出品 | 深度學習這件小事公眾號
計算機視覺（6月16日更新版）
[1] Coherent Reconstruction of Multiple Humans from a Single Image作者 | Wen Jiang, Nikos Kolotouros, Georgios Pavlakos, Xiaowei Zhou, Kostas Daniilidis連結 | https://arxiv.org/abs/2006.08586項目連結 | https://jiangwenpl.github.io/multiperson/[2] Now that I can see, I can improve: Enabling data-driven finetuning of CNNs on the edge作者 | Aditya Rajagopal, Christos-Savvas Bouganis連結 | https://arxiv.org/abs/2006.08554 備註 | Accepted for publication at CVPR2020 workshop - Efficient Deep Learning for Computer Vision[3] Visibility Guided NMS: Efficient Boosting of Amodal Object Detection in Crowded Traffic Scenes作者 | Nils Gählert, Niklas Hanselmann, Uwe Franke, Joachim Denzler連結 | https://arxiv.org/abs/2006.08547 備註 | Machine Learning for Autonomous Driving Workshop at the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada[4] Go-CaRD -- Generic, Optical Car Part Recognition and Detection: Collection, Insights, and Applications作者 | Lukas Stappen, Xinchen Du, Vincent Karas, Stefan Müller, Björn W. Schuller連結 | https://arxiv.org/abs/2006.08521 備註 | submitted to IEEE MMSP 2020[5] Towards Incorporating Contextual Knowledge into the Prediction of Driving Behavior作者 | Florian Wirthmüller, Julian Schlechtriemen, Jochen Hipp, Manfred Reichert連結 | https://arxiv.org/abs/2006.08470 備註 | the article has been accepted for publication during the 23rd IEEE Intelligent Transportation Systems Conference (ITSC)[6] 3D-ZeF: A 3D Zebrafish Tracking Benchmark Dataset作者 | Malte Pedersen, Joakim Bruslund Haurum, Stefan Hein Bengtson, Thomas B. Moeslund連結 | https://arxiv.org/abs/2006.08466 項目連結 | https://vap.aau.dk/3d-zef/[7] SD-RSIC: Summarization Driven Deep Remote Sensing Image Captioning作者 | Gencer Sumbul, Sonali Nayak, Begüm Demir連結 | https://arxiv.org/abs/2006.08432 [8] Pixel Invisibility: Detecting Objects Invisible in Color Images作者 | Yongxin, Wang, Duminda Wijesekera連結 | https://arxiv.org/abs/2006.08383 備註 | submitted to NIPS 2020[9] Generating Master Faces for Use in Performing Wolf Attacks on Face Recognition Systems作者 | Huy H. Nguyen, Junichi Yamagishi, Isao Echizen, Sébastien Marcel連結 | https://arxiv.org/abs/2006.08376 備註 | Accepted to be Published in Proceedings of the 2020 International Joint Conference on Biometrics (IJCB 2020), Houston, USA[10] Tamil Vowel Recognition With Augmented MNIST-like Data Set連結 | https://arxiv.org/abs/2006.08367 [11] CoDeNet: Algorithm-hardware Co-design for Deformable Convolution作者 | Zhen Dong, Dequan Wang, Qijing Huang, Yizhao Gao, Yaohui Cai, Bichen Wu, Kurt Keutzer, John Wawrzynek連結 | https://arxiv.org/abs/2006.08357 項目連結 | https://github.com/DequanWang/CoDeNet[12] ORD: Object Relationship Discovery for Visual Dialogue Generation作者 | Ziwei Wang, Zi Huang, Yadan Luo, Huimin Lu連結 | https://arxiv.org/abs/2006.08322 [13] On the Preservation of Spatio-temporal Information in Machine Learning Applications作者 | Yigit Oktar, Mehmet Turkan連結 | https://arxiv.org/abs/2006.08321 [14] Mitigating Gender Bias in Captioning Systems作者 | Ruixiang Tang, Mengnan Du, Yuening Li, Zirui Liu, Xia Hu連結 | https://arxiv.org/abs/2006.08315 [15] Deep-CAPTCHA: a deep learning based CAPTCHA solver for vulnerability assessment作者 | Zahra Noury, Mahdi Rezaei連結 | https://arxiv.org/abs/2006.08296 [16] AMENet: Attentive Maps Encoder Network for Trajectory Prediction作者 | Hao Cheng, Wentong Liao, Michael Ying Yang, Bodo Rosenhahn, Monika Sester連結 | https://arxiv.org/abs/2006.08264 [17] Dermatologist vs Neural Network作者 | Kaushil Mangaroliya, Mitt Shah連結 | https://arxiv.org/abs/2006.08254 [18] Learn to cycle: Time-consistent feature discovery for action recognition作者 | Alexandros Stergiou, Ronald Poppe連結 | https://arxiv.org/abs/2006.08247 [19] AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks作者 | Yonggan Fu, Wuyang Chen, Haotao Wang, Haoran Li, Yingyan Lin, Zhangyang Wang連結 | https://arxiv.org/abs/2006.08198 備註 | Accepted by ICML2020[20] Infinite Feature Selection: A Graph-based Feature Filtering Approach作者 | Giorgio Roffo, Simone Melzi, Umberto Castellani, Alessandro Vinciarelli, Marco Cristani連結 | https://arxiv.org/abs/2006.08184 [21] Binary DAD-Net: Binarized Driveable Area Detection Network for Autonomous Driving作者 | Alexander Frickenstein, Manoj Rohit Vemparala, Jakob Mayr, Naveen Shankar Nagaraja, Christian Unger, Federico Tombari, Walter Stechele連結 | https://arxiv.org/abs/2006.08178 備註 | IEEE International Conference on Robotics and Automation (ICRA) 2020[22] Neural gradients are lognormally distributed: understanding sparse and quantized training作者 | Brian Chmiel, Liad Ben-Uri, Moran Shkolnik, Elad Hoffer, Ron Banner, Daniel Soudry連結 | https://arxiv.org/abs/2006.08173 [23] Filter design for small target detection on infrared imagery using normalized-cross-correlation layer作者 | H. Seçkin Demir, Erdem Akagunduz連結 | https://arxiv.org/abs/2006.08162 [24] Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusion連結 | https://arxiv.org/abs/2006.08159 備註 | Appearing at ACM TOMM, 26 pages[25] Classifying degraded images over various levels of degradation作者 | Kazuki Endo, Masayuki Tanaka, Masatoshi Okutomi連結 | https://arxiv.org/abs/2006.08145 備註 | Accepted by the 27th IEEE International Conference on Image Processing (ICIP 2020)[26] Anomalous Motion Detection on Highway Using Deep Learning作者 | Harpreet Singh, Emily M. Hand, Kostas Alexis連結 | https://arxiv.org/abs/2006.08143 備註 | to be published in IEEE ICIP 2020[27] Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction作者 | Tong He, John Collomosse, Hailin Jin, Stefano Soatto連結 | https://arxiv.org/abs/2006.08072 [28] Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution作者 | Xianhang Cheng, Zhenzhong Chen連結 | https://arxiv.org/abs/2006.08070 [29] RasterNet: Modeling Free-Flow Speed using LiDAR and Overhead Imagery作者 | Armin Hadzic, Hunter Blanton, Weilian Song, Mei Chen, Scott Workman, Nathan Jacobs連結 | https://arxiv.org/abs/2006.08021 [30] BatVision with GCC-PHAT Features for Better Sound to Vision Predictions作者 | Jesper Haahr Christensen, Sascha Hornauer, Stella Yu連結 | https://arxiv.org/abs/2006.07995 [31] Road Mapping in Low Data Environments with OpenStreetMap作者 | John Kamalu, Benjamin Choi連結 | https://arxiv.org/abs/2006.07993 [32] Emergent Properties of Foveated Perceptual Systems作者 | Arturo Deza, Talia Konkle連結 | https://arxiv.org/abs/2006.07991 備註 | A pre-print. Currently under review at the Conference on Neural Information Processing Systems (NeurIPS 2020). Themes: Foveation, Perception & Representational Learning[33] GradAug: A New Regularization Method for Deep Neural Networks作者 | Taojiannan Yang, Sijie Zhu, Chen Chen連結 | https://arxiv.org/abs/2006.07989 [34] ShapeFlow: Learnable Deformations Among 3D Shapes作者 | Chiyu "Max" Jiang, Jingwei Huang, Andrea Tagliasacchi, Leonidas Guibas連結 | https://arxiv.org/abs/2006.07982 [35] Geodesic-HOF: 3D Reconstruction Without Cutting Corners作者 | Ziyun Wang, Eric A. Mitchell, Volkan Isler, Daniel D. Lee連結 | https://arxiv.org/abs/2006.07981 [36] Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization作者 | Junting Pan, Siyu Chen, Zheng Shou, Jing Shao, Hongsheng Li連結 | https://arxiv.org/abs/2006.07976 [37] Meta Approach to Data Augmentation Optimization作者 | Ryuichiro Hataya, Jan Zdenek, Kazuki Yoshizoe, Hideki Nakayama連結 | https://arxiv.org/abs/2006.07965 [38] Team RUC_AIM3 Technical Report at Activitynet 2020 Task 2: Exploring Sequential Events Detection for Dense Video Captioning作者 | Yuqing Song, Shizhe Chen, Yida Zhao, Qin Jin連結 | https://arxiv.org/abs/2006.07896 備註 | Winner solution in CVPR 2020 Activitynet Dense Video Captioning challenge[39] Optical Music Recognition: State of the Art and Major Challenges作者 | Elona Shatri, György Fazekas連結 | https://arxiv.org/abs/2006.07885 備註 | Author manuscript for TENOR 2020 conference. [40] FenceMask: A Data Augmentation Approach for Pre-extracted Image Features作者 | Pu Li, Xiangyang Li, Xiang Long連結 | https://arxiv.org/abs/2006.07877 [41] Explicitly Modeled Attention Maps for Image Classification作者 | Andong Tan, Duc Tam Nguyen, Maximilian Dax, Matthias Niessner, Thomas Brox連結 | https://arxiv.org/abs/2006.07872 [42] Cityscapes 3D: Dataset and Benchmark for 9 DoF Vehicle Detection作者 | Nils Gählert, Nicolas Jourdan, Marius