出品 | 深度學習這件小事公眾號
計算機視覺（11月30日更新版）
[1] Unsupervised part representation by Flow Capsules
作者 | Sara Sabour, Andrea Tagliasacchi, Soroosh Yazdani, Geoffrey E. Hinton, David J. Fleet
連結 | https://arxiv.org/abs/2011.13920
[2] Task Programming: Learning Data Efficient Behavior Representations
作者 | Jennifer J. Sun, Ann Kennedy, Eric Zhan, Yisong Yue, Pietro Perona
連結 | https://arxiv.org/abs/2011.13917
[3] Progressively Volumetrized Deep Generative Models for Data-Efficient Contextual Learning of MR Image Recovery
作者 | Mahmut Yurt, Muzaffer Özbey, Salman Ul Hassan Dar, Berk Tınaz, Kader Karlı Oğuz, Tolga Çukur
連結 | https://arxiv.org/abs/2011.13913
[4] Efficient Scene Compression for Visual-based Localization
作者 | Marcela Mera-Trujillo, Benjamin Smith, Victor Fragoso
連結 | https://arxiv.org/abs/2011.13894
[5] Field of Junctions
作者 | Dor Verbin, Todd Zickler
連結 | https://arxiv.org/abs/2011.13866
[6] Robust Detection of Non-overlapping Ellipses from Points with Applications to Circular Target Extraction in Images and Cylinder Detection in Point Clouds
作者 | Reza Maalek, Derek Lichti
連結 | https://arxiv.org/abs/2011.13849
[7] SFTrack++: A Fast Learnable Spectral Segmentation Approach for Space-Time Consistent Tracking
作者 | Elena Burceanu
連結 | https://arxiv.org/abs/2011.13843
備註 | Accepted at Neural Information Processing Systems (NeurIPS) 2020 - Pre-registration Workshop
[8] Generalized Pose-and-Scale Estimation using 4-Point Congruence Constraints
作者 | Victor Fragoso, Sudipta Sinha
連結 | https://arxiv.org/abs/2011.13817
[9] Leveraging Regular Fundus Images for Training UWF Fundus Diagnosis Models via Adversarial Learning and Pseudo-Labeling
作者 | Lie Ju, Xin Wang, Xin Zhao, Paul Bonnington, Tom Drummond, Zongyuan Ge
連結 | https://arxiv.org/abs/2011.13816
[10] Spherical Interpolated Convolutional Network with Distance-Feature Density for 3D Semantic Segmentation of Point Clouds
作者 | Guangming Wang, Yehui Yang, Huixin Zhang, Zhe Liu, Hesheng Wang
連結 | https://arxiv.org/abs/2011.13784
備註 | under review
[11] Enhancing Diversity in Teacher-Student Networks via Asymmetric branches for Unsupervised Person Re-identification
作者 | Hao Chen, Benoit Lagadec, Francois Bremond
連結 | https://arxiv.org/abs/2011.13776
備註 | WACV 2021
[12] Image Generators with Conditionally-Independent Pixel Synthesis
作者 | Ivan Anokhin, Kirill Demochkin, Taras Khakhulin, Gleb Sterkin, Victor Lempitsky, Denis Korzhenkov
連結 | https://arxiv.org/abs/2011.13775
[13] 3D Invisible Cloak
作者 | Mingfu Xue, Can He, Zhiyu Wu, Jian Wang, Zhe Liu, Weiqiang Liu
連結 | https://arxiv.org/abs/2011.13705
[14] Lightweight U-Net for High-Resolution Breast Imaging
作者 | Mickael Tardy, Diana Mateus
連結 | https://arxiv.org/abs/2011.13698
備註 | in Proceedings of iTWIST'20, Paper-ID: 30, Nantes, France, December, 2-4, 2020
[15] Robust and Natural Physical Adversarial Examples for Object Detectors
