美文网首页arXiv daily
计算机视觉每日论文速递[07.30]

计算机视觉每日论文速递[07.30]

作者: arXiv每日论文速递 | 来源:发表于2019-07-30 10:18 被阅读54次

    同步wx公主号(arXiv每日论文速递),支持后台回复'search 关键词'搜索相关的最新论文。有些许帮助的话,麻烦关注一下哦(* ̄rǒ ̄)

    cs.CV 方向,今日共计77篇

    [检测分类相关]:

    【1】 X-LineNet: Detecting Aircraft in Remote Sensing Images by a pair of Intersecting Line Segments
    X-LineNet:通过一对相交的线段检测遥感图像中的飞行器
    作者: Haoran Wei, Zhang Yue
    链接:https://arxiv.org/abs/1907.12474

    【2】 Specular- and Diffuse-reflection-based Face Liveness Detection for Mobile Devices
    基于镜面反射和漫反射的移动设备人脸活性检测
    作者: Akinori F. Ebihara, Hitoshi Imaoka
    链接:https://arxiv.org/abs/1907.12400

    【3】 On the Realization and Analysis of Circular Harmonic Transforms for Feature Detection
    特征检测中圆谐变换的实现与分析
    作者: Hugh L Kennedy
    链接:https://arxiv.org/abs/1907.12165

    【4】 It's All About The Scale -- Efficient Text Detection Using Adaptive Scaling
    这一切都是关于缩放-使用自适应缩放的高效文本检测
    作者: Elad Richardson, Stav Shapiro
    链接:https://arxiv.org/abs/1907.12122

    【5】 Real-time Tracking-by-Detection of Human Motion in RGB-D Camera Networks
    RGB-D摄像机网络中人体运动的实时跟踪
    作者: Alessandro Malaguti, Stefano Ghidoni
    备注:Accepted to IEEE SMC 2019
    链接:https://arxiv.org/abs/1907.12112

    【6】 Rethinking Classification and Localization for Cascade R-CNN
    对级联R-CNN分类和定位的再思考
    作者: Ang Li, Chongyang Zhang
    备注:BMVC 2019 Camera Ready
    链接:https://arxiv.org/abs/1907.11914

    【7】 Forced Spatial Attention for Driver Foot Activity Classification
    驾驶员足部活动分类的强制空间注意
    作者: Akshay Rangesh, Mohan M. Trivedi
    链接:https://arxiv.org/abs/1907.11824

    【8】 Grape detection, segmentation and tracking using deep neural networks and three-dimensional association
    利用深层神经网络和三维关联进行葡萄检测、分割和跟踪
    作者: Thiago T. Santos, Sandra Avila
    链接:https://arxiv.org/abs/1907.11819

    【9】 Accurate and Robust Pulmonary Nodule Detection by 3D Feature Pyramid Network with Self-supervised Feature Learning
    基于自监督特征学习的3D特征金字塔网络精确而鲁棒的肺结节检测
    作者: Jingya Liu, Yingli Tian
    备注:15 pages, 8 figures, 5 tables, under review by Medical Image Analysis. arXiv admin note: substantial text overlap with arXiv:1906.03467
    链接:https://arxiv.org/abs/1907.11704

    【10】 Automated Lesion Detection by Regressing Intensity-Based Distance with a Neural Network
    基于神经网络的基于强度的距离回归自动病变检测
    作者: Kimberlin M.H. van Wijnen, Marleen de Bruijne
    备注:MICCAI 2019
    链接:https://arxiv.org/abs/1907.12452

    [分割/语义相关]:

    【1】 FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation
    FSS-1000:用于少镜头分割的1000类数据集
    作者: Tianhan Wei, Chi-Keung Tang
    链接:https://arxiv.org/abs/1907.12347

    【2】 Multi-Task Attention-Based Semi-Supervised Learning for Medical Image Segmentation
    基于多任务注意的半监督医学图像分割学习
    作者: Shuai Chen, Marleen de Bruijne
    备注:Accepted at MICCAI 2019
    链接:https://arxiv.org/abs/1907.12303

    【3】 A Two Stage GAN for High Resolution Retinal Image Generation and Segmentation
    用于高分辨率视网膜图像生成和分割的两级GaN
    作者: Paolo Andreini, Andrea Sodi
    链接:https://arxiv.org/abs/1907.12296

    【4】 Regularizing Proxies with Multi-Adversarial Training for Unsupervised Domain-Adaptive Semantic Segmentation
    面向无监督领域自适应语义分割的多对抗性训练正规化代理
    作者: Tong Shen, Tao Mei
    链接:https://arxiv.org/abs/1907.12282

