计算机视觉每日论文速递[08.22]
同步公众号(arXiv每日论文速递),回复'search 关键词'查询相关最新论文。(* ̄rǒ ̄)
cs.CV 方向,今日共计37篇
[检测分类相关]:
【1】 Non-negative Sparse and Collaborative Representation for Pattern Classification
模式分类的非负稀疏协同表示
作者: Jun Xu, David Zhang
备注:26 pages, 11 tables, 3 figures. arXiv admin note: text overlap with arXiv:1806.04329
链接:https://arxiv.org/abs/1908.07956
【2】 Learning Structured Twin-Incoherent Twin-Projective Latent Dictionary Pairs for Classification
用于分类的学习结构双非相干双投射潜在字典对
作者: Zhao Zhang, Meng Wang
备注:Accepted by ICDM 2019 as a regular paper
链接:https://arxiv.org/abs/1908.07878
【3】 Video-based Bottleneck Detection utilizing Lagrangian Dynamics in Crowded Scenes
拥挤场景下基于拉格朗日动力学的视频瓶颈检测
作者: Maik Simon, Thomas Sikora
链接:https://arxiv.org/abs/1908.07772
【4】 FusionNet: Incorporating Shape and Texture for Abnormality Detection in 3D Abdominal CT Scans
FusionNet:结合形状和纹理用于3D腹部CT扫描中的异常检测
作者: Fengze Liu, Alan Yuille
备注:Accepted to MICCAI 2019 Workshop(MLMI)(8 pages, 3 figures)
链接:https://arxiv.org/abs/1908.07654
【5】 A novel text representation which enables image classifiers to perform text classification, applied to name disambiguation
一种新颖的文本表示,其使图像分类器能够执行文本分类,应用于名称消歧
作者: Stephen M. Petrie, T'Mir D. Julius
链接:https://arxiv.org/abs/1908.07846
[分割/语义相关]:
【1】 InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting
InstaBoost:通过概率图引导复制粘贴增强实例分割
作者: Hao-Shu Fang, Cewu Lu
备注:ICCV 2019
链接:https://arxiv.org/abs/1908.07801
【2】 Preserving Semantic and Temporal Consistency for Unpaired Video-to-Video Translation
保持语义和时间一致性的非配对视频到视频翻译
作者: Kwanyong Park, In So Kweon
备注:Accepted by ACM Multimedia(ACM MM) 2019
链接:https://arxiv.org/abs/1908.07683
【3】 Asymmetric Non-local Neural Networks for Semantic Segmentation
用于语义分割的非对称非局部神经网络
作者: Zhen Zhu, Xiang Bai
备注:To appear in ICCV 2019
链接:https://arxiv.org/abs/1908.07678
【4】 Semantic-Transferable Weakly-Supervised Endoscopic Lesions Segmentation
语义可转移的弱监督内窥镜病变分割
作者: Jiahua Dong, Dongdong Hou
链接:https://arxiv.org/abs/1908.07669
【5】 Pixel-wise Segmentation of Right Ventricle of Heart
心脏右心室的像素分割
作者: Yaman Dang, Amit Sethi
备注:Accepted at IEEE TENCON 2019
链接:https://arxiv.org/abs/1908.08004
【6】 Adaptive Segmentation of Knee Radiographs for Selecting the Optimal ROI in Texture Analysis
用于纹理分析中选择最佳ROI的膝关节射线片的自适应分割
作者: Neslihan Bayramoglu, Simo Saarakkala
链接:https://arxiv.org/abs/1908.07736
【7】 Automated Multi-sequence Cardiac MRI Segmentation Using Supervised Domain Adaptation
使用有监督域自适应的自动多序列心脏MRI分割
作者: Sulaiman Vesal, Andreas Maier
备注:Accepted at STACOM-MICCAI 2019
链接:https://arxiv.org/abs/1908.07726
【8】 Lung segmentation on chest x-ray images in patients with severe abnormal findings using deep learning
使用深度学习对严重异常发现的患者的胸部X线图像进行肺分割
作者: Mizuho Nishio, Kaori Togashi
链接:https://arxiv.org/abs/1908.07704
【9】 P2L: Predicting Transfer Learning for Images and Semantic Relations
P2L:预测图像和语义关系的迁移学习
作者: Bishwaranjan Bhattacharjee, Brian Belgodere
链接:https://arxiv.org/abs/1908.07630
【10】 Joint Motion Estimation and Segmentation from Undersampled Cardiac MR Image
欠采样心脏MR图像的联合运动估计和分割
作者: Chen Qin, Daniel Rueckert
备注:This work is published at MLMIR 2018: Machine Learning for Medical Image Reconstruction
链接:https://arxiv.org/abs/1908.07623
[GAN/对抗式/生成式相关]:
【1】 TUNA-Net: Task-oriented UNsupervised Adversarial Network for Disease Recognition in Cross-Domain Chest X-rays
金枪鱼网:用于跨域胸部X射线疾病识别的面向任务的无监督对抗性网络
作者: Yuxing Tang, Ronald M. Summers
备注:MICCAI 2019
链接:https://arxiv.org/abs/1908.07926
[行为/时空/光流/姿态/运动]:
【1】 On Object Symmetries and 6D Pose Estimation from Images
基于图像的物体对称性和6D位姿估计
作者: Giorgia Pitteri, Vincent Lepetit
链接:https://arxiv.org/abs/1908.07640
【2】 Action recognition with spatial-temporal discriminative filter banks
