每日论文速递：计算机视觉相关（2月4日更新版）

计算机视觉（2 月4日更新版）

[1] YOLOff: You Only Learn Offsets for robust 6DoF object pose estimation

作者 | Mathieu Gonzalez, Amine Kacete, Albert Murienne, Eric Marchand

链接 | https://arxiv.org/pdf/2002.00911

[2] EGO-CH: Dataset and Fundamental Tasks for Visitors BehavioralUnderstanding using Egocentric Vision

作者 | Francesco Ragusa, Antonino Furnari, Sebastiano Battiato, Giovanni Signorello, Giovanni Maria Farinella

链接 | https://arxiv.org/pdf/2002.00899

备注 | Pattern Recognition Letters 2020

[3] Effect of top-down connections in Hierarchical Sparse Coding

作者 | Victor Boutin, Angelo Franciosini, Franck Ruffier, Laurent Perrinet

链接 | https://arxiv.org/pdf/2002.00892

[4] Adversarial-based neural network for affect estimations in the wild

作者 | Decky Aspandi, Adria Mallol-Ragolta, Bj枚rn Schuller, Xavier Binefa

链接 | https://arxiv.org/pdf/2002.00883

备注 | Paper for FG 2020 Affect Challenge

[5] Deep Self-Supervised Representation Learning for Free-Hand Sketch

作者 | Peng Xu, Zeyu Song, Qiyue Yin, Yi-Zhe Song, Liang Wang

链接 | https://arxiv.org/pdf/2002.00867

[6] Learning Extremal Representations with Deep Archetypal Analysis

作者 | Sebastian Mathias Keller, Maxim Samarin, Fabricio Arend Torres, Mario Wieser, Volker Roth

链接 | https://arxiv.org/pdf/2002.00815

备注 | Under review for publication at the International Journal of Computer Vision (IJCV). Extended version of our GCPR2019 paper "Deep Archetypal Analysis"

[7] Syn2Real: Forgery Classification via Unsupervised Domain Adaptation

作者 | Akash Kumar, Arnav Bhavasar

链接 | https://arxiv.org/pdf/2002.00807

[8] Towards Accurate Vehicle Behaviour Classification With Multi-Relational Graph Convolutional Networks

作者 | Sravan Mylavarapu, Mahtab Sandhu, Priyesh Vijayan, K Madhava Krishna, Balaraman Ravindran, Anoop Namboodiri

链接 | https://arxiv.org/pdf/2002.00786

[9] Hide-and-Tell: Learning to Bridge Photo Streams for Visual Storytelling

作者 | Yunjae Jung, Dahun Kim, Sanghyun Woo, Kyungsu Kim, Sungjin Kim, In So Kweon

链接 | https://arxiv.org/pdf/2002.00774

备注 | AAAI 2020 paper

[10] Modeling the Background for Incremental Learning in Semantic Segmentation

作者 | Fabio Cermelli, Massimiliano Mancini, Samuel Rota Bulò, Elisa Ricci, Barbara Caputo

链接 | https://arxiv.org/pdf/2002.00718

[11] A Novel Incremental Cross-Modal Hashing Approach

作者 | Devraj Mandal, Soma Biswas

链接 | https://arxiv.org/pdf/2002.00677

[12] Single-Stage Object Detection from Top-View Grid Maps on Custom Sensor Setups

作者 | Sascha Wirges, Shuxiao Ding, Christoph Stiller

链接 | https://arxiv.org/pdf/2002.00667

[13] Pix2Pix-based Stain-to-Stain Translation: A Solution for Robust Stain Normalization in Histopathology Images Analysis

作者 | Pegah Salehi, Abdolah Chalechale

链接 | https://arxiv.org/pdf/2002.00647

备注 | The 11th Iranian and the first International Conference on Machine Vision and Image Processing (MVIP 2020)

[14] Classification of Chest Diseases using Wavelet Transforms and Transfer Learning

作者 | Ahmed Rasheed, Muhammad Shahzad Younis, Muhammad Bilal, Maha Rasheed

链接 | https://arxiv.org/pdf/2002.00625

备注 | Presented in International Conference On Medical Imaging And Computer-Aided Diagnosis (MICAD 2020), proceeding will be published with Springer in their "Lecture Notes in Electrical Engineering (LNEE)" (ISSN: 1876-1100)

[15] Regularizers for Single-step Adversarial Training

作者 | B.S. Vivek, R. Venkatesh Babu

链接 | https://arxiv.org/pdf/2002.00614

[16] Facial Affect Recognition in the Wild Using Multi-Task Learning Convolutional Network

作者 | Zihang Zhang, Jianping Gu

链接 | https://arxiv.org/pdf/2002.00606

备注 | submitted to ABAW challenge in FG2020

[17] Super-resolution of multispectral satellite images using convolutional neural networks