    【5】 Interlaced Sparse Self-Attention for Semantic Segmentation
    基于交错稀疏自注意的语义切分
    作者: Lang Huang, Jingdong Wang
    链接:https://arxiv.org/abs/1907.12273

    【6】 A Fine-Grain Error Map Prediction and Segmentation Quality Assessment Framework for Whole-Heart Segmentation
    一种适用于全心分割的细粒度误差图预测和分割质量评估框架
    作者: Rongzhao Zhang, Albert C.S. Chung
    备注:9 pages, accepted by MICCAI'19
    链接:https://arxiv.org/abs/1907.12244

    【7】 Automatic Text Line Segmentation Directly in JPEG Compressed Document Images
    直接在JPEG压缩文档图像中自动进行文本行分割
    作者: Bulla Rajesh, P Nagabhushan
    备注:Accepted in GCCE2019, Okinawa, Japan
    链接:https://arxiv.org/abs/1907.12219

    【8】 FocusNet: Imbalanced Large and Small Organ Segmentation with an End-to-End Deep Neural Network for Head and Neck CT Images
    FocusNet:基于端到端深度神经网络的头颈部CT图像不平衡大小器官分割
    作者: Yunhe Gao, Hongsheng Li
    备注:MICCAI 2019
    链接:https://arxiv.org/abs/1907.12056

    【9】 DAR-Net: Dynamic Aggregation Network for Semantic Scene Segmentation
    DAR-NET:面向语义场景分割的动态聚合网络
    作者: Zongyue Zhao, Karthik Ramani
    链接:https://arxiv.org/abs/1907.12022

    【10】 Segmenting Hyperspectral Images Using Spectral-Spatial Convolutional Neural Networks With Training-Time Data Augmentation
    利用训练时间数据增强的谱-空间卷积神经网络分割高光谱图像
    作者: Jakub Nalepa, Michal Kawulok
    链接:https://arxiv.org/abs/1907.11935

    【11】 Semantic Guided Single Image Reflection Removal
    语义引导的单幅图像反射去除
    作者: Yunfei Liu, Feng Lu
    链接:https://arxiv.org/abs/1907.11912

    【12】 Pick-and-Learn: Automatic Quality Evaluation for Noisy-Labeled Image Segmentation
    Pick-and-Learn:噪声标记图像分割的自动质量评估
    作者: Haidong Zhu, Ji Wu
    备注:Accepted for MICCAI2019
    链接:https://arxiv.org/abs/1907.11835

    [GAN/对抗式/生成式相关]:

    【1】 Learn to Scale: Generating Multipolar Normalized Density Map for Crowd Counting
    学会缩放:生成用于人群计数的多极归一化密度贴图
    作者: Chenfeng Xu, Xiang Bai
    备注:Accepted to ICCV 2019
    链接:https://arxiv.org/abs/1907.12428

    【2】 MaskGAN: Towards Diverse and Interactive Facial Image Manipulation
    MaskGAN:走向多样化和交互式的面部图像处理
    作者: Cheng-Han Lee, Ping Luo
    链接:https://arxiv.org/abs/1907.11922

    【3】 Blind Deblurring Using GANs
    利用GANS实现盲解模糊
    作者: Manoj Kumar Lenka, Anurag Mittal
    链接:https://arxiv.org/abs/1907.11880

    【4】 Quadtree Generating Networks: Efficient Hierarchical Scene Parsing with Sparse Convolutions
    四叉树生成网络:使用稀疏卷积的高效分层场景解析
    作者: Kashyap Chitta, Martial Hebert
    链接:https://arxiv.org/abs/1907.11821

    【5】 VITAL: A Visual Interpretation on Text with Adversarial Learning for Image Labeling
    重要:图像标注的对抗性学习文本的视觉解释
    作者: Tao Hu, Chunxia Xiao
    链接:https://arxiv.org/abs/1907.11811

    【6】 Solar Image Restoration with the Cycle-GAN Based on Multi-Fractal Properties of Texture Features
    基于纹理特征多重分形特性的周期GaN太阳图像恢复
    作者: Peng Jia, Dongmei Cai
    链接:https://arxiv.org/abs/1907.12192

    【7】 Generative Adversarial Network for Handwritten Text
    手写文本的生成对抗性网络
    作者: Bo Ji, Tianyi Chen
    备注:12 pages, 7 figures, submitted for WACV 2020
    链接:https://arxiv.org/abs/1907.11845

    [图像/视频检索]:

    【1】 A Benchmark on Tricks for Large-scale Image Retrieval
    一种用于大规模图像检索的Tricks基准测试
    作者: ByungSoo Ko, Youngjoon Kim
    链接:https://arxiv.org/abs/1907.11854