作者 | Mingfu Xue, Chengxiang Yuan, Can He, Jian Wang, Weiqiang Liu
連結 | https://arxiv.org/abs/2011.13692
[16] MEBOW: Monocular Estimation of Body Orientation In the Wild
作者 | Chenyan Wu, Yukun Chen, Jiajia Luo, Che-Chun Su, Anuja Dawane, Bikramjot Hanzra, Zhuo Deng, Bilan Liu, James Wang, Cheng-Hao Kuo
連結 | https://arxiv.org/abs/2011.13688
備註 | Accepted by CVPR2020
[17] Point and Ask: Incorporating Pointing into Visual Question Answering
作者 | Arjun Mani, Will Hinthorn, Nobline Yoo, Olga Russakovsky
連結 | https://arxiv.org/abs/2011.13681
[18] Self-EMD: Self-Supervised Object Detection without ImageNet
作者 | Songtao Liu, Zeming Li, Jian Sun
連結 | https://arxiv.org/abs/2011.13677
[19] Deinterlacing Network for Early Interlaced Videos
作者 | Yang Zhao, Wei Jia, Ronggang Wang, Xiaoping Liu, Xuesong Gao, Weiqiang Chen, Wen Gao
連結 | https://arxiv.org/abs/2011.13675
[20] Towards real-time object recognition and pose estimation in point clouds
作者 | Marlon Marcon, Olga Regina Pereira Bellon, Luciano Silva
連結 | https://arxiv.org/abs/2011.13669
備註 | Accepted as Full paper at VISAPP2021
[21] Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondence
作者 | Yu Deng, Jiaolong Yang, Xin Tong
連結 | https://arxiv.org/abs/2011.13650
[22] Descriptor-Free Multi-View Region Matching for Instance-Wise 3D Reconstruction
作者 | Takuma Doi, Fumio Okura, Toshiki Nagahara, Yasuyuki Matsushita, Yasushi Yagi
連結 | https://arxiv.org/abs/2011.13649
備註 | ACCV2020 Oral
[23] Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving
作者 | Zhenxun Yuan, Xiao Song, Lei Bai, Wengang Zhou, Zhe Wang, Wanli Ouyang
連結 | https://arxiv.org/abs/2011.13628
[24] Manipulating Medical Image Translation with Manifold Disentanglement
作者 | Siyu Liu, Jason A. Dowling, Craig Engstrom, Peter B. Greer, Stuart Crozier, Shekhar S. Chandra
連結 | https://arxiv.org/abs/2011.13615
[25] Multi-task MR Imaging with Iterative Teacher Forcing and Re-weighted Deep Learning
作者 | Kehan Qi, Yu Gong, Xinfeng Liu, Xin Liu, Hairong Zheng, Shanshan Wang
連結 | https://arxiv.org/abs/2011.13614
[26] Frequency Domain Image Translation: More Photo-realistic, Better Identity-preserving
作者 | Mu Cai, Hong Zhang, Huijuan Huang, Qichuan Geng, Gao Huang
連結 | https://arxiv.org/abs/2011.13611
[27] PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layers
作者 | Frank Yu, Mathieu Salzmann, Pascal Fua, Helge Rhodin
連結 | https://arxiv.org/abs/2011.13607
[28] Multi-objective Neural Architecture Search with Almost No Training
作者 | Shengran Hu, Ran Cheng, Cheng He, Zhichao Lu
連結 | https://arxiv.org/abs/2011.13591
備註 | EMO 2021
[29] Road Scene Graph: A Semantic Graph-Based Scene Representation Dataset for Intelligent Vehicles
作者 | Yafu Tian, Alexander Carballo, Ruifeng Li, Kazuya Takeda
連結 | https://arxiv.org/abs/2011.13588
備註 | under review ICRA 2021
