计算机视觉每日论文速递[08.26]

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36篇

[检测分类相关]:

【1】 Cephalometric Landmark Detection by AttentiveFeature Pyramid Fusion and Regression-Voting
基于AttentiveFeature金字塔融合和回归投票的头影测量地标检测
作者: Runnan Chen, Wenping Wang
备注:Early accepted by International Conference on Medical image computing and computer-assisted intervention (MICCAI 2019)
链接:https://arxiv.org/abs/1908.08841

[分割/语义相关]:

【1】 A Review of Point Cloud Semantic Segmentation
点云语义分割研究综述
作者: Yuxing Xie, Xiao Xiang Zhu
链接:https://arxiv.org/abs/1908.08854

【2】 Topology-preserving augmentation for CNN-based segmentation of congenital heart defects from 3D paediatric CMR
基于CNN的三维儿科CMR先天性心脏病分割的拓扑保持增强
作者: Nick Byrne, Andrew P. King
备注:To be published at MICCAI PIPPI 2019
链接:https://arxiv.org/abs/1908.08870

【3】 Automatic Rodent Brain MRI Lesion Segmentation with Fully Convolutional Networks
基于完全卷积网络的啮齿动物脑MRI病变自动分割
作者: Juan Miguel Valverde, Jussi Tohka
备注:Accepted to Machine Learning in Medical Imaging (MLMI 2019)
链接:https://arxiv.org/abs/1908.08746

【4】 A joint 3D UNet-Graph Neural Network-based method for Airway Segmentation from chest CTs
一种基于联合3D UNET-Graph神经网络的胸部CT气道分割方法
作者: Antonio Garcia-Uceda Juarez, Marleen de Bruijne
链接:https://arxiv.org/abs/1908.08588

[GAN/对抗式/生成式相关]:

【1】 Sparse Generative Adversarial Network
稀疏生成对抗网络
作者: Shahin Mahdizadehaghdam, Hamid Krim
链接:https://arxiv.org/abs/1908.08930

【2】 Generating High-Resolution Fashion Model Images Wearing Custom Outfits
穿着定制服装生成高分辨率时装模特图像
作者: Gökhan Yildirim, Urs Bergmann
备注:Accepted to the International Conference on Computer Vision, ICCV 2019, Workshop on Computer Vision for Fashion, Art and Design
链接:https://arxiv.org/abs/1908.08847

【3】 AdvHat: Real-world adversarial attack on ArcFace Face ID system
AdvHat:对ArcFace Face ID系统的真实对抗攻击
作者: Stepan Komkov, Aleksandr Petiushko
链接:https://arxiv.org/abs/1908.08705

【4】 Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry
自监督深度视觉里程计的序贯对抗性学习
作者: Shunkai Li, Hongbin Zha
备注:Accept to ICCV 2019
链接:https://arxiv.org/abs/1908.08704

[行为/时空/光流/姿态/运动]:

【1】 Human activity recognition from skeleton poses
基于骨架姿态的人体活动识别
作者: Frederico Belmonte Klein, Angelo Cangelosi
链接:https://arxiv.org/abs/1908.08928

【2】 In-bed Pressure-based Pose Estimation using Image Space Representation Learning
基于图像空间表示学习的床内压力位姿估计
作者: Vandad Davoodnia, Ali Etemad
链接:https://arxiv.org/abs/1908.08919

[跟踪相关]:

【1】 DefSLAM: Tracking and Mapping of Deforming Scenes from Monocular Sequences
DefSLAM:从单目序列跟踪和映射变形场景
作者: Jose Lamarca, J.M.M. Montiel
链接:https://arxiv.org/abs/1908.08918

【2】 Region Tracking in an Image Sequence: Preventing Driver Inattention
图像序列中的区域跟踪:防止驾驶员疏忽
作者: Matthew Kowal, Raner la Bastide
链接:https://arxiv.org/abs/1908.08914

[裁剪/量化/加速相关]:

【1】 Learning Filter Basis for Convolutional Neural Network Compression
卷积神经网络压缩的学习滤波器基础
作者: Yawei Li, Radu Timofte
备注:Accepted by ICCV 2019. Code is available at this https URL
链接:https://arxiv.org/abs/1908.08932

[超分辨率]:

【1】 DRFN: Deep Recurrent Fusion Network for Single-Image Super-Resolution with Large Factors
DRFN:大因子单图像超分辨率深度递归融合网络
作者: Xin Yang, Xiaopeng Wei
链接:https://arxiv.org/abs/1908.08837

[3D/3D重建等相关]:

【1】 Cross-Enhancement Transform Two-Stream 3D ConvNets for Pedestrian Action Recognition of Autonomous Vehicles
用于自主车辆行人行为识别的交叉增强变换双流3D ConvNets
作者: Dong Cao, Lisha Xu
备注:Accepted for publication in AIIPCC 2019
链接:https://arxiv.org/abs/1908.08916

[其他视频相关]:

【1】 Onion-Peel Networks for Deep Video Completion
用于深度视频完成的洋葱-剥离网络
作者: Seoung Wug Oh, Seon Joo Kim
备注:ICCV 2019
链接:https://arxiv.org/abs/1908.08718

[其他]:

