計算機視覺（3月17日更新版）
[1] Scan2Plan: Efficient Floorplan Generation from 3D Scans of Indoor Scenes作者 | Ameya Phalak, Vijay Badrinarayanan, Andrew Rabinovich連結 | https://arxiv.org/pdf/2003.07356 [2] Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks作者 | Karan Sikka, Andrew Silberfarb, John Byrnes, Indranil Sur, Ed Chow, Ajay Divakaran, Richard Rohwer連結 | https://arxiv.org/pdf/2003.07344 [3] Complexity of Shapes Embedded in Zn with a Bias Towards Squares作者 | M. Ferhat Arslan (1), Sibel Tari (1) ((1) Middle East Technical University)連結 | https://arxiv.org/pdf/2003.07341 備註 | submitted to IEEE Transactions on Image Processing[4] Learning Shape Representations for Clothing Variations in Person Re-Identification作者 | Yu-Jhe Li, Zhengyi Luo, Xinshuo Weng, Kris M. Kitani連結 | https://arxiv.org/pdf/2003.07340 [5] G-LBM:Generative Low-dimensional Background Model Estimation from Video Sequences作者 | Behnaz Rezaei, Amirreza Farnoosh, Sarah Ostadabbas連結 | https://arxiv.org/pdf/2003.07335 [6] RSVQA: Visual Question Answering for Remote Sensing Data作者 | Sylvain Lobry, Diego Marcos, Jesse Murray, Devis Tuia連結 | https://arxiv.org/pdf/2003.07333 備註 | Submitted to IEEE Transactions on Geoscience and Remote Sensing[7] Resolution Adaptive Networks for Efficient Inference作者 | Le Yang, Yizeng Han, Xi Chen, Shiji Song, Jifeng Dai, Gao Huang連結 | https://arxiv.org/pdf/2003.07326 [8] Domain Adaptive Ensemble Learning作者 | Kaiyang Zhou, Yongxin Yang, Yu Qiao, Tao Xiang連結 | https://arxiv.org/pdf/2003.07325 [9] clDice -- a Topology-Preserving Loss Function for Tubular Structure Segmentation作者 | Suprosanna Shit, Johannes C. Paetzold, Anjany Sekuboyina, Andrey Zhylka, Ivan Ezhov, Alexander Unger, Josien P. W. Pluim, Giles Tetteh, Bjoern H. Menze連結 | https://arxiv.org/pdf/2003.07311 [10] Context-Transformer: Tackling Object Confusion for Few-Shot Detection作者 | Ze Yang (1), Yali Wang (1), Xianyu Chen (1), Jianzhuang Liu (2), Yu Qiao (1 and 3) ((1) ShenZhen Key Lab of Computer Vision and Pattern Recognition, SIAT-SenseTime Joint Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, (2) Huawei Noah's Ark Lab, (3) SIAT Branch, Shenzhen Institute of Artificial Intelligence and Robotics for Society)連結 | https://arxiv.org/pdf/2003.07304 備註 | Accepted by AAAI-2020[11] MVLoc: Multimodal Variational Geometry-Aware Learning for Visual Localization作者 | Rui Zhou, Changhao Chen, Bing Wang, Andrew Markham, Niki Trigoni連結 | https://arxiv.org/pdf/2003.07289 [12] Towards Ground Truth Evaluation of Visual Explanations作者 | Ahmed Osman, Leila Arras, Wojciech Samek連結 | https://arxiv.org/pdf/2003.07258 [13] Neural Pose Transfer by Spatially Adaptive Instance Normalization作者 | Jiashun Wang, Chao Wen, Yanwei Fu, Haitao Lin, Tianyun Zou, Xiangyang Xue, Yinda Zhang連結 | https://arxiv.org/pdf/2003.07254 備註 | Accepted by CVPR2020[14] A Rotation-Invariant Framework for Deep Point Cloud Analysis作者 | Xianzhi Li, Ruihui Li, Guangyong Chen, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng連結 | https://arxiv.org/pdf/2003.07238 [15] Joint COCO and Mapillary Workshop at ICCV 2019 Keypoint Detection Challenge Track Technical Report: Distribution-Aware Coordinate Representation for Human Pose Estimation作者 | Hanbin Dai, Liangbo