計算機視覺（1月23日更新版）
[1] RDAnet: A Deep Learning Based Approach for Synthetic Aperture Radar Image Formation作者 | Andrew Rittenbach (1), John Paul Walters (1) ((1) University of Southern California Information Sciences Institute, Arlington VA)連結 | https://arxiv.org/pdf/2001.08202 [2] Automatic phantom test pattern classification through transfer learning with deep neural networks作者 | Rafael B. Fricks, Justin Solomon, Ehsan Samei連結 | https://arxiv.org/pdf/2001.08189 [3] Discovering Salient Anatomical Landmarks by Predicting Human Gaze作者 | Richard Droste, Pierre Chatelain, Lior Drukker, Harshita Sharma, Aris T. Papageorghiou, J. Alison Noble連結 | https://arxiv.org/pdf/2001.08188 備註 | Accepted at IEEE International Symposium on Biomedical Imaging 2020 (ISBI 2020)[4] Causality based Feature Fusion for Brain NeuroDevelopmental Analysis作者 | Peyman Hosseinzadeh Kassani, Li Xiao, Gemeng Zhang, Julia M. Stephen, Tony W. Wilson, Vince D. Calhoun, Yu Ping Wang連結 | https://arxiv.org/pdf/2001.08173 [5] Are Accelerometers for Activity Recognition a Dead-end?作者 | Catherine Tong, Shyam A. Tailor, Nicholas D. Lane連結 | https://arxiv.org/pdf/2001.08111 [6] Learning to Correct 3D Reconstructions from Multiple Views作者 | Ştefan Săftescu, Paul Newman連結 | https://arxiv.org/pdf/2001.08098 [7] UniPose: Unified Human Pose Estimation in Single Images and Videos作者 | Bruno Artacho, Andreas Savakis連結 | https://arxiv.org/pdf/2001.08095 [8] Depthwise Non-local Module for Fast Salient Object Detection Using a Single Thread作者 | Haofeng Li, Guanbin Li, Binbin Yang, Guanqi Chen, Liang Lin, Yizhou Yu連結 | https://arxiv.org/pdf/2001.08057 備註 | Accepted as a regular paper in the IEEE Transactions on Cybernetics[9] Attention! A Lightweight 2D Hand Pose Estimation Approach作者 | Nicholas Santavas, Ioannis Kansizoglou, Loukas Bampis, Evangelos Karakasis, Antonios Gasteratos連結 | https://arxiv.org/pdf/2001.08047 備註 | submitted to IEEE Signal Processing Letters[10] ResDepth: Learned Residual Stereo Reconstruction作者 | Corinne Stucker, Konrad Schindler連結 | https://arxiv.org/pdf/2001.08026 [11] ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data作者 | Di Qi, Lin Su, Jia Song, Edward Cui, Taroon Bharti, Arun Sachet連結 | https://arxiv.org/pdf/2001.07966 [12] A Fixation-based 360° Benchmark Dataset for Salient Object Detection作者 | Yi Zhang, Lu Zhang, Wassim Hamidouche, Olivier Deforges連結 | https://arxiv.org/pdf/2001.07960 [13] Optimized Generic Feature Learning for Few-shot Classification across Domains作者 | Tonmoy Saikia, Thomas Brox, Cordelia Schmid連結 | https://arxiv.org/pdf/2001.07926 [14] Dynamic multi-object Gaussian process models: A framework for data-driven functional modelling of human joints作者 | Jean-Rassaire Fouefack, Bhushan Borotikar, Tania S. Douglas, Valérie Burdin, Tinashe E.M. Mutsvangwa連結 | https://arxiv.org/pdf/2001.07904 [15] Partially-Shared Variational Auto-encoders for Unsupervised Domain Adaptation with Target Shift作者 | Ryuhei Takahashi, Masaaki Iiyama, Atsushi Hashimoto, Motoharu Sonogashira連結 | https://arxiv.org/pdf/2001.07895 [16] Curvature Regularized Surface Reconstruction from Point Cloud作者 | Yuchen He, Sung Ha Kang, Hao Liu連結 | https://arxiv.org/pdf/2001.07884 [17] M^2 Deep-ID: A Novel Model for Multi-View Face Identification Using Convolutional Deep Neural Networks作者 | Sara Shahsavarani, Morteza Analoui, Reza Shoja Ghiass連結 | https://arxiv.org/pdf/2001.07871 [18] LRF-Net: Learning Local Reference Frames for 3D Local Shape Description and Matching作者 | Angfan Zhu, Jiaqi Yang, Chen Zhao, Ke Xian, Zhiguo Cao, Xin Li連結 | https://arxiv.org/pdf/2001.07832 [19] Depth-Based Selective Blurring in Stereo Images Using Accelerated Framework作者 | Subhayan