计算机视觉论文速递[10.16]

论坛 期权论坛 期权     
arXiv每日论文速递   2019-10-16 11:11   3694   0
点击上方蓝字 ↑ 关注公众号,点击[阅读原]文直达arXiv
cs.CV 方向,今日共计41篇

[检测分类相关]:【1】 End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point  Clouds
标题:用于LiDAR点云中3D目标检测的端到端多视图融合
作者: Yin Zhou,  Pei Sun备注:CoRL2019链接:https://arxiv.org/abs/1910.06528  
【2】 Building Damage Detection in Satellite Imagery Using Convolutional  Neural Networks
标题:基于卷积神经网络的卫星图像建筑物损伤检测
作者: Joseph Z. Xu,  Wenhan Lu链接:https://arxiv.org/abs/1910.06444
【3】 Building Information Modeling and Classification by Visual Learning At A  City Scale
标题:基于视觉学习的城市尺度建筑信息建模与分类
作者: Qian Yu,  Chaofeng Wang备注:33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada链接:https://arxiv.org/abs/1910.06391
【4】 Quantifying Classification Uncertainty using Regularized Evidential  Neural Networks
标题:利用正则化证据神经网络量化分类不确定性
作者: Xujiang Zhao,  Yuzhe Ou备注:Presented at AAAI FSS-19: Artificial Intelligence in Government and Public Sector, Arlington, Virginia, USA链接:https://arxiv.org/abs/1910.06864
【5】 Liver segmentation and metastases detection in MR images using  convolutional neural networks
标题:基于卷积神经网络的MR图像肝脏分割与转移检测
作者: Marille J.A. Jansen,  Hugo J. Kuijf链接:https://arxiv.org/abs/1910.06635
[分割/语义相关]:【1】 SegSort: Segmentation by Discriminative Sorting of Segments
标题:SegSort:通过区别性分段排序进行分段
作者: Jyh-Jing Hwang,  Stella X. Yu备注:In ICCV 2019. Webpage & Code: this https URL链接:https://arxiv.org/abs/1910.06962
【2】 Learning to Predict Layout-to-image Conditional Convolutions for  Semantic Image Synthesis
标题:学习预测布局到图像的条件卷积用于语义图像合成
作者: Xihui Liu,  Guojun Yin链接:https://arxiv.org/abs/1910.06809
【3】 Background Segmentation for Vehicle Re-Identification
标题:用于车辆再识别的背景分割
作者: Mingjie Wu,  Yongfei Zhang链接:https://arxiv.org/abs/1910.06613
【4】 Target-Oriented Deformation of Visual-Semantic Embedding Space
标题:视觉语义嵌入空间的面向目标变形
作者: Takashi Matsubara 链接:https://arxiv.org/abs/1910.06514
【5】 End-to-End Adversarial Shape Learning for Abdomen Organ Deep  Segmentation
标题:用于腹部器官深度分割的端到端对抗性形状学习
作者: Jinzheng Cai,  Yingda Xia备注:Accepted to International Workshop on Machine Learning in Medical Imaging (MLMI2019)链接:https://arxiv.org/abs/1910.06474
【6】 FireNet: Real-time Segmentation of Fire Perimeter from Aerial Video
标题:FireNet:从航空视频中实时分割火灾边界
作者: Jigar Doshi,  Dominic Garcia备注:Published at NeurIPS 2019; Workshop on Artificial Intelligence for Humanitarian Assistance and Disaster Response(AI+HADR 2019)链接:https://arxiv.org/abs/1910.06407
[GAN/对抗式/生成式相关]:【1】 Generating Human Action Videos by Coupling 3D Game Engines and  Probabilistic Graphical Models
标题:通过耦合3D游戏引擎和概率图形模型生成人类动作视频
作者: César Roberto de Souza,  Adrien Gaidon链接:https://arxiv.org/abs/1910.06699
【2】 Restoration of marker occluded hematoxylin and eosin stained whole slide  histology images using generative adversarial networks
标题:使用生成性对抗网络恢复标记闭塞的苏木素和曙红染色的整个幻灯片组织学图像
作者: Bairavi Venkatesh,  Tosha Shah链接:https://arxiv.org/abs/1910.06428