Zhou, Feng Zhang, Zhengyu Zhang, Hong Hu, Xiatian Zhu, Mao Ye連結 | https://arxiv.org/pdf/2003.07232 [16] FragNet: Writer Identification using Deep Fragment Networks作者 | Sheng He, Lambert Schomaker連結 | https://arxiv.org/pdf/2003.07212 備註 | Accepted by IEEE Trans. on Information Forensic and Security[17] Refinements in Motion and Appearance for Online Multi-Object Tracking作者 | Piao Huang, Shoudong Han, Jun Zhao, Donghaisheng Liu, Hongwei Wang, En Yu, Alex ChiChung Kot連結 | https://arxiv.org/pdf/2003.07177 備註 | submitted to ECCV2020'[18] GraphTCN: Spatio-Temporal Interaction Modeling for Human Trajectory Prediction作者 | Chengxin Wang, Shaofeng Cai, Gary Tan連結 | https://arxiv.org/pdf/2003.07167 [19] Discriminative Feature and Dictionary Learning with Part-aware Model for Vehicle Re-identification作者 | Huibing Wang, Jinjia Peng, Guangqi Jiang, Fengqiang Xu, Xianping Fu連結 | https://arxiv.org/pdf/2003.07139 [20] Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks作者 | Majed El Helou, Ruofan Zhou, Sabine Süsstrunk連結 | https://arxiv.org/pdf/2003.07119 [21] Minimal Solvers for Indoor UAV Positioning作者 | Marcus Valtonen Örnhag, Patrik Persson, Mårten Wadenbäck, Kalle Åström, Anders Heyden連結 | https://arxiv.org/pdf/2003.07111 [22] Synthesizing human-like sketches from natural images using a conditional convolutional decoder作者 | Moritz Kampelmühler, Axel Pinz連結 | https://arxiv.org/pdf/2003.07101 備註 | In IEEE Winter Conference on Applications of Computer Vision (WACV) 2020[23] PS-RCNN: Detecting Secondary Human Instances in a Crowd via Primary Object Suppression作者 | Zheng Ge, Zequn Jie, Xin Huang, Rong Xu, Osamu Yoshie連結 | https://arxiv.org/pdf/2003.07080 備註 | accepted by ICME2020[24] LT-Net: Label Transfer by Learning Reversible Voxel-wise Correspondence for One-shot Medical Image Segmentation作者 | Shuxin Wang, Shilei Cao, Dong Wei, Renzhen Wang, Kai Ma. Liansheng Wang, Deyu Meng, Yefeng Zheng連結 | https://arxiv.org/pdf/2003.07072 備註 | Accepted to Proc. IEEE Conf. Computer Vision and Pattern Recognition 2020[25] Adapting Object Detectors with Conditional Domain Normalization作者 | Peng Su, Kun Wang, Xingyu Zeng, Shixiang Tang, Dapeng Chen, Di Qiu, Xiaogang Wang連結 | https://arxiv.org/pdf/2003.07071 [26] Self-Supervised Discovering of Causal Features: Towards Interpretable Reinforcement Learning作者 | Wenjie Shi, Zhuoyuan Wang, Shiji Song, Gao Huang連結 | https://arxiv.org/pdf/2003.07069 [27] On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location作者 | Osman Semih Kayhan, Jan C. van Gemert連結 | https://arxiv.org/pdf/2003.07064 [28] Weakly-Supervised Multi-Level Attentional Reconstruction Network for Grounding Textual Queries in Videos作者 | Yijun Song, Jingwen Wang, Lin Ma, Zhou Yu, Jun Yu連結 | https://arxiv.org/pdf/2003.07048 [29] Gated Texture CNN for Efficient and Configurable Image Denoising作者 | Kaito Imai, Takamichi Miyata連結 | https://arxiv.org/pdf/2003.07042 [30] Extended Feature Pyramid Network for Small Object Detection作者 | Chunfang Deng, Mengmeng Wang, Liang Liu, Yong Liu連結 | https://arxiv.org/pdf/2003.07021 [31] Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution作者 | Yong Guo, Jian Chen, Jingdong Wang, Qi Chen, Jiezhang Cao, Zeshuai Deng, Yanwu Xu, Mingkui Tan連結 | https://arxiv.org/pdf/2003.07018 備註 | This paper is accepted by CVPR 2020[32] AVR: Attention based Salient Visual Relationship Detection作者 | Jianming Lv, Qinzhe Xiao, Jiajie Zhong連結 | https://arxiv.org/pdf/2003.07012 [33] Any-Shot Object Detection作者 | Shafin Rahman, Salman Khan, Nick Barnes, Fahad Shahbaz Khan連結 | https://arxiv.org/pdf/2003.07003 [34] ReLaText: Exploiting Visual Relationships for Arbitrary-Shaped Scene Text Detection with Graph Convolutional Networks作者 | Chixiang Ma, Lei Sun, Zhuoyao Zhong, Qiang Huo連結 | https://arxiv.org/pdf/2003.06999 [35] Multi-Drone based Single Object Tracking with Agent Sharing Network作者 | Pengfei Zhu, Jiayu Zheng, Dawei Du, Longyin Wen, Yiming Sun, Qinghua Hu連結 | https://arxiv.org/pdf/2003.06994 [36] House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation作者 | Nelson Nauata, Kai-Hung Chang, Chin-Yi Cheng, Greg Mori, Yasutaka Furukawa連結 | https://arxiv.org/pdf/2003.06988 [37] A CNN-Based Blind Denoising Method for Endoscopic Images作者 | Shaofeng Zou, Mingzhu Long, Xuyang Wang, Xiang Xie, Guolin Li, Zhihua Wang連結 | https://arxiv.org/pdf/2003.06986 備註 | accepted in BioCAS2019 conference[38] TACO: Trash Annotations in Context for Litter Detection作者 | Pedro F Proença, Pedro Simões連結 | https://arxiv.org/pdf/2003.06975 [39] Vec2Face: Unveil Human Faces from their Blackbox Features in Face Recognition作者 | Chi Nhan Duong, Thanh-Dat Truong, Kha Gia Quach, Hung Bui, Kaushik Roy, Khoa Luu連結 | https://arxiv.org/pdf/2003.06958 [40] Frustratingly Simple Few-Shot Object Detection作者 | Xin Wang, Thomas E. Huang, Trevor Darrell, Joseph E. Gonzalez, Fisher Yu連結 | https://arxiv.org/pdf/2003.06957 [41] Camera Trace Erasing作者 | Chang Chen, Zhiwei Xiong, Xiaoming Liu, Feng Wu連結 | https://arxiv.org/pdf/2003.06951 備註 | Accepted by CVPR 2020[42] Scene Completenesss-Aware Lidar Depth Completion for Driving Scenario作者 | Cho-Ying Wu, Ulrich Neumann連結 | https://arxiv.org/pdf/2003.06945 備註 | Under Review of IROS 2020[43] Hyperspectral-Multispectral Image Fusion with Weighted LASSO作者 | Nguyen Tran, Rupali Mankar, David Mayerich, Zhu Han連結 | https://arxiv.org/pdf/2003.06944 [44] Self-Constructing Graph Convolutional Networks for Semantic Labeling作者 | Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg連結 | https://arxiv.org/pdf/2003.06932 [45] Evaluation of Rounding Functions in Nearest-Neighbor Interpolation連結 | https://arxiv.org/pdf/2003.06885 [46] Night-time Semantic Segmentation with a Large Real Dataset作者 | Xin Tan, Yiheng Zhang, Ying Cao, Lizhuang Ma, Rynson W.H. Lau連結 | https://arxiv.org/pdf/2003.06883 [47] Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes作者 | Liang Liao, Jing Xiao, Zheng Wang, Chia-wen Lin, Shin'ichi Satoh連結 | https://arxiv.org/pdf/2003.06877 [48] Multistage Curvilinear Coordinate Transform Based Document Image Dewarping using a Novel Quality Estimator作者 | Tanmoy Dasgupta, Nibaran Das, Mita Nasipuri連結 | https://arxiv.org/pdf/2003.06872 [49] Deep Affinity Net: Instance Segmentation via Affinity作者 | Xingqian Xu, Mang Tik Chiu, Thomas S. Huang, Honghui Shi連結 | https://arxiv.org/pdf/2003.06849 [50] SF-Net: Single-Frame Supervision for Temporal Action Localization作者 | Fan Ma, Linchao Zhu, Yi Yang, Shengxin