作者 | M. U. Müller, N. Ekhtiari, R. M. Almeida, C. Rieke

链接 | https://arxiv.org/pdf/2002.00580

备注 | Submitted to XXIV ISPRS Congress, 14-20 June 2020, Nice, France

[18] Unsupervised Domain Adaptive Object Detection using Forward-Backward Cyclic Adaptation

作者 | Siqi Yang, Lin Wu, Arnold Wiliem, Brian C. Lovell

链接 | https://arxiv.org/pdf/2002.00575

[19] DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data

作者 | Wei Yin, Xinlong Wang, Chunhua Shen, Yifan Liu, Zhi Tian, Songcen Xu, Changming Sun, Dou Renyin

链接 | https://arxiv.org/pdf/2002.00569

[20] Widening and Squeezing: Towards Accurate and Efficient QNNs

作者 | Chuanjian Liu, Kai Han, Yunhe Wang, Hanting Chen, Chunjing Xu, Qi Tian

链接 | https://arxiv.org/pdf/2002.00555

备注 | Tech report

[21] Towards High Performance Human Keypoint Detection

作者 | Jing Zhang, Zhe Chen, Dacheng Tao

链接 | https://arxiv.org/pdf/2002.00537

[22] Automatic Pruning for Quantized Neural Networks

作者 | Luis Guerra, Bohan Zhuang, Ian Reid, Tom Drummond

链接 | https://arxiv.org/pdf/2002.00523

[23] Novelty Detection via Non-Adversarial Generative Network

作者 | Chengwei Chen, Wang Yuan, Yuan Xie, Yanyun Qu, Yiqing Tao, Haichuan Song, Lizhuang Ma

链接 | https://arxiv.org/pdf/2002.00522

[24] Neural Sign Language Translation by Learning Tokenization

作者 | Alptekin Orbay, Lale Akarun

链接 | https://arxiv.org/pdf/2002.00479

备注 | Face & Gesture 2020

[25] Effect of Analysis Window and Feature Selection on Classification of Hand Movements Using EMG Signal

作者 | Asad Ullah, Sarwan Ali, Imdadullah Khan, Muhammad Asad Khan, Safiullah Faizullah

链接 | https://arxiv.org/pdf/2002.00461

[26] Regularizing Reasons for Outfit Evaluation with Gradient Penalty

作者 | Xingxing Zou, Zhizhong Li, Ke Bai, Dahua Lin, Waikeung Wong

链接 | https://arxiv.org/pdf/2002.00460

[27] 3D Shape Segmentation with Geometric Deep Learning

作者 | Davide Boscaini, Fabio Poiesi

链接 | https://arxiv.org/pdf/2002.00397

[28] A Novel Graph based Trajectory Predictor with Pseudo Oracle

作者 | Biao Yang, Guocheng Yan, Pin Wang, Chingyao Chan, Xiaofeng Liu, Yang Chen

链接 | https://arxiv.org/pdf/2002.00391

[29] Interpreting video features: a comparison of 3D convolutional networks and convolutional LSTM networks

作者 | Joonatan Mänttäri, Sofia Broomé, John Folkesson, Hedvig Kjellström

链接 | https://arxiv.org/pdf/2002.00367

[30] Adversarial Generation of Continuous Implicit Shape Representations

作者 | Marian Kleineberg, Matthias Fey, Frank Weichert

链接 | https://arxiv.org/pdf/2002.00349

[31] 3D Object Detection on Point Clouds using Local Ground-aware and Adaptive Representation of scenes' surface

作者 | Arun CS Kumar, Disha Ahuja, Ashwath Aithal

链接 | https://arxiv.org/pdf/2002.00336

[32] Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning

作者 | Mahesh Kumar Krishna Reddy, Mohammad Hossain, Mrigank Rochan, Yang Wang

链接 | https://arxiv.org/pdf/2002.00264

备注 | Accepted to WACV 2020

[33] Foreground object segmentation in RGB-D data implemented on GPU

作者 | Piotr Janus, Tomasz Kryjak, Marek Gorgon

链接 | https://arxiv.org/pdf/2002.00250

备注 | 12 pages, 4 figures, submitted to KKA 2020 conference

[34] Rigidity Properties of the Blum Medial Axis

作者 | James Damon

链接 | https://arxiv.org/pdf/2002.00241

[35] Domain segmentation and adjustment for generalized zero-shot learning

作者 | Xinsheng Wang, Shanmin Pang, Jihua Zhu

链接 | https://arxiv.org/pdf/2002.00226

[36] Large Hole Image Inpainting With Compress-Decompression Network

作者 | Zhenghang Wu, Yidong Cui

链接 | https://arxiv.org/pdf/2002.00199

[37] Deeply Activated Salient Region for Instance Search

作者 | Hui-Chu Xiao, Wan-Lei Zhao

链接 | https://arxiv.org/pdf/2002.00185

[38] AdvJND: Generating Adversarial Examples with Just Noticeable Difference