Cordts, Uwe Franke, Joachim Denzler連結 | https://arxiv.org/abs/2006.07864 備註 | 2020 "Scalability in Autonomous Driving" CVPR Workshop[43] An adversarial learning algorithm for mitigating gender bias in face recognition作者 | Prithviraj Dhar, Joshua Gleason, Hossein Souri, Carlos D. Castillo, Rama Chellappa連結 | https://arxiv.org/abs/2006.07845 [44] A Generalized Asymmetric Dual-front Model for Active Contours and Image Segmentation作者 | Da~Chen, Jack Spencer, Jean-Marie Mirebeau, Ke Chen, Ming-Lei Shu, Laurent D. Cohen連結 | https://arxiv.org/abs/2006.07839 [45] Multi-Miner: Object-Adaptive Region Mining for Weakly-Supervised Semantic Segmentation作者 | Kuangqi Zhou, Qibin Hou, Zun Li, Jiashi Feng連結 | https://arxiv.org/abs/2006.07834 [46] On Saliency Maps and Adversarial Robustness作者 | Puneet Mangla, Vedant Singh, Vineeth N Balasubramanian連結 | https://arxiv.org/abs/2006.07828 備註 | Accepted at ECML-PKDD 2020[47] PCAAE: Principal Component Analysis Autoencoder for organising the latent space of generative networks作者 | Chi-Hieu Pham, Saïd Ladjal, Alasdair Newson連結 | https://arxiv.org/abs/2006.07827 備註 | Preprint with Appendix[48] Few-shot Object Detection on Remote Sensing Images作者 | Jingyu Deng, Xiang Li, Yi Fang連結 | https://arxiv.org/abs/2006.07826 [49] Working with scale: 2nd place solution to Product Detection in Densely Packed Scenes [Technical Report]連結 | https://arxiv.org/abs/2006.07825 [50] Adaptively Meshed Video Stabilization作者 | Minda Zhao, Qiang Ling連結 | https://arxiv.org/abs/2006.07820 [51] Alternating ConvLSTM: Learning Force Propagation with Alternate State Updates作者 | Congyue Deng, Tai-Jiang Mu, Shi-Min Hu連結 | https://arxiv.org/abs/2006.07818 [52] 2D Image Relighting with Image-to-Image Translation作者 | Paul Gafton, Erick Maraz連結 | https://arxiv.org/abs/2006.07816 [53] Disentanglement for Discriminative Visual Recognition連結 | https://arxiv.org/abs/2006.07810 備註 | Manuscript for book "Recognition and perception of images" Willy[54] ReLGAN: Generalization of Consistency for GAN with Disjoint Constraints and Relative Learning of Generative Processes for Multiple Transformation Learning連結 | https://arxiv.org/abs/2006.07809 [55] Relative Pose Estimation for Stereo Rolling Shutter Cameras作者 | Ke Wang, Bin Fan, Yuchao Dai連結 | https://arxiv.org/abs/2006.07807 備註 | Accepted by International Conference on Image Processing (ICIP 2020)[56] Geometry-Aware Instance Segmentation with Disparity Maps作者 | Cho-Ying Wu, Xiaoyan Hu, Michael Happold, Qiangeng Xu, Ulrich Neumann連結 | https://arxiv.org/abs/2006.07802 備註 | CVPR 2020 Workshop of Scalability in Autonomous Driving (WSAD). Please refer to WSAD site for details[57] Hyper RPCA: Joint Maximum Correntropy Criterion and Laplacian Scale Mixture Modeling On-the-Fly for Moving Object Detection作者 | Zerui Shao, Yifei Pu, Jiliu Zhou, Bihan Wen, Yi Zhang連結 | https://arxiv.org/abs/2006.07795 [58] Generative 3D Part Assembly via Dynamic Graph Learning作者 | Jialei Huang, Guanqi Zhan, Qingnan Fan, Kaichun Mo, Lin Shao, Baoquan Chen, Leonidas Guibas, Hao Dong連結 | https://arxiv.org/abs/2006.07793 [59] PrimA6D: Rotational Primitive Reconstruction for Enhanced and Robust 6D Pose Estimation作者 | MyungHwan Jeon, Ayoung Kim連結 | https://arxiv.org/abs/2006.07789 [60] Cascaded deep monocular 3D human pose estimation with evolutionary training data作者 | Shichao Li, Lei Ke, Kevin Pratama, Yu-Wing Tai, Chi-Keung Tang, Kwang-Ting Cheng連結 | https://arxiv.org/abs/2006.07778 [61] Domain Adaptation and Image Classification via Deep Conditional Adaptation Network作者 | Pengfei Ge, Chuan-Xian Ren, Dao-Qing Dai, Hong Yan連結 | https://arxiv.org/abs/2006.07776 [62] Recurrent Distillation based Crowd Counting連結 | https://arxiv.org/abs/2006.07755 [63] 3D Reconstruction of Novel Object Shapes from Single Images作者 | Anh Thai, Stefan Stojanov, Vijay Upadhya, James M. Rehg連結 | https://arxiv.org/abs/2006.07752 備註 | First two authors contributed equally[64] Exploiting the ConvLSTM: Human Action Recognition using Raw Depth Video-Based Recurrent Neural Networks作者 | Adrian Sanchez-Caballero, David Fuentes-Jimenez, Cristina Losada-Gutierrez連結 | https://arxiv.org/abs/2006.07744 [65] 3DFCNN: Real-Time Action Recognition using 3D Deep Neural Networks with Raw Depth Information作者 | Adrian Sanchez-Caballero, Sergio de López-Diz, David Fuentes-Jimenez, Cristina Losada-Gutiérrez, Marta Marrón-Romera, David Casillas-Perez, Mohammad Ibrahim Sarker連結 | https://arxiv.org/abs/2006.07743 作者 | Omid Hosseini Jafari, Carsten Rother連結 | https://arxiv.org/abs/2006.07742 [67] V2E: From video frames to realistic DVS event camera streams作者 | Tobi Delbruck, Yuhuang Hu, Zhe He連結 | https://arxiv.org/abs/2006.07722 [68] Sensorless Freehand 3D Ultrasound Reconstruction via Deep Contextual Learning作者 | Hengtao Guo, Sheng Xu, Bradford Wood, Pingkun Yan連結 | https://arxiv.org/abs/2006.07694 備註 | Provisionally accepted by MICCAI 2020[69] Uncertainty-aware Score Distribution Learning for Action Quality Assessment作者 | Yansong Tang, Zanlin Ni, Jiahuan Zhou, Danyang Zhang, Jiwen Lu, Ying Wu, Jie Zhou連結 | https://arxiv.org/abs/2006.07665 [70] Convolutional Generation of Textured 3D Meshes作者 | Dario Pavllo, Graham Spinks, Thomas Hofmann, Marie-Francine Moens, Aurelien Lucchi連結 | https://arxiv.org/abs/2006.07660 [71] DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms作者 | Hua Qi, Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Wei Feng, Yang Liu, Jianjun Zhao連結 | https://arxiv.org/abs/2006.07634 [72] Equivariant Neural Rendering作者 | Emilien Dupont, Miguel Angel Bautista, Alex Colburn, Aditya Sankar, Carlos Guestrin, Josh Susskind, Qi Shan連結 | https://arxiv.org/abs/2006.07630 備註 | ICML 2020 camera ready[73] DTG-Net: Differentiated Teachers Guided Self-Supervised Video Action Recognition作者 | Ziming Liu, Guangyu Gao, A. K. Qin, Jinyang Li連結 | https://arxiv.org/abs/2006.07609 [74] HRDNet: High-resolution Detection Network for Small Objects作者 | Ziming Liu, Guangyu Gao, Lin Sun, Zhiyuan Fang連結 | https://arxiv.org/abs/2006.07607 [75] Faces à la Carte: Text-to-Face Generation via Attribute Disentanglement作者 | Tianren Wang, Teng Zhang, Brian Lovell連結 | https://arxiv.org/abs/2006.07606 [76] Dynamic gesture retrieval: searching videos by human pose sequence連結 | https://arxiv.org/abs/2006.07604 [77] NoPeopleAllowed: The Three-Step Approach to Weakly Supervised Semantic Segmentation作者 | Mariia Dobko, Ostap Viniavskyi, Oles Dobosevych連結 | https://arxiv.org/abs/2006.07601 備註 | This short-paper was submitted to Learning from Imperfect Data workshop at CVPR 2020[78] Attribute-aware Identity-hard Triplet Loss for Video-based Person Re-identification作者 | Zhiyuan Chen, Annan Li, Shilu Jiang, Yunhong Wang連結 | https://arxiv.org/abs/2006.07597 [79] Semantic-driven Colorization作者 | Man M. Ho, Lu Zhang, TU Ilmenau, Jinjia Zhou連結 | https://arxiv.org/abs/2006.07587 項目連結 | https://minhmanho.github.io/semantic-driven_colorization[80] Learning from the Scene and Borrowing from the Rich: Tackling the Long Tail in Scene Graph Generation作者 | Tao He, Lianli Gao, Jingkuan Song, Jianfei Cai, Yuan-Fang Li連結 | https://arxiv.org/abs/2006.07585 [81] Mitigating Face Recognition Bias via Group Adaptive Classifier作者 | Sixue Gong, Xiaoming Liu, Anil K. Jain連結 | https://arxiv.org/abs/2006.07576 [82] Unbiased Auxiliary Classifier GANs with MINE作者 | Ligong Han, Anastasis Stathopoulos, Tao Xue, Dimitris Metaxas連結 | https://arxiv.org/abs/2006.07567 備註 | Accepted at CVPRW-20[83] Accurate Anchor Free Tracking作者 | Shengyun Peng, Yunxuan Yu, Kun Wang, Lei He連結 | https://arxiv.org/abs/2006.07560 [84] GAN Memory with No Forgetting作者 | Yulai Cong, Miaoyun Zhao, Jianqiao Li, Sijia Wang, Lawrence Carin連結 | https://arxiv.org/abs/2006.07543 [85] FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction作者 | Yihao Huang, Felix Juefei-Xu, Run Wang, Qing Guo, Lei Ma, Xiaofei Xie, Jianwen Li, Weikai Miao, Yang Liu, Geguang Pu連結 | https://arxiv.org/abs/2006.07533 [86] CBR-Net: Cascade Boundary Refinement Network for Action Detection: Submission to ActivityNet Challenge 2020 (Task 1)作者 | Xiang Wang, Baiteng Ma, Zhiwu Qing, Yongpeng Sang, Changxin Gao, Shiwei Zhang, Nong Sang連結 | https://arxiv.org/abs/2006.07526 備註 | ActivityNet Challenge 2020 Temporal Action Localization (Task 1) Champion Solution (Rank 1)[87] Self-Supervised Discovery of Anatomical Shape Landmarks作者 | Riddhish Bhalodia, Ladislav Kavan, Ross Whitaker連結 | https://arxiv.org/abs/2006.07525 備註 | Early accept at MICCAI 2020[88] Temporal Fusion Network for Temporal Action Localization:Submission to ActivityNet Challenge 2020 (Task E)作者 | Zhiwu Qing, Xiang Wang, Yongpeng Sang, Changxin Gao, Shiwei Zhang, Nong Sang連結 | https://arxiv.org/abs/2006.07520 備註 | To appear on CVPR 2020 HACS Workshop (Rank 1st)[89] Weakly-supervised Any-shot Object Detection作者 | Siddhesh Khandelwal, Raghav Goyal, Leonid Sigal連結 | https://arxiv.org/abs/2006.07502 [90] Multi-Modal Fingerprint Presentation Attack Detection: Evaluation On A New Dataset作者 | Leonidas Spinoulas, Hengameh Mirzaalian, Mohamed Hussein, Wael AbdAlmageed連結 | https://arxiv.org/abs/2006.07498 [91] OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold作者 | Mohamed Yousef, Tom E. Bishop連結 | https://arxiv.org/abs/2006.07491 備註 | Accepted to CVPR 2020[92] Multispectral Biometrics System Framework: Application to Presentation Attack Detection作者 | Leonidas Spinoulas, Mohamed Hussein, David Geissbühler, Joe Mathai, Oswin G.Almeida, Guillaume Clivaz, Sébastien Marcel, Wael AbdAlmageed連結 | https://arxiv.org/abs/2006.07489 [93] Early Blindness Detection Based on Retinal Images Using Ensemble Learning作者 | Niloy Sikder, Md. Sanaullah Chowdhury, Abu Shamim Mohammad Arif, Abdullah-Al Nahid連結 | https://arxiv.org/abs/2006.07475 備註 | 22nd International Conference of Computer and Information Technology (ICCIT), 18-20 December, 2019[94] Learning-to-Learn Personalised Human Activity Recognition Models作者 | Anjana Wijekoon, Nirmalie Wiratunga連結 | https://arxiv.org/abs/2006.07472 [95] Defending against GAN-based Deepfake Attacks via Transformation-aware Adversarial Faces作者 | Chaofei Yang, Lei Ding, Yiran Chen, Hai Li連結 | https://arxiv.org/abs/2006.07421 [96] The DeepFake Detection Challenge Dataset作者 | Brian Dolhansky, Joanna Bitton, Ben Pflaum, Jikuo Lu, Russ Howes, Menglin Wang, Cristian Canton Ferrer連結 | https://arxiv.org/abs/2006.07397 [97] Spectral DiffuserCam: lensless snapshot hyperspectral imaging with a spectral filter array作者 | Kristina Monakhova, Kyrollos Yanny, Neerja Aggarwal, Laura Waller連結 | https://arxiv.org/abs/2006.08565 [98] Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction作者 | Yaodong Yu, Kwan Ho Ryan Chan, Chong You, Chaobing Song, Yi Ma連結 | https://arxiv.org/abs/2006.08558 [99] Efficient Black-Box Adversarial Attack Guided by the Distribution of Adversarial Perturbations作者 | Yan Feng, Baoyuan Wu, Yanbo Fan, Zhifeng Li, Shutao Xia連結 | https://arxiv.org/abs/2006.08538 [100] Improved Conditional Flow Models for Molecule to Image Synthesis作者 | Karren Yang, Samuel Goldman, Wengong Jin, Alex Lu, Regina Barzilay, Tommi Jaakkola, Caroline Uhler連結 | https://arxiv.org/abs/2006.08532 [101] The Limit of the Batch Size作者 | Yang You, Yuhui Wang, Huan Zhang, Zhao Zhang, James Demmel, Cho-Jui Hsieh連結 | https://arxiv.org/abs/2006.08517 [102] APQ: Joint Search for Network Architecture, Pruning and Quantization Policy作者 | Tianzhe Wang, Kuan Wang, Han Cai, Ji Lin, Zhijian Liu, Song Han連結 | https://arxiv.org/abs/2006.08509 備註 | Accepted by CVPR 2020[103] Deep learning mediated single time-point image-based prediction of embryo developmental outcome at the cleavage stage作者 | Manoj Kumar Kanakasabapathy, Prudhvi Thirumalaraju, Charles L Bormann, Raghav Gupta, Rohan Pooniwala, Hemanth Kandula, Irene Souter, Irene Dimitriadis, Hadi Shafiee連結 | https://arxiv.org/abs/2006.08346 [104] A Dataset and Benchmarks for Multimedia Social Analysis作者 | Bofan Xue, David Chan, John Canny連結 | https://arxiv.org/abs/2006.08335 備註 | Published as a workshop paper at "Multimodality Learning" (CVPR 2020)[105] Differentiable Neural Architecture Transformation for Reproducible Architecture Improvement作者 | Do-Guk Kim, Heung-Chang Lee連結 | https://arxiv.org/abs/2006.08231 [106] Slowing Down the Weight Norm Increase in Momentum-based Optimizers作者 | Byeongho Heo, Sanghyuk Chun, Seong Joon Oh, Dongyoon Han, Sangdoo Yun, Youngjung Uh, Jung-Woo