基于时空判别滤波器组的动作识别
作者: Brais Martinez, Joseph Tighe
备注:ICCV 2019 Accepted Paper
链接:https://arxiv.org/abs/1908.07625
[跟踪相关]:
【1】 DomainSiam: Domain-Aware Siamese Network for Visual Object Tracking
DomainSiam:用于可视对象跟踪的域感知暹罗网络
作者: Mohamed H. Abdelpakey, Mohamed S. Shehata
链接:https://arxiv.org/abs/1908.07905
【2】 Effects of Blur and Deblurring to Visual Object Tracking
模糊和去模糊对视觉目标跟踪的影响
作者: Qing Guo, Song Wang
链接:https://arxiv.org/abs/1908.07904
[迁移学习/domain/主动学习/自适应]:
【1】 Adaptive Structure-constrained Robust Latent Low-Rank Coding for Image Recovery
用于图像恢复的自适应结构约束鲁棒潜在低秩编码
作者: Zhao Zhang, Meng Wang
备注:Accepted by ICDM 2019 as a regular paper
链接:https://arxiv.org/abs/1908.07860
【2】 Communal Domain Learning for Registration in Drifted Image Spaces
用于漂移图像空间配准的公共域学习
作者: Awais Mansoor, Marius George Linguraru
备注:MLMI-2019
链接:https://arxiv.org/abs/1908.07646
[裁剪/量化/加速相关]:
【1】 RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs
RBCN:用于提高1位DCNN性能的整流二进制卷积网络
作者: Chunlei Liu, Guodong Guo
链接:https://arxiv.org/abs/1908.07748
[数据集dataset]:
【1】 Dataset Growth in Medical Image Analysis Research
医学图像分析研究中的数据集增长
作者: Yuval Landau, Nahum Kiryati
链接:https://arxiv.org/abs/1908.07765
[超分辨率]:
【1】 MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors
MobiSR:通过异构移动处理器实现高效的设备上超分辨率
作者: Royson Lee, Nicholas D. Lane
备注:Accepted at the 25th Annual International Conference on Mobile Computing and Networking (MobiCom), 2019
链接:https://arxiv.org/abs/1908.07985
[点云]:
【1】 PCRNet: Point Cloud Registration Network using PointNet Encoding
PCRNet:使用PointNet编码的点云注册网络
作者: Vinit Sarode, Howie Choset
链接:https://arxiv.org/abs/1908.07906
[深度depth相关]:
【1】 KeystoneDepth: Visualizing History in 3D
KeystoneDepth:在3D中可视化历史
作者: Xuan Luo, Steve Seitz
链接:https://arxiv.org/abs/1908.07732
[人脸相关]:
【1】 A Realistic Face-to-Face Conversation System based on Deep Neural Networks
基于深度神经网络的真实感面对面交谈系统
作者: Zezhou Chen, Kai Wang
备注:Accepted to ICCV 2019 workshop
链接:https://arxiv.org/abs/1908.07750
[3D/3D重建等相关]:
【1】 Direct Neural Network 3D Image Reconstruction of Radon Encoded Data
氡编码数据的直接神经网络三维图像重建
作者: William Whiteley, Jens Gregor
链接:https://arxiv.org/abs/1908.07516
[其他]:
【1】 Deep High-Resolution Representation Learning for Visual Recognition
用于视觉识别的深度高分辨率表征学习
作者: Jingdong Wang, Bin Xiao
备注:arXiv admin note: text overlap with arXiv:1904.04514
链接:https://arxiv.org/abs/1908.07919
【2】 Pilot Study on Verifying the Monotonic Relationship between Error and Uncertainty in Deformable Registration for Neurosurgery
神经外科形变配准中误差与不确定度单调关系验证的初步研究
作者: Jie Luo, Sarah Frisken
链接:https://arxiv.org/abs/1908.07709
【3】 Saccader: Improving Accuracy of Hard Attention Models for Vision
Saccader:提高视觉硬注意模型的准确性
作者: Gamaleldin F. Elsayed, Quoc V. Le
链接:https://arxiv.org/abs/1908.07644
【4】 Phrase Localization Without Paired Training Examples
没有成对训练示例的短语本地化
作者: Josiah Wang, Lucia Specia
备注:Accepted for oral presentation at the IEEE/CVF International Conference on Computer Vision (ICCV) 2019
链接:https://arxiv.org/abs/1908.07553
【5】 Multi-Modal Recognition of Worker Activity for Human-Centered Intelligent Manufacturing
以人为中心的智能制造中工人活动的多模态识别
作者: Wenjin Tao, Zhaozheng Yin
链接:https://arxiv.org/abs/1908.07519
【6】 Testing Robustness Against Unforeseen Adversaries
测试对不可预见的对手的鲁棒性
作者: Daniel Kang, Jacob Steinhardt
链接:https://arxiv.org/abs/1908.08016
【7】 Estimation of perceptual scales using ordinal embedding
基于序数嵌入的感知尺度估计
作者: Siavash Haghiri, Ulrike von Luxburg
链接:https://arxiv.org/abs/1908.07962
【8】 Ranking Viscous Finger Simulations to an Acquired Ground Truth with Topology-aware Matchings
使用拓扑感知匹配将粘性手指模拟排序到获取的地面真实
作者: Maxime Soler, Julien Tierny
链接:https://arxiv.org/abs/1908.07841
翻译:腾讯翻译君