计算机视觉每日论文速递[07.11]

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 ̄)

cs.CV 方向,今日共计38篇

[检测分类相关]:

【1】 Metamorphic Detection of Adversarial Examples in Deep Learning Models With Affine Transformations
仿射变换深度学习模型中对抗性样本的变形检测
作者: Rohan Reddy Mekala, Madeline Diep
链接:https://arxiv.org/abs/1907.04774

【2】 Multi-Person tracking by multi-scale detection in Basketball scenarios
篮球场景中多尺度检测的多人跟踪
作者: Adrià Arbués-Sangüesa, Coloma Ballester
备注:Accepted in IMVIP 2019
链接:https://arxiv.org/abs/1907.04637

【3】 Deep Multi Label Classification in Affine Subspaces
仿射子空间中的深层多标签分类
作者: Thomas Kurmann, Raphael Sznitman
链接:https://arxiv.org/abs/1907.04563

【4】 A review on deep learning techniques for 3D sensed data classification
三维感知数据分类的深度学习技术综述
作者: David Griffiths, Jan Boehm
链接:https://arxiv.org/abs/1907.04444

【5】 Automatic Mass Detection in Breast Using Deep Convolutional Neural Network and SVM Classifier
基于深层卷积神经网络和SVM分类器的乳腺肿块自动检测
作者: Md. Kamrul Hasan, Tajwar Abrar Aleef
链接:https://arxiv.org/abs/1907.04424

【6】 Domain Adaptation-based Augmentation for Weakly Supervised Nuclei Detection
基于域自适应的弱监督核检测增强算法
作者: Nicolas Brieu, Günter Schmidt
链接:https://arxiv.org/abs/1907.04681

【7】 Out-of-Distribution Detection Using Neural Rendering Generative Models
使用神经渲染生成模型的分布失调检测
作者: Yujia Huang, Anima Anandkumar
链接:https://arxiv.org/abs/1907.04572

[分割/语义相关]:
【1】 Generating All the Roads to Rome: Road Layout Randomization for Improved Road Marking Segmentation
生成所有通往罗马的道路:道路布局随机化用于改进的道路标记分割
作者: Tom Bruls, Paul Newman
备注:presented at ITSC 2019
链接:https://arxiv.org/abs/1907.04569

【2】 Global Optimality Guarantees for Nonconvex Unsupervised Video Segmentation
非凸无监督视频分割的全局最优性保证
作者: Brendon G. Anderson, Somayeh Sojoudi
链接:https://arxiv.org/abs/1907.04409

[GAN/对抗式/生成式相关]:
【1】 Generating Adversarial Fragments with Adversarial Networks for Physical-world Implementation
利用对抗网络生成对抗片段以用于物理世界实施
作者: Zelun Kong, Cong Liu
链接:https://arxiv.org/abs/1907.04449

【2】 M3D-GAN: Multi-Modal Multi-Domain Translation with Universal Attention
M3D-GAN:具有普遍关注的多模态多域翻译
作者: Shuang Ma, Yale Song
链接:https://arxiv.org/abs/1907.04378

【3】 BASN -- Learning Steganography with Binary Attention Mechanism
BASN-具有二元注意机制的学习隐写术
作者: Yang Yang
链接:https://arxiv.org/abs/1907.04362

【4】 Enhanced generative adversarial network for 3D brain MRI super-resolution
用于3D脑MRI超分辨率的增强型生成对抗网络
作者: Jiancong Wang, James Gee
链接:https://arxiv.org/abs/1907.04835

[图像/视频检索]:
【1】 A New Benchmark and Approach for Fine-grained Cross-media Retrieval
一种新的细粒度跨媒体检索基准和方法
作者: Xiangteng He, Liu Xie
备注:9 pages, accepted to ACM MM 2019
链接:https://arxiv.org/abs/1907.04476

[行为/时空/光流/姿态/运动]:
【1】 One Shot Learning for Deformable Medical Image Registration and Periodic Motion Tracking
一次学习用于可变形医学图像配准和周期运动跟踪
作者: Tobias Fechter, Dimos Baltas
链接:https://arxiv.org/abs/1907.04641

【2】 Video Action Recognition Via Neural Architecture Searching
基于神经结构搜索的视频动作识别
作者: Wei Peng, Guoying Zhao
备注:Accepted by IEEE ICIP2019
链接:https://arxiv.org/abs/1907.04632

【3】 Fetal Pose Estimation in Volumetric MRI using a 3D Convolution Neural Network
三维卷积神经网络在体积MRI中的胎儿姿势估计
作者: Junshen Xu, Elfar Adalsteinsson
备注:MICCAI 2019
链接:https://arxiv.org/abs/1907.04500

[跟踪相关]:
【1】 Image based Eye Gaze Tracking and its Applications
基于图像的眼睛注视跟踪及其应用
作者: Anjith George
链接:https://arxiv.org/abs/1907.04325