[30] A Sheaf and Topology Approach to Generating Local Branch Numbers in Digital Images
作者 | Chuan-Shen Hu, Yu-Min Chung
連結 | https://arxiv.org/abs/2011.13580
[31] SocialGuard: An Adversarial Example Based Privacy-Preserving Technique for Social Images
作者 | Mingfu Xue, Shichang Sun, Zhiyu Wu, Can He, Jian Wang, Weiqiang Liu
連結 | https://arxiv.org/abs/2011.13560
[32] Association: Remind Your GAN not to Forget
作者 | Yi Gu, Yuting Gao, Ruoxin Chen, Feiyang Cai, Jie Li, Chentao Wu
連結 | https://arxiv.org/abs/2011.13553
[33] Patch-VQ: 'Patching Up' the Video Quality Problem
作者 | Zhenqiang Ying (1), Maniratnam Mandal (1), Deepti Ghadiyaram (2), Alan Bovik (1) ((1) University of Texas at Austin, (2) Facebook AI)
連結 | https://arxiv.org/abs/2011.13544
[34] The NEOLIX Open Dataset for AutonomousDriving
作者 | Lichao Wang, Lanxin Lei, Hongli Song, Weibao Wang
連結 | https://arxiv.org/abs/2011.13528
[35] Robust Attacks on Deep Learning Face Recognition in the Physical World
作者 | Meng Shen, Hao Yu, Liehuang Zhu, Ke Xu, Qi Li, Xiaojiang Du
連結 | https://arxiv.org/abs/2011.13526
[36] Tractable loss function and color image generation of multinary restricted Boltzmann machine
作者 | Juno Hwang, Wonseok Hwang, Junghyo Jo
連結 | https://arxiv.org/abs/2011.13509
備註 | NueRIPS 2020 DiffCVGP workshop paper
[37] Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces
作者 | Baorui Ma, Zhizhong Han, Yu-Shen Liu, Matthias Zwicker
連結 | https://arxiv.org/abs/2011.13495
[38] Bidirectional Modeling and Analysis of Brain Aging with Normalizing Flows
作者 | Matthias Wilms, Jordan J. Bannister, Pauline Mouches, M. Ethan MacDonald, Deepthi Rajashekar, S枚nke Langner, Nils D. Forkert
連結 | https://arxiv.org/abs/2011.13484
備註 | Presented at 3rd International Workshop on Machine Learning in Clinical Neuroimaging - in conjunction with MICCAI 2020
[39] Fine-Grained Re-Identification
作者 | Priyank Pathak
連結 | https://arxiv.org/abs/2011.13475
[40] Multi-view Human Pose and Shape Estimation Using Learnable Volumetric Aggregation
作者 | Soyong Shin, Eni Halilaj
連結 | https://arxiv.org/abs/2011.13427
備註 | code will be released soon
[41] Generative Layout Modeling using Constraint Graphs
作者 | Wamiq Para, Paul Guerrero, Tom Kelly, Leonidas Guibas, Peter Wonka
連結 | https://arxiv.org/abs/2011.13417
[42] Learning from Lexical Perturbations for Consistent Visual Question Answering
作者 | Spencer Whitehead, Hui Wu, Yi Ren Fung, Heng Ji, Rogerio Feris, Kate Saenko
連結 | https://arxiv.org/abs/2011.13406
[43] Depth-Aware Action Recognition: Pose-Motion Encoding through Temporal Heatmaps
作者 | Mattia Segu, Federico Pirovano, Gianmario Fumagalli, Amedeo Fabris
連結 | https://arxiv.org/abs/2011.13399
[44] 3DSNet: Unsupervised Shape-to-Shape 3D Style Transfer
作者 | Mattia Segu, Margarita Grinvald, Roland Siegwart, Federico Tombari
連結 | https://arxiv.org/abs/2011.13388
[45] How Well Do Self-Supervised Models Transfer?
