美文网首页arXiv daily
计算机视觉每日论文速递[07.31]

计算机视觉每日论文速递[07.31]

作者: arXiv每日论文速递 | 来源:发表于2019-07-31 10:34 被阅读35次

    同步wx公号(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69篇

    [检测分类相关]:

    【1】 Pay attention to the activations: a modular attention mechanism for fine-grained image recognition
    注意激活:细粒度图像识别的模块化注意机制
    作者: Pau Rodríguez López, Jordi Gonzàlez Sabaté
    链接:https://arxiv.org/abs/1907.13075

    【2】 Attention Filtering for Multi-person Spatiotemporal Action Detection on Deep Two-Stream CNN Architectures
    深层双流CNN体系结构中多人时空行为检测的注意过滤
    作者: João Antunes, Daniel Siewiorek
    链接:https://arxiv.org/abs/1907.12919

    【3】 Reg R-CNN: Lesion Detection and Grading under Noisy Labels
    REG R-CNN:噪声标签下的病变检测和分级
    作者: Gregor N. Ramien, Klaus H. Maier-Hein
    链接:https://arxiv.org/abs/1907.12915

    【4】 Detecting Spoofing Attacks Using VGG and SincNet: BUT-Omilia Submission to ASVspoof 2019 Challenge
    使用VGG和SincNet检测欺骗攻击:但是-Omilia提交给ASVspoof 2019挑战
    作者: Hossein Zeinali, Jan "Honza'' Černocký
    链接:https://arxiv.org/abs/1907.12908

    【5】 Slot Based Image Augmentation System for Object Detection
    用于目标检测的基于槽的图像增强系统
    作者: Yingwei Zhou
    链接:https://arxiv.org/abs/1907.12900

    【6】 PointHop: An Explainable Machine Learning Method for Point Cloud Classification
    PointHop:一种可解释的点云分类机器学习方法
    作者: Min Zhang, C.-C. Jay Kuo
    链接:https://arxiv.org/abs/1907.12766

    【7】 MoBiNet: A Mobile Binary Network for Image Classification
    MoBiNet:一种用于图像分类的移动二值网络
    作者: Hai Phan, Zhiqiang Shen
    链接:https://arxiv.org/abs/1907.12629

    【8】 Screening Mammogram Classification with Prior Exams
    用前期检查筛选乳房X线片分类
    作者: Jungkyu Park, Krzysztof J. Geras
    备注:MIDL 2019 [arXiv:1907.08612]
    链接:https://arxiv.org/abs/1907.13057

    【9】 Particle Swarm Optimisation for Evolving Deep Neural Networks for Image Classification by Evolving and Stacking Transferable Blocks
    进化深层神经网络的粒子群优化算法及其在图像分类中的应用
    作者: Bin Wang, Mengjie Zhang
    备注:Under review of Australasian Joint Conference on Artificial Intelligence 2019
    链接:https://arxiv.org/abs/1907.12659

    【10】 Task Classification Model for Visual Fixation, Exploration, and Search
    用于视觉固定、探索和搜索的任务分类模型
    作者: Ayush Kumar, Klaus Mueller
    链接:https://arxiv.org/abs/1907.12635

    [分割/语义相关]:

    【1】 Deblurring Face Images using Uncertainty Guided Multi-Stream Semantic Networks
    基于不确定性引导的多流语义网络人脸图像去模糊
    作者: Rajeev Yasarla (Student Member, IEEE)
    备注:TIP 2019 submission
    链接:https://arxiv.org/abs/1907.13106

    【2】 Grid Saliency for Context Explanations of Semantic Segmentation
    语义切分上下文解释的网格显著性
    作者: Lukas Hoyer, Volker Fischer
    链接:https://arxiv.org/abs/1907.13054

    【3】 Deep Learning architectures for generalized immunofluorescence based nuclear image segmentation
    基于广义免疫荧光的核图像分割的深度学习结构
    作者: Florian Kromp, Allan Hanbury
    链接:https://arxiv.org/abs/1907.12975