    【2】 Hybrid-Attention based Decoupled Metric Learning for Zero-Shot Image Retrieval
    基于混合关注度的解耦度量学习在零镜头图像检索中的应用
    作者: Binghui Chen, Weihong Deng
    备注:CVPR 2019
    链接:https://arxiv.org/abs/1907.11832

    [行为/时空/光流/姿态/运动]:

    【1】 Optical Flow for Intermediate Frame Interpolation of Multispectral Geostationary Satellite Data
    多光谱地球同步卫星数据中间帧插值的光流
    作者: Thomas Vandal, Ramakrishna Nemani
    链接:https://arxiv.org/abs/1907.12013

    [半/弱/无监督相关]:

    【1】 Self-Supervised Learning for Stereo Reconstruction on Aerial Images
    航空图像立体重建的自监督学习
    作者: Patrick Knöbelreiter, Thomas Pock
    备注:Symposium Prize Paper Award @IGARSS 2018
    链接:https://arxiv.org/abs/1907.12446

    【2】 Recursive Cascaded Networks for Unsupervised Medical Image Registration
    递归级联网络在无监督医学图像配准中的应用
    作者: Shengyu Zhao, Yan Xu
    备注:Accepted to ICCV 2019
    链接:https://arxiv.org/abs/1907.12353

    [跟踪相关]:

    【1】 End-to-End Learning Deep CRF models for Multi-Object Tracking
    用于多目标跟踪的端到端学习深度CRF模型
    作者: Jun Xiang, Jianhua Hou
    链接:https://arxiv.org/abs/1907.12176

    【2】 ROAM: Recurrently Optimizing Tracking Model
    ROAM:递归优化跟踪模型
    作者: Tianyu Yang, Antoni B. Chan
    链接:https://arxiv.org/abs/1907.12006

    【3】 Remote Heart Rate Measurement from Highly Compressed Facial Videos: an End-to-end Deep Learning Solution with Video Enhancement
    来自高度压缩的面部视频的远程心率测量:具有视频增强的端到端深度学习解决方案
    作者: Zitong Yu, Guoying Zhao
    备注:IEEE ICCV2019, accepted
    链接:https://arxiv.org/abs/1907.11921

    【4】 Tell Me What to Track
    告诉我要跟踪什么
    作者: Qi Feng, Stan Sclaroff
    链接:https://arxiv.org/abs/1907.11751

    [迁移学习/domain/主动学习相关]:

    【1】 Fairest of Them All: Establishing a Strong Baseline for Cross-Domain Person ReID
    其中最公平的:为跨域人员Reid建立强大的基线
    作者: Devinder Kumar, Alexander Wong
    链接:https://arxiv.org/abs/1907.12016

    [裁剪/量化/加速相关]:

    【1】 Memory- and Communication-Aware Model Compression for Distributed Deep Learning Inference on IoT
    面向物联网分布式深度学习推理的内存和通信感知模型压缩
    作者: Kartikeya Bhardwaj, Radu Marculescu
    备注:This preprint is for personal use only. The official article will appear as part of the ESWEEK-TECS special issue and will be presented in the International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS), 2019
    链接:https://arxiv.org/abs/1907.11804

    [其他视频相关]:

    【1】 Meta Learning for Task-Driven Video Summarization
    用于任务驱动视频摘要的元学习
    作者: Xuelong Li, Yongsheng Dong
    链接:https://arxiv.org/abs/1907.12342

    【2】 Seeing Things in Random-Dot Videos
    在随机点视频中看东西
    作者: Thomas Dagès, Alfred M. Bruckstein
    链接:https://arxiv.org/abs/1907.12195

    [其他]:

    【1】 Towards Automatic Screening of Typical and Atypical Behaviors in Children With Autism
    自闭症儿童典型和非典型行为的自动筛选
    作者: Andrew Cook, Matthew Johnson
    备注:7 pages, 5 figures and 6 tables. 6th IEEE International Conference on Data Science and Advanced Analytics (DSAA) 2019
    链接:https://arxiv.org/abs/1907.12537

    【2】 Benefiting from Multitask Learning to Improve Single Image Super-Resolution
    利用多任务学习提高单幅图像超分辨率
    作者: Mohammad Saeed Rad, Jean-Philippe Thiran
    备注:accepted at Neurocomputing (Special Issue on Deep Learning for Image Super-Resolution), 2019
    链接:https://arxiv.org/abs/1907.12488

    【3】 Salient Slices: Improved Neural Network Training and Performance with Image Entropy
    显著切片:改进的神经网络训练和图像熵性能
    作者: Steven J. Frank, Andrea M. Frank
    链接:https://arxiv.org/abs/1907.12436

