cs.CV 方向,今日共计39篇
[检测分类相关]:
【1】 Pothole Detection Based on Disparity Transformation and Road Surface Modeling
基于视差变换和路面建模的坑洞检测
作者: Rui Fan, Ioannis Pitas
链接:https://arxiv.org/abs/1908.00894
【2】 Learning Lightweight Lane Detection CNNs by Self Attention Distillation
自注意蒸馏学习轻量级车道检测CNN
作者: Yuenan Hou, Chen Change Loy
备注:9 pages, 8 figures; This paper is accepted by ICCV 2019; Our code is available at this https URL
链接:https://arxiv.org/abs/1908.00821
【3】 Entry-Exit event detection and learning
出入口事件检测和学习
作者: Vinay Kumar V, P Nagabhushan
链接:https://arxiv.org/abs/1908.00716
【4】 ConCORDe-Net: Cell Count Regularized Convolutional Neural Network for Cell Detection in Multiplex Immunohistochemistry Images
Concorde-net:用于多重免疫组织化学图像细胞检测的细胞计数正则化卷积神经网络
作者: Yeman Brhane Hagos, Yinyin Yuan
备注:MICCAI2019 accepted, 3 figures,8.5 pages
链接:https://arxiv.org/abs/1908.00907
【5】 Road Context-aware Intrusion Detection System for Autonomous Cars
面向自主汽车的道路上下文感知入侵检测系统
作者: Jingxuan Jiang, Wei Zhang
链接:https://arxiv.org/abs/1908.00732
【6】 Improving localization-based approaches for breast cancer screening exam classification
改进基于定位的乳腺癌筛查检查分类方法
作者: Thibault Févry, Krzysztof J. Geras
备注:MIDL 2019 [arXiv:1907.08612]
链接:https://arxiv.org/abs/1908.00615
[分割/语义相关]:
【1】 An amplified-target loss approach for photoreceptor layer segmentation in pathological OCT scans
病理性OCT扫描中光感受层分割的放大靶标损失法
作者: José Ignacio Orlando, Ursula Schmidt-Erfurth
备注:Accepted for publication at MICCAI-OMIA 2019
链接:https://arxiv.org/abs/1908.00764
【2】 Robustifying deep networks for image segmentation
用于图像分割的Robustified深层网络
作者: Zheng Liu, Alan B McMillan
链接:https://arxiv.org/abs/1908.00656
[GAN/对抗式/生成式相关]:
【1】 Adversarial Camera Alignment Network for Unsupervised Cross-camera Person Re-identification
用于无监督交叉摄像机人员重新识别的对抗性摄像机对准网络
作者: Lei Qi, Yang Gao
链接:https://arxiv.org/abs/1908.00862
【2】 AdvGAN++ : Harnessing latent layers for adversary generation
AdvGAN+:利用潜伏层生成对手
作者: Puneet Mangla, Vineeth N Balasubramanian
链接:https://arxiv.org/abs/1908.00706
[行为/时空/光流/姿态/运动]:
【1】 An Evaluation of Action Recognition Models on EPIC-Kitchens
基于EPIC-Kitchens的动作识别模型评价
作者: Will Price, Dima Damen
链接:https://arxiv.org/abs/1908.00867
【2】 Fitting, Comparison, and Alignment of Trajectories on Positive Semi-Definite Matrices with Application to Action Recognition
半正定矩阵上轨迹的拟合、比较和对齐及其在动作识别中的应用
作者: Benjamin Szczapa, Estelle Massart
链接:https://arxiv.org/abs/1908.00646
【3】 Learning Variations in Human Motion via Mix-and-Match Perturbation
通过混合和匹配摄动来学习人体运动中的变化
作者: Mohammad Sadegh Aliakbarian, Amirhossein Habibian
链接:https://arxiv.org/abs/1908.00733
[半/弱/无监督相关]:
【1】 DAWN: Dual Augmented Memory Network for Unsupervised Video Object Tracking
Dawn:用于无监督视频对象跟踪的双增强内存网络
作者: Zhenmei Shi, Chi-Keung Tang
链接:https://arxiv.org/abs/1908.00777
[跟踪相关]:
【1】 Learning the Model Update for Siamese Trackers
学习暹罗跟踪器的模型更新
作者: Lichao Zhang, Fahad Shahbaz Khan
链接:https://arxiv.org/abs/1908.00855
【2】 Real Time Visual Tracking using Spatial-Aware Temporal Aggregation Network
基于空间感知时间聚合网络的实时视觉跟踪
作者: Tao Hu, Han Shen
链接:https://arxiv.org/abs/1908.00692
[视频理解VQA/caption等]:
【1】 Captioning Near-Future Activity Sequences
字幕近期活动序列
作者: Tahmida Mahmud, Amit K. Roy-Chowdhury
链接:https://arxiv.org/abs/1908.00943
[其他视频相关]:
【1】 Scale Matters: Temporal Scale Aggregation Network for Precise Action Localization in Untrimmed Videos
尺度问题:用于未裁剪视频中精确动作定位的时间尺度聚合网络
作者: Guoqiang Gong, Yadong Mu
链接:https://arxiv.org/abs/1908.00707
[其他]:
【1】 Learning to Train with Synthetic Humans
学习与人造人一起训练
作者: David T. Hoffmann, Siyu Tang
链接:https://arxiv.org/abs/1908.00967