Mukherjee, Ram Mohana Reddy Guddeti連結 | https://arxiv.org/pdf/2001.07809 [20] Scientific Image Tampering Detection Based On Noise Inconsistencies: A Method And Datasets作者 | Ziyue Xiang, Daniel Acuna連結 | https://arxiv.org/pdf/2001.07799 [21] Weakly Supervised Temporal Action Localization Using Deep Metric Learning作者 | Ashraful Islam, Richard J. Radke連結 | https://arxiv.org/pdf/2001.07793 備註 | accepted to WACV 2020[22] Deep Depth Prior for Multi-View Stereo作者 | Pallabi Ghosh, Vibhav Vineet, Larry S. Davis, Abhinav Shrivastava, Sudipta Sinha, Neel Joshi連結 | https://arxiv.org/pdf/2001.07791 [23] Lesion Harvester: Iteratively Mining Unlabeled Lesions and Hard-Negative Examples at Scale作者 | Jinzheng Cai, Adam P. Harrison, Youjing Zheng, Ke Yan, Yuankai Huo, Jing Xiao, Lin Yang, Le Lu連結 | https://arxiv.org/pdf/2001.07776 備註 | This work has been submitted to the IEEE for possible publication[24] Adaptive Loss Function for Super Resolution Neural Networks Using Convex Optimization Techniques作者 | Seyed Mehdi Ayyoubzadeh, Xiaolin Wu連結 | https://arxiv.org/pdf/2001.07766 [25] Block-wise Scrambled Image Recognition Using Adaptation Network作者 | Koki Madono, Masayuki Tanaka, Masaki Onishi, Tetsuji Ogawa連結 | https://arxiv.org/pdf/2001.07761 備註 | Artificial Intelligence of Things(AAAI-2020 WS)[26] EMOPAIN Challenge 2020: Multimodal Pain Evaluation from Facial and Bodily Expressions作者 | Nadia Berthouze, Michel Valstar, Amanda Williams, Joy Egede, Temitayo Olugbade, Chongyang Wang, Hongyin Meng, Min Aung, Nicholas Lane, Siyang Song連結 | https://arxiv.org/pdf/2001.07739 [27] An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices作者 | Xiaolong Ma, Wei Niu, Tianyun Zhang, Sijia Liu, Fu-Ming Guo, Sheng Lin, Hongjia Li, Xiang Chen, Jian Tang, Kaisheng Ma, Bin Ren, Yanzhi Wang連結 | https://arxiv.org/pdf/2001.07710 [28] Pruning CNN's with linear filter ensembles作者 | Csanád Sándor, Szabolcs Pável, Lehel Csató連結 | https://arxiv.org/pdf/2001.08142 備註 | accepted to ECAI2020[29] Optimizing Generative Adversarial Networks for Image Super Resolution via Latent Space Regularization作者 | Sheng Zhong, Shifu Zhou (Agora.io)連結 | https://arxiv.org/pdf/2001.08126 [30] DeepFL-IQA: Weak Supervision for Deep IQA Feature Learning作者 | Hanhe Lin, Vlad Hosu, Dietmar Saupe連結 | https://arxiv.org/pdf/2001.08113 [31] ManyModalQA: Modality Disambiguation and QA over Diverse Inputs作者 | Darryl Hannan, Akshay Jain, Mohit Bansal連結 | https://arxiv.org/pdf/2001.08034 [32] Safety Concerns and Mitigation Approaches Regarding the Use of Deep Learning in Safety-Critical Perception Tasks作者 | Oliver Willers, Sebastian Sudholt, Shervin Raafatnia, Stephanie Abrecht連結 | https://arxiv.org/pdf/2001.08001 [33] Anomaly detection in chest radiographs with a weakly supervised flow-based deep learning method作者 | H. Shibata (1), S. Hanaoka (2), Y. Nomura (1), T. Nakao (3), I. Sato (2 and 4 and 5), N. Hayashi (1), O. Abe (2 and 3) ((1) Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, (2) Department of Radiology, The University of Tokyo Hospital, (3) Division of Radiology and Biomedical Engineering, Graduate School of Medicine, The University of Tokyo, (4) Department of Complexity Science and Engineering, Graduate School of Frontier Sciences, The University of Tokyo, (5) Center for Advanced Intelligence Project, RIKEN)連結 | https://arxiv.org/pdf/2001.07847 [34] GhostImage: Perception Domain Attacks against Vision-based Object Classification Systems作者 | Yanmao Man, Ming Li, Ryan Gerdes連結 | https://arxiv.org/pdf/2001.07792 [35] TEASER: Fast and Certifiable Point Cloud Registration作者 | Heng Yang, Jingnan Shi, Luca Carlone連結 | https://arxiv.org/pdf/2001.07715連結 | https://arxiv.org/pdf/