    【4】 Consensus Feature Network for Scene Parsing
    用于场景解析的共识特征网络
    作者: Tianyi Wu, Yongdong Zhang
    链接:https://arxiv.org/abs/1907.12411

    【5】 Goal-Driven Sequential Data Abstraction
    目标驱动的顺序数据抽象
    作者: Umar Riaz Muhammad, Yi-Zhe Song
    备注:Accepted at ICCV 2019
    链接:https://arxiv.org/abs/1907.12336

    【6】 V-PROM: A Benchmark for Visual Reasoning Using Visual Progressive Matrices
    V-PROM:使用可视渐进矩阵的可视推理基准
    作者: Damien Teney, Anton van den Hengel
    链接:https://arxiv.org/abs/1907.12271

    【7】 AirFace:Lightweight and Efficient Model for Face Recognition
    AirFace:轻量级高效的人脸识别模型
    作者: Xianyang Li
    链接:https://arxiv.org/abs/1907.12256

    【8】 Silhouette Guided Point Cloud Reconstruction beyond Occlusion
    轮廓导引的遮挡后的点云重建
    作者: Chuhang Zou, Derek Hoiem
    链接:https://arxiv.org/abs/1907.12253

    【9】 Automatic Registration between Cone-Beam CT and Scanned Surface via Deep-Pose Regression Neural Networks and Clustered Similarities
    基于深度姿态回归神经网络和聚类相似性的锥束CT与扫描表面自动配准
    作者: Minyoung Chung, Yeong-Gil Shin
    链接:https://arxiv.org/abs/1907.12250

    【10】 KNEEL: Knee Anatomical Landmark Localization Using Hourglass Networks
    膝部:利用沙漏网络进行膝关节解剖地标定位
    作者: Aleksei Tiulpin, Simo Saarakkala
    链接:https://arxiv.org/abs/1907.12237

    【11】 Multi-Granularity Fusion Network for Proposal and Activity Localization: Submission to ActivityNet Challenge 2019 Task 1 and Task 2
    用于提案和活动本地化的多粒度融合网络:提交给ActivityNet挑战2019任务1和任务2
    作者: Haisheng Su, Shuming Liu
    链接:https://arxiv.org/abs/1907.12223

    【12】 Enforcing geometric constraints of virtual normal for depth prediction
    加强虚拟法线的几何约束进行深度预测
    作者: Yin Wei, Youliang Yan
    备注:Appearing in Proc. Int. Conf. Computer Vision 2019. Code is available at: this https URL
    链接:https://arxiv.org/abs/1907.12209

    【13】 ChaLearn Looking at People: IsoGD and ConGD Large-scale RGB-D Gesture Recognition
    ChaLearn看人:IsoGD和ConGD大规模RGB-D手势识别
    作者: Jun Wan, Stan Z. Li
    链接:https://arxiv.org/abs/1907.12193

    【14】 Iris Recognition for Personal Identification using LAMSTAR neural network
    LAMSTAR神经网络用于个人身份识别的虹膜识别
    作者: Shideh Homayon, Mahdi Salarian
    链接:https://arxiv.org/abs/1907.12145

    【15】 An Empirical Study on Leveraging Scene Graphs for Visual Question Answering
    利用场景图进行视觉问答的实证研究
    作者: Cheng Zhang, Dong Xuan
    备注:Accepted as oral presentation at BMVC 2019
    链接:https://arxiv.org/abs/1907.12133

    【16】 Dilated Point Convolutions: On the Receptive Field of Point Convolutions
    扩张点卷积:关于点卷积的接受场
    作者: Francis Engelmann, Bastian Leibe
    链接:https://arxiv.org/abs/1907.12046

    【17】 Learning Wear Patterns on Footwear Outsoles Using Convolutional Neural Networks
    用卷积神经网络学习鞋底磨损模式
    作者: Xavier Francis, Soheil Varastehpour
    链接:https://arxiv.org/abs/1907.12005

    【18】 Attribute-Guided Deep Polarimetric Thermal-to-visible Face Recognition
    属性引导的深度偏振热-可见光人脸识别
    作者: Seyed Mehdi Iranmanesh, Nasser M. Nasrabadi
    链接:https://arxiv.org/abs/1907.11980

    【19】 Learning Body Shape and Pose from Dense Correspondences
    从密集对应中学习身体形状和姿势
    作者: Yusuke Yoshiyasu, Lucas Gamez
    链接:https://arxiv.org/abs/1907.11955

