计算机视觉每日论文速递[08.28]
同步公众号(arXiv每日论文速递)，回复'search 关键词'查询相关最新论文。
[检测分类相关]：
【1】 Fingerprint Presentation Attack Detection Based on Local Features Encoding for Unknown Attacks
作者： Lázaro J. González-Soler, Christoph Busch
链接：https://arxiv.org/abs/1908.10163
【2】 Dual Directed Capsule Network for Very Low Resolution Image Recognition
作者： Maneet Singh, Mayank Vatsa
备注：Accepted in the International Conference on Computer Vision (ICCV) 2019
链接：https://arxiv.org/abs/1908.10027
【3】 Unsupervised Deep Feature Transfer for Low Resolution Image Classification
作者： Yuanwei Wu, Guanghui Wang
备注：4 pages, accepted to ICCV19 Workshop and Challenge on Real-World Recognition from Low-Quality Images and Videos
链接：https://arxiv.org/abs/1908.10012
【4】 Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning
作者： Xugong Qin, Weiping Wang
备注：Accepted by ICDAR 2019
链接：https://arxiv.org/abs/1908.09990
【5】 Key Protected Classification for Collaborative Learning
作者： Mert Bülent Sarıyıldız, Erman Ayday
备注：\c{opyright} 2019. This manuscript version is made available under the CC-BY-NC-ND 4.0 license this http URL
链接：https://arxiv.org/abs/1908.10172
【6】 Deep Learning-Based Strategy for Macromolecules Classification with Imbalanced Data from Cellular Electron Cryotomography
作者： Ziqian Luo, Min Xu
链接：https://arxiv.org/abs/1908.09993
[分割/语义相关]：
【1】 Segmentation Mask Guided End-to-End Person Search
作者： Dingyuan Zheng, Yao Zhao
链接：https://arxiv.org/abs/1908.10179
【2】 A Weakly Supervised Method for Instance Segmentation of Biological Cells
作者： Fidel A. Guerrero-Peña, Alexandre Cunha
备注：Accepted at MICCAI Worshop 2019
链接：https://arxiv.org/abs/1908.09891
【3】 Global Planar Convolutions for improved context aggregation in Brain Tumor Segmentation
作者： Santi Puch, Vesna Prchkovska
备注：Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2018
链接：https://arxiv.org/abs/1908.10281
【4】 A hybrid deep learning framework for integrated segmentation and registration: evaluation on longitudinal white matter tract changes
作者： Bo Li, Esther Bron
备注：MICCAI 2019 (oral presentation)
链接：https://arxiv.org/abs/1908.10221
【5】 Reproducible White Matter Tract Segmentation Using 3D U-Net on a Large-scale DTI Dataset
作者： Bo Li, Esther Bron
备注：Machine Learning in Medical Imaging (MLMI), 2018
链接：https://arxiv.org/abs/1908.10219
[GAN/对抗式/生成式相关]：
【1】 End-to-End Conditional GAN-based Architectures for Image Colourisation
作者： Marc Górriz, Noel E. O'Connor
备注：IEEE 21st International Workshop on Multimedia Signal Processing, 27-29 Sept 2019, Kuala Lumpur, Malaysia
链接：https://arxiv.org/abs/1908.09873
[图像/视频检索]：
【1】 Fashion Image Retrieval with Capsule Networks
作者： Furkan Kınlı, Furkan Kıraç
备注：Accepted to the International Conference on Computer Vision, ICCV 2019, Workshop on Computer Vision for Fashion, Art and Design
链接：https://arxiv.org/abs/1908.09943
[行为/时空/光流/姿态/运动]：
【1】 Bottom-up Higher-Resolution Networks for Multi-Person Pose Estimation
作者： Bowen Cheng, Lei Zhang
链接：https://arxiv.org/abs/1908.10357
【2】 Mobile Video Action Recognition
作者： Yuqi Huo, Ji-Rong Wen
链接：https://arxiv.org/abs/1908.10155
【3】 Temporal Reasoning Graph for Activity Recognition
作者： Jingran Zhang, Heng Tao Shen
链接：https://arxiv.org/abs/1908.09995
[半/弱/无监督相关]：
【1】 Unsupervised Domain-Adaptive Person Re-identification Based on Attributes
作者： Xiangping Zhu, Vittorio Murino
备注：5 pages, accepted by ICIP2019
链接：https://arxiv.org/abs/1908.10359
【2】 Attention-based Dropout Layer for Weakly Supervised Object Localization
作者： Junsuk Choe, Hyunjung Shim
备注：CVPR 2019 (Oral)
链接：https://arxiv.org/abs/1908.10028
[跟踪相关]：
【1】 Learning Reinforced Attentional Representation for End-to-End Visual Tracking
作者： Peng Gao, Fei Wang
链接：https://arxiv.org/abs/1908.10009
[迁移学习/domain/主动学习/自适应]：
【1】 MetaMixUp: Learning Adaptive Interpolation Policy of MixUp with Meta-Learning
作者： Zhijun Mai, Heng Tao Shen
链接：https://arxiv.org/abs/1908.10059
[Re-id相关]：
【1】 Intra-Camera Supervised Person Re-Identification: A New Benchmark
作者： Xiangping Zhu, Shaogang Gong
备注：9 pages, 3 figures, accepted by ICCV Workshop on Real-World Recognition from Low-Quality Images and Videos, 2019