[数据集dataset]:
【1】 Dunhuang Grotto Painting Dataset and Benchmark
敦煌石窟绘画数据集及基准
作者: Tianxiu Yu, Shaodi You
链接:https://arxiv.org/abs/1907.04589

【2】 A New Stereo Benchmarking Dataset for Satellite Images
一种新的卫星图像立体基准数据集
作者: Sonali Patil, Avinash C. Kak
链接:https://arxiv.org/abs/1907.04404

[其他视频相关]:
【1】 Learning to Reason with Relational Video Representation for Question Answering
学习使用关系视频表示进行推理以进行问题回答
作者: Thao Minh Le, Truyen Tran
链接:https://arxiv.org/abs/1907.04553

[其他]:
【1】 Fast geodesic shooting for landmark matching using CUDA
使用CUDA进行地标匹配的快速测地线拍摄
作者: Jiancong Wang
链接:https://arxiv.org/abs/1907.04839

【2】 Barnes-Hut Approximation for Point SetGeodesic Shooting
点集测地射击的Barnes-Hut近似
作者: Jiancong Wang, James Gee
链接:https://arxiv.org/abs/1907.04834

【3】 Toward a Procedural Fruit Tree Rendering Framework for Image Analysis
面向图像分析的过程性果树绘制框架
作者: Thomas Duboudin (imagine), Liming Chen (imagine)
链接:https://arxiv.org/abs/1907.04759

【4】 SynthCity: A large scale synthetic point cloud
SynthCity:大规模的合成点云
作者: David Griffiths, Jan Boehm
链接:https://arxiv.org/abs/1907.04758

【5】 Utilizing Eye Gaze to Enhance the Generalization of Imitation Networks to Unseen Environments
利用眼睛凝视增强模拟网络对不可见环境的泛化
作者: Congcong Liu, Bertram Shi
备注:4 pages, 3 figures, accepted by ICML 2019 Workshop on Understanding and Improving Generalization in Deep Learning
链接:https://arxiv.org/abs/1907.04728

【6】 Regularizing Neural Networks for Future Trajectory Prediction via Inverse Reinforcement Learning
反向强化学习用于未来弹道预测的正则化神经网络
作者: Dooseop Choi, Jeongdan Choi
链接:https://arxiv.org/abs/1907.04525

【7】 User Preference Prediction in Visual Data on Mobile Devices
移动设备视觉数据中的用户偏好预测
作者: A.V. Savchenko, I.S. Grechikhin
链接:https://arxiv.org/abs/1907.04519

【8】 Joint Learning of Multiple Image Restoration Tasks
多个图像恢复任务的联合学习
作者: Xing Liu, Takayuki Okatani
链接:https://arxiv.org/abs/1907.04508

【9】 Fast Estimating Pedestrian Moving State Based on Single 2D Body Pose by Shallow Neural Network
基于单个二维体姿态的浅层神经网络快速估计行人运动状态
作者: Zixing Wang, Nikolaos Papanikolopoulos
备注:CoRL 2019
链接:https://arxiv.org/abs/1907.04361

【10】 Improving Prognostic Performance in Resectable Pancreatic Ductal Adenocarcinoma using Radiomics and Deep Learning Features Fusion in CT Images
利用CT图像中的放射组学和深度学习特征融合提高可切除胰腺导管腺癌的预后性能
作者: Yucheng Zhang, Farzad Khalvati
链接:https://arxiv.org/abs/1907.04822

【11】 Towards Affordance Prediction with Vision via Task Oriented Grasp Quality Metrics
通过面向任务的抓取质量度量实现具有视觉的AfforDance预测
作者: Luca Cavalli, Matteo Matteucci
链接:https://arxiv.org/abs/1907.04761

【12】 A Projectional Ansatz to Reconstruction
投射反重构
作者: Sören Dittmer, Peter Maass
链接:https://arxiv.org/abs/1907.04675

【13】 Playing Go without Game Tree Search Using Convolutional Neural Networks
用卷积神经网络进行无博弈树搜索的围棋
作者: Jeffrey Barratt, Chuanbo Pan
链接:https://arxiv.org/abs/1907.04658

【14】 Progressive Wasserstein Barycenters of Persistence Diagrams
持续图的渐进Wasserstein Barycenter
作者: Jules Vidal, Julien Tierny
链接:https://arxiv.org/abs/1907.04565

【15】 Coarse Graining of Data via Inhomogeneous Diffusion Condensation
通过非均匀扩散凝聚对数据进行粗粒度处理
作者: Nathan Brugnone (1), (5) Université de Montréal)
链接:https://arxiv.org/abs/1907.04463

【16】 GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing
GluonCV和GluonNLP:计算机视觉和自然语言处理中的深度学习
作者: Jian Guo, Shuai Zheng
链接:https://arxiv.org/abs/1907.04433

【17】 Hybrid system identification using switching density networks
基于开关密度网络的混合系统辨识
作者: Michael Burke, Subramanian Ramamoorthy
链接:https://arxiv.org/abs/1907.04360

翻译:腾讯翻译君

你可能感兴趣的:(计算机视觉每日论文速递[07.11])