Ha連結 | https://arxiv.org/abs/2006.08217 備註 | First two authors contributed equally[107] Dissimilarity Mixture Autoencoder for Deep Clustering作者 | Juan S. Lara, Fabio A. González連結 | https://arxiv.org/abs/2006.08177 [108] Emotion Recognition in Audio and Video Using Deep Neural Networks作者 | Mandeep Singh, Yuan Fang連結 | https://arxiv.org/abs/2006.08129 [109] Generalized Adversarially Learned Inference作者 | Yatin Dandi, Homanga Bharadhwaj, Abhishek Kumar, Piyush Rai連結 | https://arxiv.org/abs/2006.08089 [110] CompressNet: Generative Compression at Extremely Low Bitrates作者 | Suraj Kiran Raman (1), Aditya Ramesh (1), Vijayakrishna Naganoor (1), Shubham Dash (1), Giridharan Kumaravelu (1), Honglak Lee (1) ((1) University of Michigan, Ann Arbor)連結 | https://arxiv.org/abs/2006.08003 [111] Leveraging Multimodal Behavioral Analytics for Automated Job Interview Performance Assessment and Feedback作者 | Anumeha Agrawal, Rosa Anil George, Selvan Sunitha Ravi, Sowmya Kamath S, Anand Kumar M連結 | https://arxiv.org/abs/2006.07909 [112] Continual General Chunking Problem and SyncMap作者 | Danilo Vasconcellos Vargas, Toshitake Asabuki連結 | https://arxiv.org/abs/2006.07853 [113] Structural Autoencoders Improve Representations for Generation and Transfer作者 | Felix Leeb, Yashas Annadani, Stefan Bauer, Bernhard Scholkopf連結 | https://arxiv.org/abs/2006.07796 備註 | Submitted to NeurIPS 2020[114] DeeperGCN: All You Need to Train Deeper GCNs作者 | Guohao Li, Chenxin Xiong, Ali Thabet, Bernard Ghanem連結 | https://arxiv.org/abs/2006.07739 項目連結 | https://www.deepgcns.org/備註 | This work is still working in process. More results will be updated in the future version. [115] Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning作者 | Jean-Bastien Grill, Florian Strub, Florent Altché, et al.連結 | https://arxiv.org/abs/2006.07733 [116] RoadNet-RT: High Throughput CNN Architecture and SoC Design for Real-Time Road Segmentation作者 | Lin Bai, Yecheng Lyu, Xinming Huang連結 | https://arxiv.org/abs/2006.07644 備註 | has been submitted for peer review[117] Adversarial Self-Supervised Contrastive Learning作者 | Minseon Kim, Jihoon Tack, Sung Ju Hwang連結 | https://arxiv.org/abs/2006.07589 [118] Sparse Separable Nonnegative Matrix Factorization作者 | Nicolas Nadisic, Arnaud Vandaele, Jeremy E. Cohen, Nicolas Gillis連結 | https://arxiv.org/abs/2006.07553 備註 | accepted in ECML 2020[119] Rethinking the Value of Labels for Improving Class-Imbalanced Learning連結 | https://arxiv.org/abs/2006.07529 [120] TURB-Rot. A large database of 3d and 2d snapshots from turbulent rotating flows作者 | L. Biferale, F. Bonaccorso, M. Buzzicotti, P. Clark di Leoni連結 | https://arxiv.org/abs/2006.07469 [121] BI-MAML: Balanced Incremental Approach for Meta Learning作者 | Yang Zheng, Jinlin Xiang, Kun Su, Eli Shlizerman連結 | https://arxiv.org/abs/2006.07412 項目視頻 | https://youtu.be/4qlb-iG5SFo[122] Robust Baggage Detection and Classification Based on Local Tri-directional Pattern作者 | Shahbano, Muhammad Abdullah, Kashif Inayat連結 | https://arxiv.org/abs/2006.07345 [123] GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning作者 | Xinshuo Weng, Yongxin Wang, Yunze Man, Kris Kitani連結 | https://arxiv.org/abs/2006.07327 作者主頁 | http://www.xinshuoweng.com/[124] Multiple-Vehicle Tracking in the Highway Using Appearance Model and Visual Object Tracking作者 | Fateme Bafghi, Bijan Shoushtarian連結 | https://arxiv.org/abs/2006.07309 [125] Pitfalls of the Gram Loss for Neural Texture Synthesis in Light of Deep Feature Histograms作者 | Eric Heitz, Kenneth Vanhoey, Thomas Chambon, Laurent Belcour連結 | https://arxiv.org/abs/2006.07229 [126] Local-Area-Learning Network: Meaningful Local Areas for Efficient Point Cloud Analysis作者 | Qendrim Bytyqi, Nicola Wolpert, Elmar Schömer連結 | https://arxiv.org/abs/2006.07226 [127] Branch-Cooperative OSNet for Person Re-Identification作者 | Lei Zhang, Xiaofu Wu, Suofei Zhang, Zirui Yin連結 | https://arxiv.org/abs/2006.07206 [128] Video Understanding as Machine Translation作者 | Bruno Korbar, Fabio Petroni, Rohit Girdhar, Lorenzo Torresani連結 | https://arxiv.org/abs/2006.07203 [129] ESAD: Endoscopic Surgeon Action Detection Dataset作者 | Vivek Singh Bawa, Gurkirt Singh, Francis KapingA, InnaSkarga-Bandurova, Alice Leporini, Carmela Landolfo, Armando Stabile, Francesco Setti, Riccardo Muradore, Elettra Oleari, Fabio Cuzzolin連結 | https://arxiv.org/abs/2006.07164 備註 | In context of SARAS ESAD Challeneg at MIDL[130] Are we done with ImageNet?