【3】 Multi-Frame GAN: Image Enhancement for Stereo Visual Odometry in Low  Light
标题:多帧GaN:微光下立体视觉里程计的图像增强
作者: Eunah Jung,  Nan Yang备注:Accepted by the 3rd Conference on Robot Learning, Osaka, Japan (CoRL 2019). The first two authors contributed equally to this paper链接:https://arxiv.org/abs/1910.06632
[行为/时空/光流/姿态/运动]:【1】 Human Action Recognition with Multi-Laplacian Graph Convolutional  Networks
标题:基于多拉普拉斯图卷积网络的人体行为识别
作者: Ahmed Mazari,  Hichem Sahbi 链接:https://arxiv.org/abs/1910.06934
【2】 Stereo-based Multi-motion Visual Odometry for Mobile Robots
标题:基于立体的移动机器人多运动视觉里程计
作者: Qing Zhao,  Bin Luo链接:https://arxiv.org/abs/1910.06607
[Re-id相关]:【1】 Learning Generalisable Omni-Scale Representations for Person  Re-Identification
标题:用于人再识别的学习泛化全尺度表示
作者: Kaiyang Zhou,  Xiatian Zhu备注:Extension of conference version: arXiv:1905.00953. Source code: this https URL链接:https://arxiv.org/abs/1910.06827
[视频理解VQA/caption等]:【1】 Integrating Temporal and Spatial Attentions for VATEX Video Captioning  Challenge 2019
标题:集成时间和空间关注的VATEX视频字幕挑战2019年
作者: Shizhe Chen,  Yida Zhao备注:ICCV 2019 VATEX challenge链接:https://arxiv.org/abs/1910.06737
【2】 Exploring Overall Contextual Information for Image Captioning in  Human-Like Cognitive Style
标题:类人认知风格下图像字幕的整体上下文信息研究
作者: Hongwei Ge,  Zehang Yan备注:ICCV 2019链接:https://arxiv.org/abs/1910.06475
[数据集dataset]:【1】 Mitigating the Effect of Dataset Bias on Training Deep Models for Chest  X-rays
标题:减轻数据集偏差对训练胸部X光深层模型的影响
作者: Yundong Zhang,  Hang Wu链接:https://arxiv.org/abs/1910.06745
[深度depth相关]:【1】 Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints
标题:基于深度-法线约束的稀疏LiDAR数据深度补全
作者: Yan Xu,  Xinge Zhu备注:Accepted to ICCV 2019链接:https://arxiv.org/abs/1910.06727
[3D/3D重建等相关]:【1】 Real-time monitoring of driver drowsiness on mobile platforms using 3D  neural networks
标题:基于3D神经网络的移动平台驾驶员瞌睡实时监测
作者: Jasper S. Wijnands,  Jason Thompson链接:https://arxiv.org/abs/1910.06540
[其他视频相关]:【1】 Tiny Video Networks
标题:微型视频网络
作者: AJ Piergiovanni,  Anelia Angelova链接:https://arxiv.org/abs/1910.06961
[其他]:【1】 DeepGCNs: Making GCNs Go as Deep as CNNs
标题:DeepGCNs:让GCNS与CNN一样深入
作者: Guohao Li,  Matthias Müller备注:First two authors contributed equally. This work is a journal extension of our ICCV'19 paper arXiv:1904.03751链接:https://arxiv.org/abs/1910.06849
【2】 A Compact Neural Architecture for Visual Place Recognition
标题:一种用于视觉位置识别的紧凑神经结构
作者: Marvin Chancán,  Luis Hernandez-Nunez备注:Submitted to RA-L with ICRA 2020 presentation option, 8 pages, 13 figures链接:https://arxiv.org/abs/1910.06840
【3】 Cortical-inspired Wilson-Cowan-type equations for orientation-dependent  contrast perception modelling
标题:皮层启发的Wilson-Cowan型方程式用于方位相关的对比度知觉建模
作者: Marcelo Bertalmío,  Luca Calatroni备注:This is the extended invited journal version of the SSVM 2019 conference proceeding arXiv:1812.07425链接:https://arxiv.org/abs/1910.06808
【4】 Seeing and Hearing Egocentric Actions: How Much Can We Learn?