作者 | Linus Ericsson, Henry Gouk, Timothy M. Hospedales
連結 | https://arxiv.org/abs/2011.13377
項目連結 | https://github.com/linusericsson/ssl-transfer
[46] Invisible Perturbations: Physical Adversarial Examples Exploiting the Rolling Shutter Effect
作者 | Athena Sayles, Ashish Hooda, Mohit Gupta, Rahul Chatterjee, Earlence Fernandes
連結 | https://arxiv.org/abs/2011.13375
[47] Automated Blood Cell Counting from Non-invasive Capillaroscopy Videos with Bidirectional Temporal Deep Learning Tracking Algorithm
作者 | Luojie Huang, Gregory N. McKay, Nicholas J. Durr
連結 | https://arxiv.org/abs/2011.13371
[48] SoccerNet-v2 : A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos
作者 | Adrien Delinge, Anthony Cioppa, Silvio Giancola, Meisam J. Seikavandi, Jacob V. Dueholm, Kamal Nasrollahi, Bernard Ghanem, Thomas B. Moeslund, Marc Van Droogenbroeck
連結 | https://arxiv.org/abs/2011.13367
備註 | This document contains 8 pages + references + supplementary material
[49] SSDL: Self-Supervised Domain Learning for Improved Face Recognition
作者 | S. W. Arachchilage, E. Izquierdo
連結 | https://arxiv.org/abs/2011.13361
[50] ClusterFace: Joint Clustering and Classification for Set-Based Face Recognition
作者 | S. W. Arachchilage, E. Izquierdo
連結 | https://arxiv.org/abs/2011.13360
[51] Beyond Single Instance Multi-view Unsupervised Representation Learning
作者 | Xiangxiang Chu, Xiaohang Zhan, Xiaolin Wei
連結 | https://arxiv.org/abs/2011.13356
備註 | A plug-in approach with minimal modification to existing methods based on instance discrimination
[52] 4D Human Body Capture from Egocentric Video via 3D Scene Grounding
作者 | Miao Liu, Dexin Yang, Yan Zhang, Zhaopeng Cui, James M. Rehg, Siyu Tang
連結 | https://arxiv.org/abs/2011.13341
[53] DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution
作者 | Tong He, Chunhua Shen, Anton van den Hengel
連結 | https://arxiv.org/abs/2011.13328
[54] Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition
作者 | Zhen Huang, Xu Shen, Xinmei Tian, Houqiang Li, Jianqiang Huang, Xian-Sheng Hua
連結 | https://arxiv.org/abs/2011.13322
備註 | ACMMM 2020
[55] Adaptive Multiplane Image Generation from a Single Internet Picture
作者 | Diogo C. Luvizon, Gustavo Sutter P. Carvalho, Andreza A. dos Santos, Jhonatas S. Conceicao, Jose L. Flores-Campana, Luis G. L. Decker, Marcos R. Souza, Helio Pedrini, Antonio Joia, Otavio A. B. Penatti
連結 | https://arxiv.org/abs/2011.13317
[56] Polarization-driven Semantic Segmentation via Efficient Attention-bridged Fusion
作者 | Kaite Xiang, Kailun Yang, Kaiwei Wang
連結 | https://arxiv.org/abs/2011.13313
項目連結 | https://github.com/Katexiang/EAFNet
[57] SelfText Beyond Polygon: Unconstrained Text Detection with Box Supervision and Dynamic Self-Training
作者 | Weijia Wu, Enze Xie, Ruimao Zhang, Wenhai Wang, Guan Pang, Zhen Li, Hong Zhou, Ping Luo
連結 | https://arxiv.org/abs/2011.13307
[58] Group-Skeleton-Based Human Action Recognition in Complex Events
作者 | Tingtian Li, Zixun Sun, Xiao Chen
連結 | https://arxiv.org/abs/2011.13273
備註 | accpeted by ACM MM 2020
[59] CYPUR-NN: Crop Yield Prediction Using Regression and Neural Networks
作者 | Sandesh Ramesh, Anirudh Hebbar, Varun Yadav, Thulasiram Gunta, A Balachandra
連結 | https://arxiv.org/abs/2011.13265
備註 | Advances in Intelligent Systems and Computing
[60] Channel-wise Distillation for Semantic Segmentation
作者 | Changyong Shu, Yifan Liu, Jianfei Gao, Lin Xu, Chunhua Shen
連結 | https://arxiv.org/abs/2011.13256
項目連結 | https://git.io/ChannelDis
[61] IFSS-Net: Interactive Few-Shot Siamese Network for Faster Muscles Segmentation and Propagation in 3-D Freehand Ultrasound
作者 | Dawood Al Chanti, Vanessa Gonzalez Duque, Marion Crouzier, Antoine Nordez, Lilian Lacourpaille, Diana Mateus
連結 | https://arxiv.org/abs/2011.13246
[62] MVTN: Multi-View Transformation Network for 3D Shape Recognition
作者 | Abdullah Hamdi, Silvio Giancola, Bing Li, Ali Thabet, Bernard Ghanem
連結 | https://arxiv.org/abs/2011.13244
備註 | preprint
[63] The Devil is in the Boundary: Exploiting Boundary Representation for Basis-based Instance Segmentation