    【4】 2D and 3D Segmentation of uncertain local collagen fiber orientations in SHG microscopy
    SHG显微镜中不确定局部胶原纤维取向的二维和三维分割
    作者: Lars Schmarje, Reinhard Koch
    链接:https://arxiv.org/abs/1907.12868

    【5】 ColorMapGAN: Unsupervised Domain Adaptation for Semantic Segmentation Using Color Mapping Generative Adversarial Networks
    ColorMapGAN:基于颜色映射生成对抗性网络的无监督领域自适应语义分割
    作者: Onur Tasar, Pierre Alliez
    链接:https://arxiv.org/abs/1907.12859

    【6】 Orientation-aware Semantic Segmentation on Icosahedron Spheres
    基于二十面体球体的方位感知语义分割
    作者: Chao Zhang, Roberto Cipolla
    备注:9 pages, accepted to iccv 2019
    链接:https://arxiv.org/abs/1907.12849

    【7】 An Empirical Study of Propagation-based Methods for Video Object Segmentation
    基于传播的视频对象分割方法的实证研究
    作者: Hengkai Guo, Xuefeng Xiao
    备注:The 2019 DAVIS Challenge on Video Object Segmentation - CVPR Workshops
    链接:https://arxiv.org/abs/1907.12769

    【8】 Lung image segmentation by generative adversarial networks
    基于生成对抗性网络的肺图像分割
    作者: Jiaxin Cai, Hongfeng Zhu
    链接:https://arxiv.org/abs/1907.13033

    【9】 Attention Guided Network for Retinal Image Segmentation
    注意力引导网络在视网膜图像分割中的应用
    作者: Shihao Zhang, Yanwu Xu
    备注:Accepted by MICCAI 2019. Project page: (this https URL)
    链接:https://arxiv.org/abs/1907.12930

    【10】 Automatic Lesion Boundary Segmentation in Dermoscopic Images with Ensemble Deep Learning Methods
    基于集成深度学习方法的皮肤镜图像病变边界自动分割
    作者: Manu Goyal, Moi Hoon Yap
    链接:https://arxiv.org/abs/1902.00809

    [GAN/对抗式/生成式相关]:

    【1】 ISEA: Image Steganalysis using Evolutionary Algorithms
    ISEA:使用进化算法的图像隐写分析
    作者: Farid Ghareh Mohammadi, Hamid R. Arabnia
    链接:https://arxiv.org/abs/1907.12914

    【2】 Data augmentation with Symbolic-to-Real Image Translation GANs for Traffic Sign Recognition
    用于交通标志识别的符号-真实图像转换GANS数据增强
    作者: Nour Soufi, Matias Valdenegro-Toro
    链接:https://arxiv.org/abs/1907.12902

    【3】 Increasing Shape Bias in ImageNet-Trained Networks Using Transfer Learning and Domain-Adversarial Methods
    使用转移学习和领域对抗性方法在ImageNet训练的网络中增加形状偏差
    作者: Francis Brochu
    链接:https://arxiv.org/abs/1907.12892

    【4】 Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding
    并不是所有的对抗实例都需要复杂的防御:使用基于IQR的logit阈值识别过度优化的对抗实例
    作者: Utku Ozbulak, Wesley De Neve
    备注:Accepted for the 2019 International Joint Conference on Neural Networks (IJCNN-19)
    链接:https://arxiv.org/abs/1907.12744

    [行为/时空/光流/姿态/运动]:

    【1】 SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition
    SkeleMotion:一种新的基于运动信息的骨骼关节序列表示方法
    作者: Carlos Caetano, William Robson Schwartz
    备注:16-th IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS2019)
    链接:https://arxiv.org/abs/1907.13025

    【2】 Preterm infants' limb-pose estimation from depth images using convolutional neural networks
    基于卷积神经网络的深度图像早产儿肢体姿势估计
    作者: Sara Moccia, Emanuele Frontoni
    链接:https://arxiv.org/abs/1907.12949

