美文网首页arXiv daily
计算机视觉每日论文速递[07.29]

计算机视觉每日论文速递[07.29]

作者: arXiv每日论文速递 | 来源:发表于2019-07-29 10:00 被阅读49次

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

    今日共计42篇

    [检测分类相关]:

    【1】 Deep Learning for Classification and Severity Estimation of Coffee Leaf Biotic Stress
    深度学习用于咖啡叶生物胁迫的分类和严重程度估计
    作者: J. G. M. Esgario, J. A. Ventura
    链接:https://arxiv.org/abs/1907.11561

    【2】 Report on UG^2+ Challenge Track 1: Assessing Algorithms to Improve Video Object Detection and Classification from Unconstrained Mobility Platforms
    UG^2+挑战轨道1:改进无约束移动平台视频对象检测和分类的评估算法报告
    作者: Sreya Banerjee, Walter J. Scheirer
    链接:https://arxiv.org/abs/1907.11529

    【3】 DCT-CompCNN: A Novel Image Classification Network Using JPEG Compressed DCT Coefficients
    DCT-CompCNN:一种使用JPEG压缩DCT系数的新型图像分类网络
    作者: Bulla Rajesh, Shubham Srivastava
    链接:https://arxiv.org/abs/1907.11503

    【4】 Multi-level Domain Adaptive learning for Cross-Domain Detection
    用于跨域检测的多级域自适应学习
    作者: Rongchang Xie, Li Zhang
    备注:Accepted to the TASK-CV workshop at ICCV 2019
    链接:https://arxiv.org/abs/1907.11484

    【5】 Product Image Recognition with Guidance Learning and Noisy Supervision
    基于指导学习和噪声监控的产品图像识别
    作者: Qing Li, Yu Qiao
    链接:https://arxiv.org/abs/1907.11384

    【6】 NoduleNet: Decoupled False Positive Reductionfor Pulmonary Nodule Detection and Segmentation
    NobileNet:用于肺结节检测和分割的解耦假阳性降低
    作者: Hao Tang, Xiaohui Xie
    备注:Accepted to MICCAI 2019
    链接:https://arxiv.org/abs/1907.11320

    【7】 A Novel Approach for Robust Multi Human Action Detection and Recognition based on 3-Dimentional Convolutional Neural Networks
    一种基于三维卷积神经网络的鲁棒多人体动作检测与识别新方法
    作者: Noor Almaadeed, Azeddine Beghdadi
    链接:https://arxiv.org/abs/1907.11272

    【8】 AVEC 2019 Workshop and Challenge: State-of-Mind, Detecting Depression with AI, and Cross-Cultural Affect Recognition
    Avec 2019研讨会和挑战:心态,用人工智能检测抑郁,以及跨文化情感识别
    作者: Fabien Ringeval, Maja Pantic
    链接:https://arxiv.org/abs/1907.11510

    [分割/语义相关]:

    【1】 Semantic Deep Intermodal Feature Transfer: Transferring Feature Descriptors Between Imaging Modalities
    语义深度多模态特征转移:在成像模态之间转移特征描述符
    作者: Sebastian P. Kleinschmidt, Bernardo Wagner
    链接:https://arxiv.org/abs/1907.11436

    【2】 A Comparative Study of High-Recall Real-Time Semantic Segmentation Based on Swift Factorized Network
    基于SWIFT因式网络的高召回率实时语义切分比较研究
    作者: Kaite Xiang, Kailun Yang
    备注:14 pages, 11figures, SPIE Security + Defence 2019
    链接:https://arxiv.org/abs/1907.11394

    【3】 DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation
    DABNet:面向实时语义分割的深度非对称瓶颈
    作者: Gen Li, Joongkyu Kim
    备注:Accepted to BMVC 2019
    链接:https://arxiv.org/abs/1907.11357

    【4】 Self-Adaptive 2D-3D Ensemble of Fully Convolutional Networks for Medical Image Segmentation
    用于医学图像分割的全卷积网络自适应2D-3D集成
    作者: Maria G. Baldeon Calisto, Susana K. Lai-Yuen
    链接:https://arxiv.org/abs/1907.11587