Zha, Gourab Kundu, Matt Feiszli, Zheng Shou連結 | https://arxiv.org/pdf/2003.06845 [51] 3D-CariGAN: An End-to-End Solution to 3D Caricature Generation from Face Photos作者 | Zipeng Ye, Ran Yi, Minjing Yu, Juyong Zhang, Yu-Kun Lai, Yong-jin Liu連結 | https://arxiv.org/pdf/2003.06841 [52] Energy-based Periodicity Mining with Deep Features for Action Repetition Counting in Unconstrained Videos作者 | Jianqin Yin, Yanchun Wu, Huaping Liu, Yonghao Dang, Zhiyi Liu, Jun Liu連結 | https://arxiv.org/pdf/2003.06838 [53] FGSD: A Dataset for Fine-Grained Ship Detection in High Resolution Satellite Images作者 | Kaiyan Chen, Ming Wu, Jiaming Liu, Chuang Zhang連結 | https://arxiv.org/pdf/2003.06832 [54] VCNet: A Robust Approach to Blind Image Inpainting作者 | Yi Wang, Ying-Cong Chen, Xin Tao, Jiaya Jia連結 | https://arxiv.org/pdf/2003.06816 [55] OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features作者 | Anton Osokin, Denis Sumin, Vasily Lomakin連結 | https://arxiv.org/pdf/2003.06800 [56] StarNet: towards weakly supervised few-shot detection and explainable few-shot classification作者 | Leonid Karlinsky, Joseph Shtok, Amit Alfassy, Moshe Lichtenstein, Sivan Harary, Eli Schwartz, Sivan Doveh, Prasanna Sattigeri, Rogerio Feris, Alexander Bronstein, Raja Giryes連結 | https://arxiv.org/pdf/2003.06798 [57] Performance Evaluation of Advanced Deep Learning Architectures for Offline Handwritten Character Recognition作者 | Moazam Soomro, Muhammad Ali Farooq, Rana Hammad Raza連結 | https://arxiv.org/pdf/2003.06794 備註 | FIT 2017 Paper Published in IEEE FIT 2017[58] Learning Enriched Features for Real Image Restoration and Enhancement作者 | Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, Ling Shao連結 | https://arxiv.org/pdf/2003.06792 [59] GMM-UNIT: Unsupervised Multi-Domain and Multi-Modal Image-to-Image Translation via Attribute Gaussian Mixture Modeling作者 | Yahui Liu, Marco De Nadai, Jian Yao, Nicu Sebe, Bruno Lepri, Xavier Alameda-Pineda連結 | https://arxiv.org/pdf/2003.06788 [60] Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection作者 | Guansong Pang, Cheng Yan, Chunhua Shen, Anton van den Hengel, Xiao Bai連結 | https://arxiv.org/pdf/2003.06780 備註 | Accepted to Proc. IEEE Conf. Computer Vision and Pattern Recognition 2020[61] DeepEMD: Few-Shot Image Classification with Differentiable Earth Mover's Distance and Structured Classifiers作者 | Chi Zhang, Yujun Cai, Guosheng Lin, Chunhua Shen連結 | https://arxiv.org/pdf/2003.06777 備註 | Accepted to CVPR2020 (oral)[62] Siamese Box Adaptive Network for Visual Tracking作者 | Zedu Chen, Bineng Zhong, Guorong Li, Shengping Zhang, Rongrong Ji連結 | https://arxiv.org/pdf/2003.06761 備註 | Accepted to CVPR 2020[63] Channel Pruning Guided by Classification Loss and Feature Importance作者 | Jinyang Guo, Wanli Ouyang, Dong Xu連結 | https://arxiv.org/pdf/2003.06757 [64] MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps作者 | Pengxiang Wu, Siheng Chen, Dimitris Metaxas連結 | https://arxiv.org/pdf/2003.06754 [65] Learning 2D-3D Correspondences To Solve The Blind Perspective-n-Point Problem作者 | Liu Liu, Dylan Campbell, Hongdong Li, Dingfu Zhou, Xibin Song, Ruigang Yang連結 | https://arxiv.org/pdf/2003.06752 [66] A Novel Learnable Gradient Descent Type Algorithm for Non-convex Non-smooth