【1】 2D moment invariants from the point of view of the classical invariant theory
从经典不变量理论的角度看二维矩不变量
作者: Leonid Bedratyuk
备注:20 pages
链接:https://arxiv.org/abs/1908.08927

【2】 Efficient Deep Neural Networks
高效深度神经网络
作者: Bichen Wu
链接:https://arxiv.org/abs/1908.08926

【3】 Trajectory Prediction by Coupling Scene-LSTM with Human Movement LSTM
场景-LSTM与人体运动LSTM耦合的轨迹预测
作者: Manh Huynh, Gita Alaghband
备注:To appear in ISVC 2019
链接:https://arxiv.org/abs/1908.08908

【4】 Feature Learning to Automatically Assess Radiographic Knee Osteoarthritis Severity
自动评估X线膝关节骨关节炎严重程度的特征学习
作者: Joseph Antony, Noel E O' Connor
链接:https://arxiv.org/abs/1908.08840

【5】 Multi-Spectral Visual Odometry without Explicit Stereo Matching
无显式立体匹配的多光谱视觉里程计
作者: Weichen Dai, Ping Li
链接:https://arxiv.org/abs/1908.08814

【6】 Mutual information neural estimation in CNN-based end-to-end medical image registration
基于CNN的端到端医学图像配准中的互信息神经估计
作者: Yechong Huang, Xiahai Zhuang
链接:https://arxiv.org/abs/1908.08767

【7】 Crowd Counting with Deep Structured Scale Integration Network
基于深度结构规模集成网络的人群计数
作者: Lingbo Liu, Liang Lin
备注:Accepted to ICCV 2019
链接:https://arxiv.org/abs/1908.08692

【8】 A BLSTM Network for Printed Bengali OCR System with High Accuracy
一种用于高精度印刷孟加拉OCR系统的BLSTM网络
作者: Debabrata Paul, Bidyut Baran Chaudhuri
链接:https://arxiv.org/abs/1908.08674

【9】 Shadow Removal via Shadow Image Decomposition
通过阴影图像分解去除阴影
作者: Hieu Le, Dimitris Samaras
备注:ICCV 19 Poster. Higher resolution version is available in the project homepage: www3.cs.stonybrook.edu/~cvl/projects/SID/index.html
链接:https://arxiv.org/abs/1908.08628

【10】 Sign Language Recognition, Generation, and Translation: An Interdisciplinary Perspective
手语识别、生成与翻译:一个跨学科的视角
作者: Danielle Bragg, Meredith Ringel Morris
链接:https://arxiv.org/abs/1908.08597

【11】 Learning Similarity Conditions Without Explicit Supervision
在没有显式监督的情况下学习相似条件
作者: Reuben Tan, Bryan A. Plummer
备注:Accepted at ICCV 2019
链接:https://arxiv.org/abs/1908.08589

【12】 Predicting knee osteoarthritis severity: comparative modeling based on patient's data and plain X-ray images
预测膝关节骨关节炎严重程度:基于患者数据和普通X线图像的对比建模
作者: Jaynal Abedin, John Newell
备注:Published in Nature Scientific Reports, 2019
链接:https://arxiv.org/abs/1908.08873

【13】 Assessing Knee OA Severity with CNN attention-based end-to-end architectures
使用CNN基于注意力的端到端架构评估膝关节OA严重程度
作者: Marc Górriz, Noel E. O'Connor
链接:https://arxiv.org/abs/1908.08856

【14】 Gaussian implementation of the multi-Bernoulli mixture filter
多重Bernoulli混合滤波器的高斯实现
作者: Ángel F. García-Fernández, Jason L. Williams
链接:https://arxiv.org/abs/1908.08819

【15】 Spooky effect in optimal OSPA estimation and how GOSPA solves it
最优OSPA估计中的诡异效应及GOSPA如何解决它
作者: Ángel F. García-Fernández, Lennart Svensson
备注:This paper received the third best paper award at the 22nd International Conference on Information Fusion, Ottawa, Canada, 2019. Matlab code of the GOSPA metric can be found in this https URL . Additional information on MTT can be found in the online course this https URL
链接:https://arxiv.org/abs/1908.08815

【16】 Efficient Capon-Based Approach Exploiting Temporal Windowing For Electric Network Frequency Estimation
基于Capon的有效利用时间窗口的电网频率估计方法
作者: Georgios Karantaidis, Constantine Kotropoulos
备注:6 pages, 1 figure, IEEE International Workshop on Machine Learning For Signal Processing (MLSP) 2019
链接:https://arxiv.org/abs/1908.08813

【17】 Mish: A Self Regularized Non-Monotonic Neural Activation Function
MISH:一种自正则的非单调神经激活函数
作者: Diganta Misra
链接:https://arxiv.org/abs/1908.08681

【18】 MTCNET: Multi-task Learning Paradigm for Crowd Count Estimation
MTCNET:人群计数估计的多任务学习范式
作者: Abhay Kumar, Kamal Krishna
备注:5 pages, 3 figures, Accepted in IEEE AVSS 2019
链接:https://arxiv.org/abs/1908.08652

【19】 Image based cellular contractile force evaluation with small-world network inspired CNN: SW-UNet
基于图像的基于小世界网络的细胞收缩力评估CNN:SW-UNET
作者: Li Honghan, Shinji Deguchi
链接:https://arxiv.org/abs/1908.08631

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[08.26])