    【5】 Annotation-Free Cardiac Vessel Segmentation via Knowledge Transfer from Retinal Images
    基于视网膜图像知识转移的无注释心脏血管分割
    作者: Fei Yu, Li Zhang
    备注:Accepted at MICCAI 2019
    链接:https://arxiv.org/abs/1907.11483

    【6】 Recurrent Aggregation Learning for Multi-View Echocardiographic Sequences Segmentation
    用于多视角超声心动图序列分割的循环聚集学习
    作者: Ming Li, Shuo Li
    备注:MICCAI 2019
    链接:https://arxiv.org/abs/1907.11292

    【7】 Boundary loss for highly unbalanced segmentation
    高度不平衡分割的边界损失
    作者: Hoel Kervadec, Ismail Ben Ayed
    备注:Talk at MIDL 2019 [arXiv:1907.08612]
    链接:https://arxiv.org/abs/1812.07032

    [GAN/对抗式/生成式相关]:

    【1】 On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method
    利用无梯度优化和算子分裂方法设计黑盒对抗性例子
    作者: Pu Zhao, Xue Lin
    备注:accepted by ICCV 2019
    链接:https://arxiv.org/abs/1907.11684

    【2】 LinearConv: Regenerating Redundancy in Convolution Filters as Linear Combinations for Parameter Reduction
    LinearConv:将卷积滤波器中的冗余重新生成为用于参数缩减的线性组合
    作者: Kumara Kahatapitiya, Ranga Rodrigo
    链接:https://arxiv.org/abs/1907.11432

    【3】 UGAN: Untraceable GAN for Multi-Domain Face Translation
    UGAN:用于多域人脸翻译的不可追踪的GAN
    作者: Defa Zhu, Guodong Guo
    链接:https://arxiv.org/abs/1907.11418

    [行为/时空/光流/姿态/运动]:

    【1】 Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
    基于金字塔卷积LSTM的光流估计的无监督学习
    作者: Shuosen Guan, Wei-Shi Zheng
    备注:IEEE International Conference on Multimedia and Expo(ICME). 2019
    链接:https://arxiv.org/abs/1907.11628

    【2】 Using 3D Convolutional Neural Networks to Learn Spatiotemporal Features for Automatic Surgical Gesture Recognition in Video
    利用三维卷积神经网络学习时空特征用于视频手术手势自动识别
    作者: Isabel Funke, Stefanie Speidel
    备注:Accepted at MICCAI 2019. Source code will be made available
    链接:https://arxiv.org/abs/1907.11454

    [半/弱/无监督相关]:

    【1】 Unsupervised Learning Framework of Interest Point Via Properties Optimization
    基于属性优化的兴趣点无监督学习框架
    作者: Pei Yan, Cai Wen
    链接:https://arxiv.org/abs/1907.11375

    [Re-id相关]:

    【1】 MVB: A Large-Scale Dataset for Baggage Re-Identification and Merged Siamese Networks
    MVB:用于行李重新识别和合并暹罗网络的大规模数据集
    作者: Zhulin Zhang, Li Zhang
    链接:https://arxiv.org/abs/1907.11366

    [视频理解VQA/caption等]:

    【1】 Cooperative image captioning
    协同图像字幕
    作者: Gilad Vered, Gal Chechik
    链接:https://arxiv.org/abs/1907.11565

    [其他视频相关]:

    【1】 A Fully-Convolutional Neural Network for Background Subtraction of Unseen Videos
    一种用于不可见视频背景减除的全卷积神经网络
    作者: M. Ozan Tezcan, Prakash Ishwar
    链接:https://arxiv.org/abs/1907.11371

    [其他]:

    【1】 Differential Scene Flow from Light Field Gradients
    来自光场梯度的差分场景流
    作者: Sizhuo Ma, Mohit Gupta
    链接:https://arxiv.org/abs/1907.11637

    【2】 Learning Transparent Object Matting
    学习透明对象遮罩
    作者: Guanying Chen, Kwan-Yee K. Wong
    备注:To appear in International Journal of Computer Vision, Project Page: this https URL arXiv admin note: substantial text overlap with arXiv:1803.04636
    链接:https://arxiv.org/abs/1907.11544

    【3】 Minimal Solvers for Rectifying from Radially-Distorted Scales and Change of Scales
    径向畸变比例尺校正和比例尺变化的最小求解器
    作者: James Pritts, Ondřej Chum
    备注:arXiv admin note: text overlap with arXiv:1807.06110
    链接:https://arxiv.org/abs/1907.11539