Inverse Problems作者 | Qingchao Zhang, Xiaojing Ye, Hongcheng Liu, Yunmei Chen連結 | https://arxiv.org/pdf/2003.06748 [67] Beyond without Forgetting: Multi-Task Learning for Classification with Disjoint Datasets作者 | Yan Hong, Li Niu, Jianfu Zhang, Liqing Zhang連結 | https://arxiv.org/pdf/2003.06746 備註 | This paper is accepted by ICME 2020[68] Vision-Dialog Navigation by Exploring Cross-modal Memory作者 | Yi Zhu, Fengda Zhu, Zhaohuan Zhan, Bingqian Lin, Jianbin Jiao, Xiaojun Chang, Xiaodan Liang連結 | https://arxiv.org/pdf/2003.06745 [69] A model of figure ground organization incorporating local and global cues作者 | Sudarshan Ramenahalli連結 | https://arxiv.org/pdf/2003.06731 [70] NoiseRank: Unsupervised Label Noise Reduction with Dependence Models作者 | Karishma Sharma, Pinar Donmez, Enming Luo, Yan Liu, I. Zeki Yalniz連結 | https://arxiv.org/pdf/2003.06729 [71] Class Conditional Alignment for Partial Domain Adaptation作者 | Mohsen Kheirandishfard, Fariba Zohrizadeh, Farhad Kamangar連結 | https://arxiv.org/pdf/2003.06722 [72] Emotions Don't Lie: A Deepfake Detection Method using Audio-Visual Affective Cues作者 | Trisha Mittal, Uttaran Bhattacharya, Rohan Chandra, Aniket Bera, Dinesh Manocha連結 | https://arxiv.org/pdf/2003.06711 [73] Identifying Individual Dogs in Social Media Images作者 | Djordje Batic, Dubravko Culibrk連結 | https://arxiv.org/pdf/2003.06705 備註 | Presented at BMVC 2019: Workshop on Visual AI and Entrepreneurship, Cardiff, UK[74] TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification作者 | Moshe Lichtenstein, Prasanna Sattigeri, Rogerio Feris, Raja Giryes, Leonid Karlinsky連結 | https://arxiv.org/pdf/2003.06670 [75] Structured Domain Adaptation for Unsupervised Person Re-identification作者 | Yixiao Ge, Feng Zhu, Rui Zhao, Hongsheng Li連結 | https://arxiv.org/pdf/2003.06650 [76] Fast Depth Estimation for View Synthesis作者 | Nantheera Anantrasirichai, Majid Geravand, David Braendler, David R. Bull連結 | https://arxiv.org/pdf/2003.06637 [77] Large-Scale Optimal Transport via Adversarial Training with Cycle-Consistency作者 | Guansong Lu, Zhiming Zhou, Jian Shen, Cheng Chen, Weinan Zhang, Yong Yu連結 | https://arxiv.org/pdf/2003.06635 [78] Non-Local Part-Aware Point Cloud Denoising作者 | Chao Huang, Ruihui Li, Xianzhi Li, Chi-Wing Fu連結 | https://arxiv.org/pdf/2003.06631 [79] Monocular Depth Estimation Based On Deep Learning: An Overview作者 | Chaoqiang Zhao, Qiyu Sun, Chongzhen Zhang, Yang Tang, Feng Qian連結 | https://arxiv.org/pdf/2003.06620 [80] Medical Image Enhancement Using Histogram Processing and Feature Extraction for Cancer Classification作者 | Sakshi Patel, Bharath K P, Rajesh Kumar Muthu連結 | https://arxiv.org/pdf/2003.06615 [81] Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition作者 | Canjie Luo, Yuanzhi Zhu, Lianwen Jin, Yongpan Wang連結 | https://arxiv.org/pdf/2003.06606 備註 | Accepted to Proc. IEEE Conf. Comp. Vis. Pattern Recogn. (CVPR) 2020[82] Collaborative Motion Prediction via Neural Motion Message Passing作者 | Yue Hu, Siheng Chen, Ya Zhang, Xiao Gu連結 | https://arxiv.org/pdf/2003.06594 備註 | Accepted by CVPR 2020 Oral[83] Image-to-image Neural Network for Addition and Subtraction of a Pair of Not Very Large Numbers連結 | https://arxiv.org/pdf/2003.06592 [84] From