【2】 Effects of Illumination on the Categorization of Shiny Materials
光照对发光材料分类的影响
作者: J. Farley Norman, Flip Phillips
链接:https://arxiv.org/abs/1908.00902
【3】 Distilling Knowledge From a Deep Pose Regressor Network
从深度姿态回归器网络中提取知识
作者: Muhamad Risqi U. Saputra, Niki Trigoni
备注:Accepted to ICCV 2019
链接:https://arxiv.org/abs/1908.00858
【4】 A Structural Graph-Based Method for MRI Analysis
一种基于结构图的MRI分析方法
作者: Larissa de O. Penteado, Roberto M. Cesar Jr
备注:Published in the Workshop of Works In Progress of the SIBGRAPI 2018
链接:https://arxiv.org/abs/1908.00778
【5】 L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention
L2G自动编码器:通过分层自关注的局部到全局重建来理解点云
作者: Xinhai Liu, Matthias Zwicker
链接:https://arxiv.org/abs/1908.00720
【6】 Indices Matter: Learning to Index for Deep Image Matting
索引很重要:学习为深度图像拼接编制索引
作者: Hao Lu, Songcen Xu
备注:Accepted to Proc. Int. Conf. Computer Vision 2019
链接:https://arxiv.org/abs/1908.00672
【7】 Recognizing Image Objects by Relational Analysis Using Heterogeneous Superpixels and Deep Convolutional Features
利用异质超像素和深层卷积特征的相关分析识别图像对象
作者: Alex Yang, Grant J. Scott
链接:https://arxiv.org/abs/1908.00669
【8】 Neural Architecture based on Fuzzy Perceptual Representation For Online Multilingual Handwriting Recognition
基于模糊感知表征的在线多语种手写识别神经结构
作者: Hanen Akouaydi, Adel M. Alimi
链接:https://arxiv.org/abs/1908.00634
【9】 Multi-Scale Learned Iterative Reconstruction
多尺度学习迭代重建
作者: Andreas Hauptmann, Ozan Öktem
链接:https://arxiv.org/abs/1908.00936
【10】 Exact and Fast Inversion of the Approximate Discrete Radon Transform
近似离散Radon变换的精确快速反演
作者: Donsub Rim
链接:https://arxiv.org/abs/1908.00887
【11】 Space-adaptive anisotropic bivariate Laplacian regularization for image restoration
空间自适应各向异性二元拉普拉斯正则化图像复原
作者: Luca Calatroni, Fiorella Sgallari
链接:https://arxiv.org/abs/1908.00801
【12】 Uncertainty Quantification in Computer-Aided Diagnosis: Make Your Model say "I don't know" for Ambiguous Cases
计算机辅助诊断中的不确定性量化:让模型对于不明确的案例说“我不知道”
作者: Max-Heinrich Laves, Tobias Ortmaier
备注:Accepted at MIDL 2019 [arXiv:1907.08612]
链接:https://arxiv.org/abs/1908.00792
【13】 Deformable Medical Image Registration Using a Randomly-Initialized CNN as Regularization Prior
使用随机初始化的CNN作为正则化先验的可变形医学图像配准
作者: Max-Heinrich Laves, Tobias Ortmaier
备注:Accepted at MIDL 2019 [arXiv:1907.08612]
链接:https://arxiv.org/abs/1908.00788
【14】 Network with Sub-Networks
带子网的网络
作者: Ninnart Fuengfusin, Hakaru Tamukoh
链接:https://arxiv.org/abs/1908.00763
【15】 Integrating Spatial Configuration into Heatmap Regression Based CNNs for Landmark Localization
将空间配置集成到基于热图回归的CNN中用于地标定位
作者: Christian Payer, Martin Urschler
备注:MIDL 2019 [arXiv:1907.08612]
链接:https://arxiv.org/abs/1908.00748
【16】 Combining learned skills and reinforcement learning for robotic manipulations
结合学习技能和强化学习的机器人操作
作者: Robin Strudel, Cordelia Schmid
链接:https://arxiv.org/abs/1908.00722
【17】 AutoML: A Survey of the State-of-the-Art
AutoML:最新进展综述
作者: Xin He, Xiaowen Chu
链接:https://arxiv.org/abs/1908.00709
【18】 Greedy AutoAugment
贪婪的自动加薪
作者: Alireza Naghizadeh, Dimitris N. Metaxas
链接:https://arxiv.org/abs/1908.00704
【19】 Attention-guided Low-light Image Enhancement
注意力引导的微光图像增强
作者: Feifan Lv, Feng Lu
链接:https://arxiv.org/abs/1908.00682
【20】 Deep Optics for Single-shot High-dynamic-range Imaging
用于单次激发高动态范围成像的深度光学
作者: Christopher A. Metzler, Gordon Wetzstein
链接:https://arxiv.org/abs/1908.00620
【21】 StructureNet: Hierarchical Graph Networks for 3D Shape Generation
StringreNet:用于3D形状生成的分层图网络
作者: Kaichun Mo, Leonidas J. Guibas
备注:Conditionally Accepted to Siggraph Asia 2019
链接:https://arxiv.org/abs/1908.00575
翻译:腾讯翻译君
网友评论