    【4】 Context-Aware Multipath Networks
    上下文感知多路径网络
    作者: Dumindu Tissera, Ranga Rodrigo
    链接:https://arxiv.org/abs/1907.11519

    【5】 Outfit Compatibility Prediction and Diagnosis with Multi-Layered Comparison Network
    基于多层比较网络的装备相容性预测与诊断
    作者: Xin Wang, Yueqi Zhong
    链接:https://arxiv.org/abs/1907.11496

    【6】 Single Level Feature-to-Feature Forecasting with Deformable Convolutions
    具有可变形卷积的单层特征到特征预测
    作者: Josip Šarić, Siniša Šegvić
    备注:Accepted to German Conference on Pattern Recognition 2019. 19 pages, 8 figures, 7 tables
    链接:https://arxiv.org/abs/1907.11475

    【7】 Context-Integrated and Feature-Refined Network for Lightweight Urban Scene Parsing
    用于轻量级城市场景解析的上下文集成和特征细化网络
    作者: Bin Jiang, Junsong Yuan
    链接:https://arxiv.org/abs/1907.11474

    【8】 Multiple Human Association between Top and Horizontal Views by Matching Subjects' Spatial Distributions
    通过匹配主体的空间分布实现俯视图和水平视图之间的多人关联
    作者: Ruize Han, Song Wang
    链接:https://arxiv.org/abs/1907.11458

    【9】 Universal Pooling -- A New Pooling Method for Convolutional Neural Networks
    通用池化-一种新的卷积神经网络池化方法
    作者: Junhyuk Hyun, Euntai Kim
    链接:https://arxiv.org/abs/1907.11440

    【10】 Improving Generalization via Attribute Selection on Out-of-the-box Data
    通过对开箱即用数据进行属性选择来改进泛化
    作者: Xiaofeng Xu, Chuancai Liu
    链接:https://arxiv.org/abs/1907.11397

    【11】 Place Clustering-based Feature Recombination for Visual Place Recognition
    基于位置聚类的视觉位置识别特征重组
    作者: Qiang Zhai, Huiqin Zhan
    链接:https://arxiv.org/abs/1907.11350

    【12】 Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image
    基于摄像机距离感知的自上而下的单幅RGB图像三维多人姿态估计方法
    作者: Gyeongsik Moon, Kyoung Mu Lee
    备注:Published at ICCV 2019
    链接:https://arxiv.org/abs/1907.11346

    【13】 SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation
    SceneGraphNet:用于3D室内场景增强的神经消息传递
    作者: Yang Zhou, Evangelos Kalogerakis
    备注:8 pages, 8 figures, to appear in ICCV 2019
    链接:https://arxiv.org/abs/1907.11308

    【14】 Multi-Stage Prediction Networks for Data Harmonization
    数据协调的多级预测网络
    作者: Stefano B. Blumberg, Daniel C. Alexander
    备注:Accepted In Medical Image Computing and Computer Assisted Intervention (MICCAI) 2019
    链接:https://arxiv.org/abs/1907.11629

    【15】 Bayesian Volumetric Autoregressive generative models for better semisupervised learning
    用于更好的半监督学习的贝叶斯体积自回归生成模型
    作者: Guilherme Pombo, Parashkev Nachev
    链接:https://arxiv.org/abs/1907.11559

    【16】 A bisector line field approach to interpolation of orientation fields
    方向场插值的平分线场方法
    作者: Nicolas Boizot (LIS), Ludovic Sacchelli (LIS)
    链接:https://arxiv.org/abs/1907.11449

    【17】 Automatic Calcium Scoring in Cardiac and Chest CT Using DenseRAUnet
    用DenseRAUnet实现心脏和胸部CT中钙的自动评分
    作者: Jiechao Ma, Rongguo Zhang
    链接:https://arxiv.org/abs/1907.11392

    【18】 Image Enhancement by Recurrently-trained Super-resolution Network
    基于递归训练超分辨率网络的图像增强
    作者: Saem Park, Nojun Kwak
    链接:https://arxiv.org/abs/1907.11341

    相关文章

      网友评论

        本文标题:计算机视觉每日论文速递[07.29]

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