W-Net to CDGAN: Bi-temporal Change Detection via Deep Learning Techniques作者 | Bin Hou, Qingjie Liu, Heng Wang, Yunhong Wang連結 | https://arxiv.org/pdf/2003.06583 [85] Counterfactual Samples Synthesizing for Robust Visual Question Answering作者 | Long Chen, Xin Yan, Jun Xiao, Hanwang Zhang, Shiliang Pu, Yueting Zhuang連結 | https://arxiv.org/pdf/2003.06576 備註 | Appear in CVPR 2020;[86] Efficient Backbone Search for Scene Text Recognition作者 | Hui Zhang, Quanming Yao, Mingkun Yang, Yongchao Xu, Xiang Bai連結 | https://arxiv.org/pdf/2003.06567 [87] Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation作者 | Xiaogang Xu, Hengshuang Zhao, Jiaya Jia連結 | https://arxiv.org/pdf/2003.06555 [88] OccuSeg: Occupancy-aware 3D Instance Segmentation作者 | Lei Han, Tian Zheng, Lan Xu, Lu Fang連結 | https://arxiv.org/pdf/2003.06537 [89] An End-to-End Geometric Deficiency Elimination Algorithm for 3D Meshes作者 | Bingtao Ma, Hongsen Liu, Liangliang Nan, Yang Cong連結 | https://arxiv.org/pdf/2003.06535 [90] Learning Reinforced Agents with Counterfactual Simulation for Medical Automatic Diagnosis作者 | Junfan Lin, Ziliang Chen, Xiaodan Liang, Keze Wang, Liang Lin連結 | https://arxiv.org/pdf/2003.06534 備註 | Submitted to TPAMI 2020.[91] Instant recovery of shape from spectrum via latent space connections作者 | Riccardo Marin, Arianna Rampini, Umberto Castellani, Emanuele Rodolà, Maks Ovsjanikov, Simone Melzi連結 | https://arxiv.org/pdf/2003.06523 [92] Symmetry Detection of Occluded Point Cloud Using Deep Learning作者 | Zhelun Wu, Hongyan Jiang, Siyun He連結 | https://arxiv.org/pdf/2003.06520 [93] Explainable Deep Classification Models for Domain Generalization作者 | Andrea Zunino, Sarah Adel Bargal, Riccardo Volpi, Mehrnoosh Sameki, Jianming Zhang, Stan Sclaroff, Vittorio Murino, Kate Saenko連結 | https://arxiv.org/pdf/2003.06498 [94] Recurrent convolutional neural networks for mandible segmentation from computed tomography作者 | Bingjiang Qiu, Jiapan Guo, Joep Kraeima, Haye H. Glas, Ronald J. H. Borra, Max J. H. Witjes, Peter M. A. van Ooijen連結 | https://arxiv.org/pdf/2003.06486 [95] Self-supervised Single-view 3D Reconstruction via Semantic Consistency作者 | Xueting Li, Sifei Liu, Kihwan Kim, Shalini De Mello, Varun Jampani, Ming-Hsuan Yang, Jan Kautz連結 | https://arxiv.org/pdf/2003.06473 [96] Inducing Optimal Attribute Representations for Conditional GANs作者 | Binod Bhattarai, Tae-Kyun Kim連結 | https://arxiv.org/pdf/2003.06472 [97] GeoDA: a geometric framework for black-box adversarial attacks作者 | Ali Rahmati, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard, Huaiyu Dai連結 | https://arxiv.org/pdf/2003.06468 備註 | In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020[98] The GraphNet Zoo: A Plug-and-Play Framework for Deep Semi-Supervised Classification作者 | Marianne de Vriendt, Philip Sellars, Angelica I Aviles-Rivero連結 | https://arxiv.org/pdf/2003.06451 [99] Mutual Information Maximization for Effective Lip Reading作者 | Xing Zhao, Shuang Yang, Shiguang Shan, Xilin Chen連結 | https://arxiv.org/pdf/2003.06439 備註 | Accepted in the 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)[100] Learning Unbiased Representations via Mutual Information Backpropagation作者 | Ruggero Ragonesi, Riccardo Volpi, Jacopo