作者 | Myungchul Kim, Sanghyun Woo, Dahun Kim, In So Kweon
連結 | https://arxiv.org/abs/2011.13241
[64] MultiStar: Instance Segmentation of Overlapping Objects with Star-Convex Polygons
作者 | Florin C. Walter, Sebastian Damrich, Fred A. Hamprecht
連結 | https://arxiv.org/abs/2011.13228
備註 | Submitted to ISBI 2021
[65] Depth-Enhanced Feature Pyramid Network for Occlusion-Aware Verification of Buildings from Oblique Images
作者 | Qing Zhu, Shengzhi Huang, Han Hu, Haifeng Li, Min Chen, Ruofei Zhong
連結 | https://arxiv.org/abs/2011.13226
[66] Handling Object Symmetries in CNN-based Pose Estimation
作者 | Jesse Richter-Klug, Udo Frese
連結 | https://arxiv.org/abs/2011.13209
備註 | This work has been submitted to the IEEE (ICRA 2021) for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible
[67] t-EVA: Time-Efficient t-SNE Video Annotation
作者 | Soroosh Poorgholi, Osman Semih Kayhan, Jan C. van Gemert
連結 | https://arxiv.org/abs/2011.13202
備註 | ICPR 2020 (HCAU)
[68] TinaFace: Strong but Simple Baseline for Face Detection
作者 | Yanjia Zhu, Hongxiang Cai, Shuhan Zhang, Chenhao Wang, Yichao Xiong
連結 | https://arxiv.org/abs/2011.13183
[69] Transformation Driven Visual Reasoning
作者 | Xin Hong, Yanyan Lan, Liang Pang, Jiafeng Guo, Xueqi Cheng
連結 | https://arxiv.org/abs/2011.13160
[70] Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN
作者 | Serin Yang, Eung Yeop Kim, Jong Chul Ye
連結 | https://arxiv.org/abs/2011.13150
[71] Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Images
作者 | Qijian Zhang, Runmin Cong, Chongyi Li, Ming-Ming Cheng, Yuming Fang, Xiaochun Cao, Yao Zhao, Sam Kwong
連結 | https://arxiv.org/abs/2011.13144
項目連結 | https://github.com/rmcong/EORSSD-dataset
備註 | Accepted by IEEE Transactions on Image Processing
[72] A Fast Point Cloud Ground Segmentation Approach Based on Coarse-To-Fine Markov Random Field
作者 | Weixin Huang, Huawei Liang, Linglong Lin, Zhiling Wang, Shaobo Wang, Biao Yu, Runxin Niu
連結 | https://arxiv.org/abs/2011.13140
備註 | 16 page,22 figures
[73] Lifting 2D StyleGAN for 3D-Aware Face Generation
作者 | Yichun Shi, Divyansh Aggarwal, Anil K. Jain
連結 | https://arxiv.org/abs/2011.13126
[74] Multi-view Depth Estimation using Epipolar Spatio-Temporal Network
作者 | Xiaoxiao Long, Lingjie Liu, Wei Li, Christian Theobalt, Wenping Wang
連結 | https://arxiv.org/abs/2011.13118
[75] Polka Lines: Learning Structured Illumination and Reconstruction for Active Stereo
作者 | Seung-Hwan Baek, Felix Heide
連結 | https://arxiv.org/abs/2011.13117
[76] Automatic Detection of Cardiac Chambers Using an Attention-based YOLOv4 Framework from Four-chamber View of Fetal Echocardiography
作者 | Sibo Qiao, Shanchen Pang, Gang Luo, Silin Pan, Xun Wang, Min Wang, Xue Zhai, Taotao Chen
連結 | https://arxiv.org/abs/2011.13096
[77] Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes
作者 | Zhengqi Li, Simon Niklaus, Noah Snavely, Oliver Wang
連結 | https://arxiv.org/abs/2011.13084
項目連結 | http://www.cs.cornell.edu/~zl548/NSFF/
[78] Photoacoustic Reconstruction Using Sparsity in Curvelet Frame
作者 | Bolin Pan, Simon R. Arridge, Felix Lucka, Ben T. Cox, Nam Huynh, Paul C. Beard, Edward Z. Zhang, Marta M. Betcke
連結 | https://arxiv.org/abs/2011.13080
[79] Non-Rigid Puzzles
作者 | Or Litany, Emanuele Rodolà, Alex Bronstein, Michael Bronstein, Daniel Cremers
連結 | https://arxiv.org/abs/2011.13076
[80] Omni-GAN: On the Secrets of cGANs and Beyond
作者 | Peng Zhou, Lingxi Xie, Bingbing Ni, Qi Tian
連結 | https://arxiv.org/abs/2011.13074
項目連結 | https://github.com/PeterouZh/Omni-GAN-PyTorch
[81] Effective Sample Pair Generation for Ultrasound Video Contrastive Representation Learning
作者 | Yixiong Chen, Chunhui Zhang, Li Liu, Cheng Feng, Changfeng Dong, Yongfang Luo, Xiang Wan
連結 | https://arxiv.org/abs/2011.13066
[82] How to train your conditional GAN: An approach using geometrically structured latent manifolds
作者 | Sameera Ramasinghe, Moshiur Farazi, Salman Khan, Nick Barnes, Stepehn Gould
連結 | https://arxiv.org/abs/2011.13055
[83] Can Temporal Information Help with Contrastive Self-Supervised Learning?