标题:看到和听到以自我为中心的行动:我们能学到多少?
作者: Alejandro Cartas,  Jordi Luque备注:Accepted for the Fifth International Workshop on Egocentric Perception, Interaction and Computing (EPIC) at the International Conference on Computer Vision (ICCV) 2019链接:https://arxiv.org/abs/1910.06693
【5】 Being the center of attention: A Person-Context CNN framework for  Personality Recognition
标题:成为关注的中心:人格识别的人-语境CNN框架
作者: Dario Dotti,  Mirela Popa链接:https://arxiv.org/abs/1910.06690
【6】 A Method to Generate Synthetically Warped Document Image
标题:一种综合生成扭曲文档图像的方法
作者: Arpan Garai,  Samit Biswas链接:https://arxiv.org/abs/1910.06621
【7】 Trajectorylet-Net: a novel framework for pose prediction based on  trajectorylet descriptors
标题:Trajectorylet-net:一种新的基于Trajectorylet描述子的位姿预测框架
作者: Xiaoli Liu,  Jianqin Yin链接:https://arxiv.org/abs/1910.06583
【8】 IMMVP: An Efficient Daytime and Nighttime On-Road Object Detector
标题:IMMVP:一种高效的昼夜道路目标检测器
作者: Cheng-En Wu,  Yi-Ming Chan链接:https://arxiv.org/abs/1910.06573
【9】 Tell-the-difference: Fine-grained Visual Descriptor via a Discriminating  Referee
标题:告诉区别:通过有辨别力的裁判提供细粒度的视觉描述符
作者: Shuangjie Xu,  Feng Xu链接:https://arxiv.org/abs/1910.06426
【10】 The Local Elasticity of Neural Networks
标题:神经网络的局部弹性
作者: Hangfeng He,  Weijie J. Su 链接:https://arxiv.org/abs/1910.06943
【11】 Deep learning for Aerosol Forecasting
标题:气溶胶预报的深度学习
作者: Caleb Hoyne,  S. Karthik Mukkavilli备注:Machine Learning and the Physical Sciences Workshop at the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada链接:https://arxiv.org/abs/1910.06789
【12】 Self Driving RC Car using Behavioral Cloning
标题:使用行为克隆的自动驾驶RC车
作者: Aliasgar Haji,  Priyam Shah链接:https://arxiv.org/abs/1910.06734
【13】 Neural Approximation of an Auto-Regressive Process through Confidence  Guided Sampling
标题:自回归过程的置信引导抽样神经逼近
作者: YoungJoon Yoo,  Sanghyuk Chun链接:https://arxiv.org/abs/1910.06705
【14】 SafeCritic: Collision-Aware Trajectory Prediction
标题:SafeCritic:碰撞感知轨迹预测
作者: Tessa van der Heiden,  Naveen Shankar Nagaraja备注:To Appear as workshop paper for the British Machine Vision Conference (BMVC) 2019链接:https://arxiv.org/abs/1910.06673
【15】 Topological Navigation Graph
标题:拓扑导航图
作者: Povilas Daniusis,  Shubham Juneja链接:https://arxiv.org/abs/1910.06658
【16】 Training CNNs faster with Dynamic Input and Kernel Downsampling
标题:利用动态输入和内核下采样更快地训练CNN
作者: Zissis Poulos,  Ali Nouri链接:https://arxiv.org/abs/1910.06548
【17】 State of Compact Architecture Search For Deep Neural Networks
标题:深层神经网络紧凑结构搜索研究现状
作者: Mohammad Javad Shafiee,  Andrew Hryniowski链接:https://arxiv.org/abs/1910.06466
【18】 Real-time Data Driven Precision Estimator for RAVEN-II Surgical Robot  End Effector Position
标题:实时数据驱动的RAVEN-II手术机器人末端效应器位置精确估计器
作者: Haonan Peng,  Xingjian Yang备注:6 pages, 10 figures, ICRA2020(under review)链接:https://arxiv.org/abs/1910.06425
机器翻译,仅供参考
分享到 :
0 人收藏
您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

积分:43
帖子:4
精华:0
期权论坛 期权论坛
发布
内容

下载期权论坛手机APP