作者 | Lucas Beyer, Olivier J. Hénaff, Alexander Kolesnikov, Xiaohua Zhai, Aäron van den Oord連結 | https://arxiv.org/abs/2006.07159 備註 | All five authors contributed equally. New labels at https://github.com/google-research/reassessed-imagenet[131] Attribute analysis with synthetic dataset for person re-identification作者 | Suncheng Xiang, Yuzhuo Fu, Guanjie You, Ting Liu連結 | https://arxiv.org/abs/2006.07139 [132] Knowledge Distillation Meets Self-Supervision作者 | Guodong Xu, Ziwei Liu, Xiaoxiao Li, Chen Change Loy連結 | https://arxiv.org/abs/2006.07114 項目連結 | https://github.com/xuguodong03/SSKD[133] A Face Preprocessing Approach for Improved DeepFake Detection作者 | Polychronis Charitidis, Giorgos Kordopatis-Zilos, Symeon Papadopoulos, Ioannis Kompatsiaris連結 | https://arxiv.org/abs/2006.07084 [134] Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences作者 | Marissa A. Weis, Kashyap Chitta, Yash Sharma, Wieland Brendel, Matthias Bethge, Andreas Geiger, Alexander S. Ecker連結 | https://arxiv.org/abs/2006.07034 [135] Rethinking Sampling in 3D Point Cloud Generative Adversarial Networks作者 | He Wang, Zetian Jiang, Li Yi, Kaichun Mo, Hao Su, Leonidas J. Guibas連結 | https://arxiv.org/abs/2006.07029 [136] Background Modeling via Uncertainty Estimation for Weakly-supervised Action Localization作者 | Pilhyeon Lee, Jinglu Wang, Yan Lu, Hyeran Byun連結 | https://arxiv.org/abs/2006.07006 [137] Quantum Robust Fitting作者 | Tat-Jun Chin, David Suter, Shin-Fang Chng, James Quach連結 | https://arxiv.org/abs/2006.06986 [138] Towards Robust Pattern Recognition: A Review作者 | Xu-Yao Zhang, Cheng-Lin Liu, Ching Y. Suen連結 | https://arxiv.org/abs/2006.06976 [139] Multi Layer Neural Networks as Replacement for Pooling Operations作者 | Wolfgang Fuhl, Enkelejda Kasneci連結 | https://arxiv.org/abs/2006.06969 [140] The eyes know it: FakeET -- An Eye-tracking Database to Understand Deepfake Perception作者 | Parul Gupta, Komal Chugh, Abhinav Dhall, Ramanathan Subramanian連結 | https://arxiv.org/abs/2006.06961 [141] Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?作者 | Shen Yan, Yu Zheng, Wei Ao, Xiao Zeng, Mi Zhang連結 | https://arxiv.org/abs/2006.06936 [142] Iterate & Cluster: Iterative Semi-Supervised Action Recognition作者 | Jingyuan Li, Eli Shlizerman連結 | https://arxiv.org/abs/2006.06911 項目視頻 | https://www.youtube.com/watch?v=ewuoz2tt73E[143] SemifreddoNets: Partially Frozen Neural Networks for Efficient Computer Vision Systems作者 | Leo F Isikdogan, Bhavin V Nayak, Chyuan-Tyng Wu, Joao Peralta Moreira, Sushma Rao, Gilad Michael連結 | https://arxiv.org/abs/2006.06888 [144] Rethinking Pre-training and Self-training作者 | Barret Zoph, Golnaz Ghiasi, Tsung-Yi Lin, Yin Cui, Hanxiao Liu, Ekin D. Cubuk, Quoc V. Le連結 | https://arxiv.org/abs/2006.06882 [145] Feudal Steering: Hierarchical Learning for Steering Angle Prediction作者 | Faith Johnson, Kristin Dana連結 | https://arxiv.org/abs/2006.06869 備註 | InThe IEEE/CVFConference on Computer Vision and Pattern Recognition(CVPR) Workshops, June 2020[146] SegNBDT: Visual Decision Rules for Segmentation作者 | Alvin Wan, Daniel Ho, Younjin Song, Henk Tillman, Sarah Adel Bargal, Joseph E. Gonzalez連結 | https://arxiv.org/abs/2006.06868 [147] On Improving the Generalization of Face Recognition in the Presence of Occlusions作者 | Xiang Xu, Nikolaos Sarafianos, Ioannis A. Kakadiaris連結 | https://arxiv.org/abs/2006.06787 [148] On Improving Temporal Consistency for Online Face Liveness Detection作者 | Xiang Xu, Yuanjun Xiong, Wei Xia連結 | https://arxiv.org/abs/2006.06756 [149] PRGFlow: Benchmarking SWAP-Aware Unified Deep Visual Inertial Odometry作者 | Nitin J. Sanket, Chahat Deep Singh, Cornelia Fermüller, Yiannis Aloimonos連結 | https://arxiv.org/abs/2006.06753 [150] An Unsupervised Information-Theoretic Perceptual Quality Metric作者 | Sangnie Bhardwaj, Ian Fischer, Johannes