作者 | Yutong Bai, Haoqi Fan, Ishan Misra, Ganesh Venkatesh, Yongyi Lu, Yuyin Zhou, Qihang Yu, Vikas Chandra, Alan Yuille
連結 | https://arxiv.org/abs/2011.13046
[84] Learning to Infer Shape Programs Using Latent Execution Self Training
作者 | Homer Walke, R. Kenny Jones, Daniel Ritchie
連結 | https://arxiv.org/abs/2011.13045
[85] Augmentation-Interpolative AutoEncoders for Unsupervised Few-Shot Image Generation
作者 | Davis Wertheimer, Omid Poursaeed, Bharath Hariharan
連結 | https://arxiv.org/abs/2011.13026
[86] PREDATOR: Registration of 3D Point Clouds with Low Overlap
作者 | Shengyu Huang, Zan Gojcic, Mikhail Usvyatsov, Andreas Wieser, Konrad Schindler
連結 | https://arxiv.org/abs/2011.13005
[87] Sign language segmentation with temporal convolutional networks
作者 | Katrin Renz, Nicolaj C. Stache, Samuel Albanie, Gül Varol
連結 | https://arxiv.org/abs/2011.12986
[88] Grafit: Learning fine-grained image representations with coarse labels
作者 | Hugo Touvron, Alexandre Sablayrolles, Matthijs Douze, Matthieu Cord, Hervé Jégou
連結 | https://arxiv.org/abs/2011.12982
[89] Deep Convolutional Neural Networks: A survey of the foundations, selected improvements, and some current applications
作者 | Lars Lien Ankile, Morgan Feet Heggland, Kjartan Krange
連結 | https://arxiv.org/abs/2011.12960
[90] PS-DeVCEM: Pathology-sensitive deep learning model for video capsule endoscopy based on weakly labeled data
作者 | A. Mohammed, I. Farup, M. Pedersen, S. Yildirim, Ø Hovde
連結 | https://arxiv.org/abs/2011.12957
[91] Real-time Active Vision for a Humanoid Soccer Robot Using Deep Reinforcement Learning
作者 | Soheil Khatibi, Meisam Teimouri, Mahdi Rezaei
連結 | https://arxiv.org/abs/2011.13851
備註 | The paper has been accepted in ICAART 2021
[92] Navigating the GAN Parameter Space for Semantic Image Editing
作者 | Anton Cherepkov, Andrey Voynov, Artem Babenko
連結 | https://arxiv.org/abs/2011.13786
項目連結 | https://github.com/yandex-research/navigan
[93] Robust Autonomous Landing of UAV in Non-Cooperative Environments based on Dynamic Time Camera-LiDAR Fusion
作者 | Lyujie Chen, Xiaming Yuan, Yao Xiao, Yiding Zhang, Jihong Zhu
連結 | https://arxiv.org/abs/2011.13761
備註 | Submitted to ICRA 2021
[94] Rethinking Generalization in American Sign Language Prediction for Edge Devices with Extremely Low Memory Footprint
作者 | Aditya Jyoti Paul, Puranjay Mohan, Stuti Sehgal
連結 | https://arxiv.org/abs/2011.13741
項目連結 | https://raics.in/
備註 | Accepted and presented in IEEE RAICS 2020
[95] A study of traits that affect learnability in GANs
作者 | Niladri Shekhar Dutt, Sunil Patel
連結 | https://arxiv.org/abs/2011.13728
[96] Detection of Malaria Vector Breeding Habitats using Topographic Models
作者 | Aishwarya Jadhav
連結 | https://arxiv.org/abs/2011.13714
備註 | Presented at NeurIPS 2020 Workshop on Machine Learning for the Developing World
[97] An Ethical Highlighter for People-Centric Dataset Creation
作者 | Margot Hanley, Apoorv Khandelwal, Hadar Averbuch-Elor, Noah Snavely, Helen Nissenbaum
連結 | https://arxiv.org/abs/2011.13583
備註 | Part of the Navigating the Broader Impacts of AI Research Workshop at NeurIPS 2020
[98] A Survey of Deep Learning Approaches for OCR and Document Understanding
作者 | Nishant Subramani, Alexandre Matton, Malcolm Greaves, Adrian Lam
連結 | https://arxiv.org/abs/2011.13534
備註 | Accepted to the ML-RSA Workshop at NeurIPS2020.
