters, Simone Frintrop連結 | https://arxiv.org/abs/2007.02084 備註 | Accepted for publication in IEEE Robotics and Automation Letters[114] Registration of Histopathogy Images Using Structural Information From Fine Grained Feature Maps作者 | Dwarikanath Mahapatra連結 | https://arxiv.org/abs/2007.02078 [115] Speckle2Void: Deep Self-Supervised SAR Despeckling with Blind-Spot Convolutional Neural Networks作者 | Andrea Bordone Molini, Diego Valsesia, Giulia Fracastoro, Enrico Magli連結 | https://arxiv.org/abs/2007.02075 [116] Deep Bilateral Retinex for Low-Light Image Enhancement作者 | Jinxiu Liang, Yong Xu, Yuhui Quan, Jingwen Wang, Haibin Ling, Hui Ji連結 | https://arxiv.org/abs/2007.02018 [117] Interpretation of Disease Evidence for Medical Images Using Adversarial Deformation Fields作者 | Ricardo Bigolin Lanfredi, Joyce D. Schroeder, Clement Vachet, Tolga Tasdizen連結 | https://arxiv.org/abs/2007.01975 備註 | Accepted for MICCAI 2020[118] Structure-Aware Human-Action Generation作者 | Ping Yu, Yang Zhao, Chunyuan Li, Changyou Chen連結 | https://arxiv.org/abs/2007.01971 備註 | accepted by ECCV 2020[119] Knowledge Distillation Beyond Model Compression作者 | Fahad Sarfraz, Elahe Arani, Bahram Zonooz連結 | https://arxiv.org/abs/2007.01922 備註 | Accepted at ICPR 2020[120] TLIO: Tight Learned Inertial Odometry作者 | Wenxin Liu, David Caruso, Eddy Ilg, Jing Dong, Anastasios I. Mourikis, Kostas Daniilidis, Vijay Kumar, Jakob Engel連結 | https://arxiv.org/abs/2007.01867 [121] Selecting Regions of Interest in Large Multi-Scale Images for Cancer Pathology作者 | Rui Aguiar, Jon Braatz連結 | https://arxiv.org/abs/2007.01866