Cavazza, Vittorio Murino連結 | https://arxiv.org/pdf/2003.06430 [101] Active Depth Estimation: Stability Analysis and its Applications作者 | Romulo T. Rodrigues, Pedro Miraldo, Dimos V. Dimarogonas, A. Pedro Aguiar連結 | https://arxiv.org/pdf/2003.07137 備註 | International Conference on Robotics and Automation (ICRA), 2020[102] Anomalous Instance Detection in Deep Learning: A Survey作者 | Saikiran Bulusu, Bhavya Kailkhura, Bo Li, Pramod K. Varshney, Dawn Song連結 | https://arxiv.org/pdf/2003.06979 [103] Toward Adversarial Robustness via Semi-supervised Robust Training作者 | Yiming Li, Baoyuan Wu, Yan Feng, Yanbo Fan, Yong Jiang, Zhifeng Li, Shutao Xia連結 | https://arxiv.org/pdf/2003.06974 [104] OmniTact: A Multi-Directional High Resolution Touch Sensor作者 | Akhil Padmanabha, Frederik Ebert, Stephen Tian, Roberto Calandra, Chelsea Finn, Sergey Levine連結 | https://arxiv.org/pdf/2003.06965 備註 | Accepted at International Conference on Robotics and Automation (ICRA) 2020[105] Output Diversified Initialization for Adversarial Attacks作者 | Yusuke Tashiro, Yang Song, Stefano Ermon連結 | https://arxiv.org/pdf/2003.06878 [106] Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks作者 | Amir Rahimi, Amirreza Shaban, Ching-An Cheng, Byron Boots, Richard Hartley連結 | https://arxiv.org/pdf/2003.06820 [107] Towards Privacy Protection by Generating Adversarial Identity Masks作者 | Xiao Yang, Yinpeng Dong, Tianyu Pang, Jun Zhu, Hang Su連結 | https://arxiv.org/pdf/2003.06814 [108] Experimenting with Convolutional Neural Network Architectures for the automatic characterization of Solitary Pulmonary Nodules' malignancy rating作者 | Ioannis D. Apostolopoulos連結 | https://arxiv.org/pdf/2003.06801 [109] A proto-object based audiovisual saliency map作者 | Sudarshan Ramenahalli連結 | https://arxiv.org/pdf/2003.06779 [110] Interactive Neural Style Transfer with Artists作者 | Thomas Kerdreux, Louis Thiry, Erwan Kerdreux連結 | https://arxiv.org/pdf/2003.06659 [111] Investigating Generalization in Neural Networks under Optimally Evolved Training Perturbations作者 | Subhajit Chaudhury, Toshihiko Yamasaki連結 | https://arxiv.org/pdf/2003.06646 備註 | Accepted at IEEE ICASSP 2020[112] Rapid Whole Slide Imaging via Learning-based Two-shot Virtual Autofocusing作者 | Qiang Li, Xianming Liu, Kaige Han, Cheng Guo, Xiangyang Ji, Xiaolin Wu連結 | https://arxiv.org/pdf/2003.06630 [113] VarMixup: Exploiting the Latent Space for Robust Training and Inference作者 | Puneet Mangla, Vedant Singh, Shreyas Jayant Havaldar, Vineeth N Balasubramanian連結 | https://arxiv.org/pdf/2003.06566 [114] Boundary Guidance Hierarchical Network for Real-Time Tongue Segmentation作者 | Xinyi Zeng, Qian Zhang, Jia Chen, Guixu Zhang, Aimin Zhou, Yiqin Wang連結 | https://arxiv.org/pdf/2003.06529 [115] Leveraging Vision and Kinematics Data to Improve Realism of Biomechanic Soft-tissue Simulation for Robotic Surgery作者 | Jie Ying Wu, Peter Kazanzides, Mathias Unberath連結 | https://arxiv.org/pdf/2003.06518 備註 | to be published in IJCARS IPCAI special edition 2020[116] A Privacy-Preserving DNN Pruning and Mobile Acceleration Framework作者 | Zheng Zhan, Yifan Gong, Zhengang Li, Pu Zhao, Xiaolong Ma, Wei Niu, Xiaolin Xu, Bin Ren, Yanzhi Wang, Xue Lin連結 | https://arxiv.org/pdf/2003.06513