    【3】 EmoCo: Visual Analysis of Emotion Coherence in Presentation Videos
    EmoCo:演示视频中情感连贯性的视觉分析
    作者: Haipeng Zeng, Huamin Qu
    备注:11 pages, 8 figures. Accepted by IEEE VAST 2019
    链接:https://arxiv.org/abs/1907.12918

    【4】 Open Set Domain Adaptation for Image and Action Recognition
    用于图像和动作识别的开集域自适应
    作者: Pau Panareda Busto, Juergen Gall
    链接:https://arxiv.org/abs/1907.12865

    [半/弱/无监督相关]:

    【1】 Weakly Supervised Body Part Parsing with Pose based Part Priors
    基于姿势优先的弱监督人体部位分析
    作者: Zhengyuan Yang, Jiebo Luo
    链接:https://arxiv.org/abs/1907.13051

    【2】 Weakly Supervised Object Localization using Min-Max Entropy: an Interpretable Framework
    基于最小-最大熵的弱监督对象定位:一种可解释的框架
    作者: Soufiane Belharbi, Eric Granger
    链接:https://arxiv.org/abs/1907.12934

    【3】 Distill-to-Label: Weakly Supervised Instance Labeling Using Knowledge Distillation
    提取到标签:使用知识蒸馏的弱监督实例标签
    作者: Jayaraman J. Thiagarajan, Alexandros Karagyris
    链接:https://arxiv.org/abs/1907.12926

    【4】 Unsupervised Separation of Dynamics from Pixels
    动态与像素的无监督分离
    作者: Silvia Chiappa, Ulrich Paquet
    链接:https://arxiv.org/abs/1907.12906

    【5】 Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction
    多角度点云-VAE:基于联合自重构和半预测的多角度三维点云无监督特征学习
    作者: Zhizhong Han, Matthias Zwicker
    备注:To appear at ICCV 2019
    链接:https://arxiv.org/abs/1907.12704

    [跟踪相关]:

    【1】 Tracking Holistic Object Representations
    跟踪整体对象表示
    作者: Axel Sauer, Sami Haddadin
    备注:Accepted for oral presentation at BMVC 2019
    链接:https://arxiv.org/abs/1907.12920

    【2】 End-to-end Recurrent Multi-Object Tracking and Trajectory Prediction with Relational Reasoning
    基于关系推理的端到端循环多目标跟踪与轨迹预测
    作者: Fabian B. Fuchs, Ingmar Posner
    链接:https://arxiv.org/abs/1907.12887

    【3】 Deep Learning in Video Multi-Object Tracking: A Survey
    视频多目标跟踪中的深度学习:综述
    作者: Gioele Ciaparrone, Francisco Herrera
    链接:https://arxiv.org/abs/1907.12740

    [迁移学习/domain/主动学习相关]:

    【1】 Temporal Attentive Alignment for Large-Scale Video Domain Adaptation
    大规模视频域自适应的时间注意对齐
    作者: Min-Hung Chen, Jian Zheng
    备注:International Conference on Computer Vision (ICCV) 2019. Code and data: this http URL
    链接:https://arxiv.org/abs/1907.12743

    【2】 Artistic Domain Generalisation Methods are Limited by their Deep Representations
    艺术领域综合方法受深度表征的限制
    作者: Padraig Boulton, Peter Hall
    链接:https://arxiv.org/abs/1907.12622

    [视频理解VQA/caption等]:

    【1】 Watch It Twice: Video Captioning with a Refocused Video Encoder
    观看两次:使用重新聚焦的视频编码器的视频字幕
    作者: Xiangxi Shi, Jiuxiang Gu
    链接:https://arxiv.org/abs/1907.12905

    [数据集dataset]:

    【1】 Covering up bias in CelebA-like datasets with Markov blankets: A post-hoc cure for attribute prior avoidance
    用马尔可夫毯子掩盖类CelebA数据集中的偏差:属性先验避免的一种后特效疗法
    作者: Vinay Uday Prabhu, John Whaley
    备注:Accepted for presentation at the first workshop on Invertible Neural Networks and Normalizing Flows (ICML 2019), Long Beach, CA, USA
    链接:https://arxiv.org/abs/1907.12917