[99] They are Not Completely Useless: Towards Recycling Transferable Unlabeled Data for Class-Mismatched Semi-Supervised Learning
作者 | Huang Zhuo, Tai Ying, Wang Chengjie, Yang Jian, Gong Chen
連結 | https://arxiv.org/abs/2011.13529
[100] Explaining Deep Learning Models for Structured Data using Layer-Wise Relevance Propagation
作者 | hsan Ullah, Andre Rios, Vaibhav Gala, Susan Mckeever
連結 | https://arxiv.org/abs/2011.13429
[101] Exposing the Robustness and Vulnerability of Hybrid 8T-6T SRAM Memory Architectures to Adversarial Attacks in Deep Neural Networks
作者 | Abhishek Moitra, Priyadarshini Panda
連結 | https://arxiv.org/abs/2011.13392
[102] Joint Reconstruction and Calibration using Regularization by Denoising
作者 | Mingyang Xie, Yu Sun, Jiaming Liu, Brendt Wohlberg, Ulugbek S. Kamilov
連結 | https://arxiv.org/abs/2011.13391
[103] Analysing Social Media Network Data with R: Semi-Automated Screening of Users, Comments and Communication Patterns
作者 | Dennis Klinkhammer
連結 | https://arxiv.org/abs/2011.13327
[104] Regularization with Latent Space Virtual Adversarial Training
作者 | Genki Osada, Budrul Ahsan, Revoti Prasad Bora, Takashi Nishide
連結 | https://arxiv.org/abs/2011.13181
備註 | Accepted at ECCV 2020 (Oral)
[105] Saliency-based segmentation of dermoscopic images using color information
作者 | Giuliana Ramella
連結 | https://arxiv.org/abs/2011.13179
備註 | Preprint
[106] Energy Drain of the Object Detection Processing Pipeline for Mobile Devices: Analysis and Implications
作者 | Haoxin Wang, BaekGyu Kim, Jiang Xie, Zhu Han
連結 | https://arxiv.org/abs/2011.13075
備註 | This is a personal copy of the authors. Not for redistribution. The final version of this paper was accepted by IEEE Transactions on Green Communications and Networking
[107] Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization
作者 | Tianyu Han, Sven Nebelung, Federico Pedersoli, Markus Zimmermann, Maximilian Schulze-Hagen, Michael Ho, Christoph Haarburger, Fabian Kiessling, Christiane Kuhl, Volkmar Schulz, Daniel Truhn
連結 | https://arxiv.org/abs/2011.13011
[108] Ax-BxP: Approximate Blocked Computation for Precision-Reconfigurable Deep Neural Network Acceleration
作者 | Reena Elangovan, Shubham Jain, Anand Raghunathan
連結 | https://arxiv.org/abs/2011.13000
[109] Learning to dance: A graph convolutional adversarial network to generate realistic dance motions from audio
作者 | João P. Ferreira, Thiago M. Coutinho, Thiago L. Gomes, José F. Neto, Rafael Azevedo, Renato Martins, Erickson R. Nascimento
連結 | https://arxiv.org/abs/2011.12999