链接：https://arxiv.org/abs/1908.10344
【2】 Global-Local Temporal Representations For Video Person Re-Identification
作者： Jianing Li, Shiliang Zhang
链接：https://arxiv.org/abs/1908.10049
[视频理解VQA/caption等]：
【1】 Controllable Video Captioning with POS Sequence Guidance Based on Gated Fusion Network
作者： Bairui Wang, Wei Liu
备注：Accepted by ICCV 2019
链接：https://arxiv.org/abs/1908.10072
[数据集dataset]：
【1】 Large-Scale Historical Watermark Recognition: dataset and a new consistency-based approach
作者： Xi Shen, Mathieu Aubry
链接：https://arxiv.org/abs/1908.10254
[点云]：
【1】 LiDARTag: A Real-Time Fiducial Tag using Point Clouds
作者： Jiunn-Kai Huang, Jessy W. Grizzle
链接：https://arxiv.org/abs/1908.10349
[深度depth相关]：
【1】 A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image
作者： Fu Xiong, Junsong Yuan
备注：Accepted by ICCV2019
链接：https://arxiv.org/abs/1908.09999
[3D/3D重建等相关]：
【1】 HRGE-Net: Hierarchical Relational Graph Embedding Network for Multi-view 3D Shape Recognition
作者： Xin Wei, Jian Sun
链接：https://arxiv.org/abs/1908.10098
【2】 3D Convolutional Neural Networks Image Registration Based on Efficient Supervised Learning from Artificial Deformations
作者： Hessam Sokooti, Marius Staring
链接：https://arxiv.org/abs/1908.10235
[其他]：
【1】 Physics-Based Rendering for Improving Robustness to Rain
作者： Shirsendu Sukanta Halder, Raoul de Charette
备注：ICCV 2019. Supplementary pdf / videos available on project page
链接：https://arxiv.org/abs/1908.10335
【2】 Few-shot Learning with Deep Triplet Networks for Brain Imaging Modality Recognition
作者： Santi Puch, Matt Rowe
备注：Medical Image Learning with Less Labels and Imperfect Data, MICCAI 2019 workshop
链接：https://arxiv.org/abs/1908.10266
【3】 Large Scale Landmark Recognition via Deep Metric Learning
作者： Andrei Boiarov, Eduard Tyantov
备注：Accepted at CIKM 2019
链接：https://arxiv.org/abs/1908.10192
【4】 Cooperative Cross-Stream Network for Discriminative Action Representation
作者： Jingran Zhang, Heng Tao Shen
链接：https://arxiv.org/abs/1908.10136
【5】 Synthetic patches, real images: screening for centrosome aberrations in EM images of human cancer cells
作者： Artem Lukoyanov, Anna Kreshuk
备注：Accepted at MICCAI 2019
链接：https://arxiv.org/abs/1908.10109
【6】 Distorted Representation Space Characterization Through Backpropagated Gradients
作者： Gukyeong Kwon, Ghassan AlRegib
备注：5 pages, 5 figures, 2 tables, ICIP 2019
链接：https://arxiv.org/abs/1908.09998
【7】 PixelVAE++: Improved PixelVAE with Discrete Prior
作者： Hossein Sadeghi, Mohammad H. Amin
链接：https://arxiv.org/abs/1908.09948
【8】 Index Network
作者： Hao Lu, Songcen Xu
备注：Extended version of "Indices Matter: Learning to Index for Deep Image Matting" at arXiv:1908.00672
链接：https://arxiv.org/abs/1908.09895
【9】 Learning to Discover Novel Visual Categories via Deep Transfer Clustering
作者： Kai Han, Andrew Zisserman
备注：ICCV 2019
链接：https://arxiv.org/abs/1908.09884
【10】 Physiological and Affective Computing through Thermal Imaging: A Survey
作者： Youngjun Cho, Nadia Bianchi-Berthouze
链接：https://arxiv.org/abs/1908.10307
【11】 Is the Red Square Big? MALeViC: Modeling Adjectives Leveraging Visual Contexts
作者： Sandro Pezzelle, Raquel Fernández
备注：Accepted at EMNLP-IJCNLP 2019
链接：https://arxiv.org/abs/1908.10285
【12】 DRD-Net: Detail-recovery Image Deraining via Context Aggregation Networks
作者： Sen Deng, Meng Wang
链接：https://arxiv.org/abs/1908.10267
【13】 Enabling Hyper-Personalisation: Automated Ad Creative Generation and Ranking for Fashion e-Commerce
作者： Sreekanth Vempati, Sandeep R
备注：Workshop on Recommender Systems in Fashion, 13th ACM Conference on Recommender Systems, 2019
链接：https://arxiv.org/abs/1908.10139
【14】 No Peeking through My Windows: Conserving Privacy in Personal Drones
作者： Alem Fitwi, Sencun Zhu
备注：To be presented at The Fifth IEEE Annual International Smart Cities Conference (ISC2 2019), Casablanca, Morocco, October 2019
链接：https://arxiv.org/abs/1908.09935
【15】 Long Range Neural Navigation Policies for the Real World
作者： Ayzaan Wahid, Tsang-Wei Edward Lee
链接：https://arxiv.org/abs/1903.09870
机器翻译，仅供参考