    【20】 Triangulation: Why Optimize?
    三角剖分:为什么要优化?
    作者: Seong Hun Lee, Javier Civera
    备注:Accepted to BMVC2019 (oral presentation)
    链接:https://arxiv.org/abs/1907.11917

    【21】 Context Model for Pedestrian Intention Prediction using Factored Latent-Dynamic Conditional Random Fields
    基于因子潜在动态条件随机场的行人意向预测上下文模型
    作者: Satyajit Neogi, Justin Dauwels
    链接:https://arxiv.org/abs/1907.11881

    【22】 Genetic Deep Learning for Lung Cancer Screening
    遗传深度学习在肺癌筛查中的应用
    作者: Hunter Park, Connor Monahan
    链接:https://arxiv.org/abs/1907.11849

    【23】 Learning Instance-wise Sparsity for Accelerating Deep Models
    学习实例稀疏性加速深度模型
    作者: Chuanjian Liu, Chang Xu
    备注:Accepted by IJCAI 2019
    链接:https://arxiv.org/abs/1907.11840

    【24】 Attribute Aware Pooling for Pedestrian Attribute Recognition
    用于行人属性识别的属性感知池
    作者: Kai Han, Chang Xu
    备注:Accepted by IJCAI 2019
    链接:https://arxiv.org/abs/1907.11837

    【25】 Reprojection R-CNN: A Fast and Accurate Object Detector for 360° Images
    再投影R-CNN:一种快速准确的360°图像物体检测器
    作者: Pengyu Zhao, Yunhai Tong
    链接:https://arxiv.org/abs/1907.11830

    【26】 To Learn or Not to Learn: Analyzing the Role of Learning for Navigation in Virtual Environments
    学习还是不学习:虚拟环境中导航学习的角色分析
    作者: Noriyuki Kojima, Jia Deng
    链接:https://arxiv.org/abs/1907.11770

    【27】 Solving the Robot-World Hand-Eye(s) Calibration Problem with Iterative Methods
    用迭代方法求解机器人世界手眼标定问题
    作者: Amy Tabb, Khalil M. Ahmad Yousef
    链接:https://arxiv.org/abs/1907.12425

    【28】 Charting the Right Manifold: Manifold Mixup for Few-shot Learning
    绘制正确的流形:流形混合用于少量学习
    作者: Puneet Mangla, Balaji Krishnamurthy
    链接:https://arxiv.org/abs/1907.12087

    【29】 Two-Stream CNN with Loose Pair Training for Multi-modal AMD Categorization
    基于松散对训练的双流CNN多模态AMD分类
    作者: Weisen Wang, Xirong Li
    备注:accepted by MICCAI 2019
    链接:https://arxiv.org/abs/1907.12023

    【30】 What Should I Ask? Using Conversationally Informative Rewards for Goal-Oriented Visual Dialog
    我该问什么?为面向目标的可视对话使用会话信息性奖励
    作者: Pushkar Shukla, William Yang Wang
    备注:Accepted to ACL 2019
    链接:https://arxiv.org/abs/1907.12021

    【31】 Learnable Parameter Similarity
    可学习参数相似性
    作者: Guangcong Wang, Guangrun Wang
    链接:https://arxiv.org/abs/1907.11943

    【32】 Deep learning-based prediction of kinetic parameters from myocardial perfusion MRI
    基于深度学习的心肌灌注MRI动力学参数预测
    作者: Cian M. Scannell, Mitko Veta
    备注:Medical Imaging with Deep Learning: MIDL 2019 Extended Abstract Track. MIDL 2019 [arXiv:1907.08612]
    链接:https://arxiv.org/abs/1907.11899

    【33】 Effective and efficient ROI-wise visual encoding using an end-to-end CNN regression model and selective optimization
    使用端到端CNN回归模型和选择性优化的有效且高效的ROI-wise视觉编码
    作者: Kai Qiao, Bin Yan
    链接:https://arxiv.org/abs/1907.11885

    【34】 Momentum-Net: Fast and convergent iterative neural network for inverse problems
    动量网:快速收敛的反问题迭代神经网络
    作者: Il Yong Chun, Jeffrey A. Fessler
    链接:https://arxiv.org/abs/1907.11818

    【35】 Deep MRI Reconstruction: Unrolled Optimization Algorithms Meet Neural Networks
    深度MRI重建:展开优化算法满足神经网络
    作者: Dong Liang, Leslie Ying
    链接:https://arxiv.org/abs/1907.11711

    翻译:腾讯翻译君

    相关文章

      网友评论

        本文标题:计算机视觉每日论文速递[07.30]

        本文链接:https://www.haomeiwen.com/subject/prrgrctx.html