计算机视觉每日论文速递[08.07]

cs.CV 方向,今日共计38篇

[检测分类相关]:

【1】 EdgeNet: A novel approach for Arabic numeral classification
EdgeNet:一种新的阿拉伯数字分类方法
作者: S. M. A. Sharif, S. M. Nadim Uddin
链接:https://arxiv.org/abs/1908.02254

【2】 MetaAdvDet: Towards Robust Detection of Evolving Adversarial Attacks
MetaAdvDet:朝着稳健检测进化中的对抗性攻击
作者: Chen Ma, Dan Zeng
备注:10 pages, 2 figures, accepted as the conference paper of Proceedings of the 27th ACM International Conference on Multimedia (MM'19)
链接:https://arxiv.org/abs/1908.02199

【3】 Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection
教师指导学生如何从部分标记的图像中学习用于面部地标检测
作者: Xuanyi Dong, Yi Yang
备注:This paper was accepted to IEEE ICCV 2019. Code is publicly available on GitHub: this https URL
链接:https://arxiv.org/abs/1908.02116

【4】 Generalised Zero-Shot Learning with a Classifier Ensemble over Multi-Modal Embedding Spaces
多模态嵌入空间上具有分类器集成的广义零激发学习
作者: Rafael Felix, Gustavo Carneiro
链接:https://arxiv.org/abs/1908.02013

【5】 Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector
基于注意-RPN和多关系检测器的少镜头目标检测
作者: Qi Fan, Yu-Wing Tai
链接:https://arxiv.org/abs/1908.01998

【6】 Semi-supervised Skin Detection by Network with Mutual Guidance
基于相互引导的网络半监督皮肤检测
作者: Yi He, Jue Wang
备注:Accepted by ICCV 2019
链接:https://arxiv.org/abs/1908.01977

【7】 Multiple Riemannian Manifold-valued Descriptors based Image Set Classification with Multi-Kernel Metric Learning
基于多核度量学习的多黎曼流形值描述子图像集分类
作者: Rui Wang, Josef Kittler
链接:https://arxiv.org/abs/1908.01950

[分割/语义相关]:

【1】 Aligning Linguistic Words and Visual Semantic Units for Image Captioning
用于图像字幕的语言单词和视觉语义单元的对齐
作者: Longteng Guo, Hanqing Lu
备注:8 pages, 5 figures. Accepted by ACM MM 2019
链接:https://arxiv.org/abs/1908.02127

【2】 Contour Loss: Boundary-Aware Learning for Salient Object Segmentation
轮廓丢失:边缘感知学习的凸起对象分割
作者: Zixuan Chen, Jianhuang Lai
链接:https://arxiv.org/abs/1908.01975

【3】 Learning Cross-Modal Deep Representations for Multi-Modal MR Image Segmentation
学习多模态MR图像分割的跨模态深度表示
作者: Cheng Li, Shanshan Wang
链接:https://arxiv.org/abs/1908.01997

[GAN/对抗式/生成式相关]:

【1】 Semi-Supervised Adversarial Monocular Depth Estimation
半监督对抗性单目深度估计
作者: Rongrong Ji, Jiebo Luo
链接:https://arxiv.org/abs/1908.02126

【2】 Attribute-Guided Coupled GAN for Cross-Resolution Face Recognition
用于交叉分辨率人脸识别的属性引导耦合GaN
作者: Veeru Talreja, Nasser M Nasrabadi
链接:https://arxiv.org/abs/1908.01790

[图像/视频检索]:

【1】 View N-gram Network for 3D Object Retrieval
用于三维对象检索的视图N-gram网络
作者: Xinwei He, Xiang Bai
备注:The paper was accepted to ICCV 2019
链接:https://arxiv.org/abs/1908.01958

[行为/时空/光流/姿态/运动]:

【1】 Hybrid Camera Pose Estimation with Online Partitioning
基于在线分割的混合摄像机姿态估计
作者: Xinyi Li, Haibin Ling
链接:https://arxiv.org/abs/1908.01797

[半/弱/无监督相关]:

【1】 Deep Self-Learning From Noisy Labels
从噪声标签中进行深度自学习
作者: Jiangfan Han, Xiaogang Wang
备注:Accepted by IEEE International Conference on Computer Vision(ICCV) 2019
链接:https://arxiv.org/abs/1908.02160

【2】 Unsupervised Representations of Pollen in Bright-Field Microscopy
明场显微镜中花粉的无监督表示
作者: Peter He, Alexis Gkantiragas
备注:Accepted at the Workshop on Computational Biology at the International Conference on Machine Learning (ICML) in Long Beach, CA, USA on June 14, 2019
链接:https://arxiv.org/abs/1908.01866

[跟踪相关]:

【1】 Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking
用于无人机实时跟踪的学习畸变抑制相关滤波器
作者: Ziyuan Huang, Peng Lu
备注:iccv 2019 accepted, 10 pages, 8 figures
链接:https://arxiv.org/abs/1908.02231

[裁剪/量化/加速相关]:

【1】 Restoration of Non-rigidly Distorted Underwater Images using a Combination of Compressive Sensing and Local Polynomial Image Representations
结合压缩感知和局部多项式图像表示的非刚性畸变水下图像恢复
作者: Jerin Geo James, Ajit Rajwade
备注:Accepted in ICCV 2019 for oral presentation
链接:https://arxiv.org/abs/1908.01940