Ballé, Troy Chinen連結 | https://arxiv.org/abs/2006.06752 備註 | Submitted to the 34th Conference on Neural Information Processing Systems (NeurIPS 2020)[151] Deep Convolutional Likelihood Particle Filter for Visual Tracking作者 | Reza Jalil Mozhdehi, Henry Medeiros連結 | https://arxiv.org/abs/2006.06746 備註 | Accepted in Transactions on Computational Science & Computational Intelligence[152] Gaze estimation problem tackled through synthetic images作者 | Gonzalo Garde, Andoni Larumbe-Bergera, Beno卯t Bossavit, Rafael Cabeza, Sonia Porta, Arantxa Villanueva連結 | https://arxiv.org/abs/2006.06740 論文連結 | https://dl.acm.org/doi/abs/10.1145/3379156.3391368備註 | ETRA '20 Short Papers: ACM Symposium on Eye Tracking Research and Applications; June 2020; Article No.: 16; Pages 1 to 5[153] Training Generative Adversarial Networks with Limited Data作者 | Tero Karras, Miika Aittala, Janne Hellsten, Samuli Laine, Jaakko Lehtinen, Timo Aila連結 | https://arxiv.org/abs/2006.06676 [154] Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis作者 | Ye Yuan, Kris Kitani連結 | https://arxiv.org/abs/2006.07364 項目視頻 | https://youtu.be/XuzH1u78o1Y[155] CPR: Classifier-Projection Regularization for Continual Learning作者 | Sungmin Cha, Hsiang Hsu, Flavio P. Calmon, Taesup Moon連結 | https://arxiv.org/abs/2006.07326 [156] FedGAN: Federated Generative Adversarial Networks for Distributed Data作者 | Mohammad Rasouli, Tao Sun, Ram Rajagopal連結 | https://arxiv.org/abs/2006.07228 [157] Sparse and Continuous Attention Mechanisms作者 | André F. T. Martins, Marcos Treviso, António Farinhas, Vlad Niculae, Mário A. T. Figueiredo, Pedro M. Q. Aguiar連結 | https://arxiv.org/abs/2006.07214 [158] HMIC: Hierarchical Medical Image Classification, A Deep Learning Approach作者 | Kamran Kowsari, Rasoul Sali, Lubaina Ehsan, William Adorno, Asad Ali, Sean Moore, Beatrice Amadi, Paul Kelly, Sana Syed, Donald Brown連結 | https://arxiv.org/abs/2006.07187 [159] Move-to-Data: A new Continual Learning approach with Deep CNNs, Application for image-class recognition作者 | Miltiadis Poursanidis (LaBRI), Jenny Benois-Pineau (LaBRI), Akka Zemmari (LaBRI), Boris Mansenca (LaBRI), Aymar de Rugy (INCIA)連結 | https://arxiv.org/abs/2006.07152 [160] Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimation作者 | Masahiro Kato, Takeshi Teshima連結 | https://arxiv.org/abs/2006.06979 [161] Early Detection of Retinopathy of Prematurity (ROP) in Retinal Fundus Images Via Convolutional Neural Networks作者 | Xin Guo, Yusuke Kikuchi, Guan Wang, Jinglin Yi, Qiong Zou, Rui Zhou連結 | https://arxiv.org/abs/2006.06968 [162] LSSL: Longitudinal Self-Supervised Learning作者 | Qingyu Zhao, Zixuan Liu, Ehsan Adeli, Kilian M. Pohl連結 | https://arxiv.org/abs/2006.06930 [163] Potential Field Guided Actor-Critic Reinforcement Learning連結 | https://arxiv.org/abs/2006.06923 [164] Online Sequential Extreme Learning Machines: Features Combined From Hundreds of Midlayers作者 | Chandra Swarathesh Addanki連結 | https://arxiv.org/abs/2006.06893 [165] Reintroducing Straight-Through Estimators as Principled Methods for Stochastic Binary Networks作者 | Viktor Yanush, Alexander Shekhovtsov, Dmitry Molchanov, Dmitry Vetrov連結 | https://arxiv.org/abs/2006.06880 [166] Combining the band-limited parameterization and Semi-Lagrangian Runge--Kutta integration for efficient PDE-constrained LDDMM連結 | https://arxiv.org/abs/2006.06823 [167] Automated Identification of Thoracic Pathology from Chest Radiographs with Enhanced Training Pipeline作者 | Adora M. DSouza, Anas Z. Abidin, Axel Wismüller連結 | https://arxiv.org/abs/2006.06805 [168] Multigrid-in-Channels Architectures for Wide Convolutional Neural Networks作者 | Jonathan Ephrath, Lars Ruthotto, Eran Treister連結 | https://arxiv.org/abs/2006.06799 [169] One Ring to Rule Them All: Certifiably Robust Geometric Perception with Outliers作者 | Heng Yang, Luca Carlone連結 | https://arxiv.org/abs/2006.06769 [170] Data Driven Prediction Architecture for Autonomous Driving and its Application on Apollo Platform作者 | Kecheng Xu, Xiangquan Xiao, Jinghao Miao, Qi Luo連結 | https://arxiv.org/abs/2006.06715 備註 | Accepted by the 31st IEEE Intelligent Vehicles Symposium (2020)