    【2】 Exploring large scale public medical image datasets
    探索大规模公共医学图像数据集
    作者: Luke Oakden-Rayner
    链接:https://arxiv.org/abs/1907.12720

    [其他视频相关]:

    【1】 Temporal Localization of Moments in Video Collections with Natural Language
    基于自然语言的视频集合中矩的时间定位
    作者: Victor Escorcia, Bryan Russell
    链接:https://arxiv.org/abs/1907.12763

    [其他]:

    【1】 Deformable Filter Convolution for Point Cloud Reasoning
    用于点云推理的可变形滤波卷积
    作者: Yuwen Xiong, Raquel Urtasun
    链接:https://arxiv.org/abs/1907.13079

    【2】 Efficient Method for Categorize Animals in the Wild
    一种高效的野外动物分类方法
    作者: Abulikemu Abuduweili, Xingchen Tao
    链接:https://arxiv.org/abs/1907.13037

    【3】 Bilateral Operators for Functional Maps
    函数映射的双边算子
    作者: Gautam Pai, Ron Kimmel
    链接:https://arxiv.org/abs/1907.12993

    【4】 FingerNet: Pushing The Limits of Fingerprint Recognition Using Convolutional Neural Network
    FingerNet:利用卷积神经网络突破指纹识别的极限
    作者: Shervin Minaee, Amirali Abdolrashidi
    备注:arXiv admin note: substantial text overlap with arXiv:1907.09380
    链接:https://arxiv.org/abs/1907.12956

    【5】 RNN-based Online Handwritten Character Recognition Using Accelerometer and Gyroscope Data
    使用加速度计和陀螺仪数据的基于RNN的在线手写字符识别
    作者: Davit Soselia, Levan Shugliashvili
    链接:https://arxiv.org/abs/1907.12935

    【6】 Object as Distribution
    对象作为分布
    作者: Li Ding, Lex Fridman
    备注:NeurIPS 2019
    链接:https://arxiv.org/abs/1907.12929

    【7】 Improved Super-Resolution Convolution Neural Network for Large Images
    改进的大图像超分辨率卷积神经网络
    作者: Junyu (Jason) Wang, Rong Song
    链接:https://arxiv.org/abs/1907.12928

    【8】 Unifying Structure Analysis and Surrogate-driven Function Regression for Glaucoma OCT Image Screening
    统一结构分析和代理驱动函数回归在青光眼OCT图像筛选中的应用
    作者: Xi Wang, Pheng-Ann Heng
    备注:9 pages, 2 figures, MICCAI2019
    链接:https://arxiv.org/abs/1907.12927

    【9】 Look Further to Recognize Better: Learning Shared Topics and Category-Specific Dictionaries for Open-Ended 3D Object Recognition
    进一步了解更好:学习共享主题和类别特定词典,用于开放式3D对象识别
    作者: S. Hamidreza Kasaei
    备注:arXiv admin note: text overlap with arXiv:1902.03057
    链接:https://arxiv.org/abs/1907.12924

    【10】 Evaluation of Distance Measures for Feature based Image Registration using AlexNet
    使用AlexNet评估基于特征的图像配准的距离度量
    作者: K.Kavitha, B. Thirumala Rao
    链接:https://arxiv.org/abs/1907.12921

    【11】 DANTE: Deep Affinity Network for Clustering Conversational Interactants
    Dante:用于会话交互者聚类的深度亲和力网络
    作者: Mason Swofford, Silvio Savarese
    链接:https://arxiv.org/abs/1907.12910

    【12】 Learned Image Downscaling for Upscaling using Content Adaptive Resampler
    使用内容自适应重采样器进行向上缩放的学习图像缩小
    作者: Wanjie Sun, Zhenzhong Chen
    链接:https://arxiv.org/abs/1907.12904