【2】 Architecture-aware Network Pruning for Vision Quality Applications
用于视觉质量应用的体系结构感知网络修剪
作者: Wei-Ting Wang, Yi-Min Tsai
备注:Accepted to be Published in the 26th IEEE International Conference on Image Processing (ICIP 2019). Updated to contain the IEEE copyright notice
链接:https://arxiv.org/abs/1908.02125

[其他视频相关]:

【1】 Live Illumination Decomposition of Videos
视频的实时光照分解
作者: Abhimitra Meka, Christian Theobalt
链接:https://arxiv.org/abs/1908.01961

[其他]:

【1】 ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
ViLBERT:训练前任务-视觉和语言任务的可视语言表征
作者: Jiasen Lu, Stefan Lee
链接:https://arxiv.org/abs/1908.02265

【2】 Neural Blind Deconvolution Using Deep Priors
使用深度先验的神经盲反卷积
作者: Dongwei Ren, Wangmeng Zuo
链接:https://arxiv.org/abs/1908.02197

【3】 Addressing Data Bias Problems for Chest X-ray Image Report Generation
解决胸部X光图像报告生成中的数据偏差问题
作者: Philipp Harzig, Rainer Lienhart
备注:Oral at BMVC 2019
链接:https://arxiv.org/abs/1908.02123

【4】 AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks
AttentionBoost:通过提升完全卷积网络来学习参加什么
作者: Gozde Nur Gunesli, Cigdem Gunduz-Demir
链接:https://arxiv.org/abs/1908.02095

【5】 Fast Fourier Color Constancy and Grayness Index for ISPA Illumination Estimation Challenge
ISPA光照估计挑战的快速傅立叶颜色恒定性和灰度指数
作者: Yanlin Qian, Huanglin Yu
备注:The 3-page challenge report for the Illumination Estimation Challenge, in the Int'l Workshop on Color Vision, affiliated to the 11th Int'l Symposium on Image and Signal Processing and Analysis (ISPA2019, Dubrovnik, Croatia)
链接:https://arxiv.org/abs/1908.02076

【6】 Full-Stack Filters to Build Minimum Viable CNNs
构建最小可行CNN的全堆栈过滤器
作者: Kai Han, Chang Xu
链接:https://arxiv.org/abs/1908.02023

【7】 Consensus Maximization Tree Search Revisited
重新审视共识最大化树搜索
作者: Zhipeng Cai, Vladlen Koltun
备注:Accepted as oral presentation to ICCV'19
链接:https://arxiv.org/abs/1908.02021

【8】 Multi-view Deep Subspace Clustering Networks
多视图深子空间聚类网络
作者: Pengfei Zhu, Qinghua Hu
链接:https://arxiv.org/abs/1908.01978

【9】 REAPS: Towards Better Recognition of Fine-grained Images by Region Attending and Part Sequencing
REAP:通过区域参与和零件排序更好地识别细粒度图像
作者: Peng Zhang, Yi Niu
备注:PRCV 2019
链接:https://arxiv.org/abs/1908.01962

【10】 Symmetry-constrained Rectification Network for Scene Text Recognition
用于场景文本识别的对称约束校正网络
作者: MingKun Yang, Xiang Bai
备注:The paper was accepted to ICCV2019
链接:https://arxiv.org/abs/1908.01957

【11】 Logic could be learned from images
逻辑可以从图像中学习
作者: Qian Guo, Jiye Liang
链接:https://arxiv.org/abs/1908.01931

【12】 Attract or Distract: Exploit the Margin of Open Set
吸引或分散注意力:利用Open Set的边缘
作者: Qianyu Feng, Yi Yang
链接:https://arxiv.org/abs/1908.01925

【13】 Attention Control with Metric Learning Alignment for Image Set-based Recognition
基于图像集识别的基于度量学习对齐的注意控制
作者: Xiaofeng Liu, B.V.K Vijaya Kumar
备注:Accepted to IEEE T-IFS (Extension of ECCV 2018 paper: Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets). arXiv admin note: substantial text overlap with arXiv:1907.03030; text overlap with arXiv:1707.00130 by other authors
链接:https://arxiv.org/abs/1908.01872

【14】 Semi-Automatic Labeling for Deep Learning in Robotics
用于机器人深度学习的半自动标注
作者: Daniele De Gregorio, Luigi Di Stefano
链接:https://arxiv.org/abs/1908.01862

【15】 Answering Questions about Data Visualizations using Efficient Bimodal Fusion
使用有效的双峰融合回答有关数据可视化的问题
作者: Kushal Kafle, Christopher Kanan
链接:https://arxiv.org/abs/1908.01801

【16】 An attempt at beating the 3D U-Net
一次击败3DU-NET的尝试
作者: Fabian Isensee, Klaus H. Maier-Hein
链接:https://arxiv.org/abs/1908.02182

【17】 Semiparametric Wavelet-based JPEG IV Estimator for endogenously truncated data
基于半参数小波的内生截断数据的JPEG IV估计
作者: Nir Billfeld, Moshe Kim
备注:18 pages
链接:https://arxiv.org/abs/1908.02166

【18】 Model-based Convolutional De-Aliasing Network Learning for Parallel MR Imaging
基于模型的卷积去混叠网络学习在并行MR成像中的应用
作者: Yanxia Chen, Shanshan Wang
链接:https://arxiv.org/abs/1908.02054

翻译:腾讯翻译君

计算机视觉每日论文速递[08.07]_第1张图片
图片发自App

你可能感兴趣的:(计算机视觉每日论文速递[08.07])