    【13】 A Multi-Scale Mapping Approach Based on a Deep Learning CNN Model for Reconstructing High-Resolution Urban DEMs
    基于深度学习CNN模型的高分辨率城市DEM重建的多比例尺映射方法
    作者: Ling Jiang, Andrea Soltoggio
    链接:https://arxiv.org/abs/1907.12898

    【14】 Safe Augmentation: Learning Task-Specific Transformations from Data
    安全增强:从数据中学习特定于任务的转换
    作者: Irynei Baran, Arseny Kravchenko
    链接:https://arxiv.org/abs/1907.12896

    【15】 4X4 Census Transform
    4x4人口普查转型
    作者: Olivier Rukundo
    链接:https://arxiv.org/abs/1907.12891

    【16】 CoachAI: A Project for Microscopic Badminton Match Data Collection and Tactical Analysis
    CoachAI:微观羽毛球比赛数据采集与战术分析项目
    作者: Tzu-Han Hsu, Yu-Tai Ching
    链接:https://arxiv.org/abs/1907.12888

    【17】 LEAF-QA: Locate, Encode & Attend for Figure Question Answering
    LEAF-QA:定位、编码和参加图形问答
    作者: Ritwick Chaudhry, Ajay Joshi
    链接:https://arxiv.org/abs/1907.12861

    【18】 Towards Pure End-to-End Learning for Recognizing Multiple Text Sequences from an Image
    面向从图像中识别多个文本序列的纯端到端学习
    作者: Xu Zhenlong, Pu shiliang
    链接:https://arxiv.org/abs/1907.12791

    【19】 Statistical Descriptors-based Automatic Fingerprint Identification: Machine Learning Approaches
    基于统计描述符的自动指纹识别:机器学习方法
    作者: Hamid Jan, Gautam Srivastava
    链接:https://arxiv.org/abs/1907.12741

    【20】 Deep Learning For Face Recognition: A Critical Analysis
    人脸识别的深度学习:批判性分析
    作者: Andrew Jason Shepley
    链接:https://arxiv.org/abs/1907.12739

    【21】 Propose-and-Attend Single Shot Detector
    提议并参加单发探测器
    作者: Ho-Deok Jang, In So Kweon
    链接:https://arxiv.org/abs/1907.12736

    【22】 Mapping road safety features from streetview imagery: A deep learning approach
    从街景图像绘制道路安全特征:一种深度学习方法
    作者: Arpan Sainju, Zhe Jiang
    链接:https://arxiv.org/abs/1907.12647

    【23】 Camera Exposure Control for Robust Robot Vision with Noise-Aware Image Quality Assessment
    基于噪声感知图像质量评估的鲁棒机器人视觉相机曝光控制
    作者: Ukcheol Shin, In So Kweon
    备注:8 pages,6 figures, accepted in IROS2019
    链接:https://arxiv.org/abs/1907.12646

    【24】 GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
    创世:以对象为中心的潜在表征的生成性场景推理和采样
    作者: Martin Engelcke, Ingmar Posner
    备注:Submitted to the 3rd Conference on Robot Learning (CoRL 2019)
    链接:https://arxiv.org/abs/1907.13052

    【25】 Synthesis and Inpainting-Based MR-CT Registration for Image-Guided Thermal Ablation of Liver Tumors
    基于合成和修复的MR-CT图像引导热消融肝脏肿瘤配准
    作者: Dongming Wei, Qian Wang
    备注:Accepted in MICCAI 2019
    链接:https://arxiv.org/abs/1907.13020

    【26】 Inertial nonconvex alternating minimizations for the image deblurring
    图像去模糊的惯性非凸交替最小化
    作者: Tao Sun, Hao Jiang
    链接:https://arxiv.org/abs/1907.12945

    【27】 Confounder-Aware Visualization of ConvNets
    ConvNets的混杂感知可视化
    作者: Qingyu Zhao, Kilian M. Pohl
    链接:https://arxiv.org/abs/1907.12727

    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[07.31]

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