计算机视觉每日论文速递[08.20]

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90篇

[检测分类相关]:

【1】 A Kings Ransom for Encryption: Ransomware Classification using Augmented One-Shot Learning and Bayesian Approximation
用于加密的Kings Ransom:使用增强单次学习和贝叶斯近似的勒索软件分类
作者: Amir Atapour-Abarghouei, Andrew Stephen McGough
备注:Submitted to 2019 IEEE International Conference on Big Data
链接:https://arxiv.org/abs/1908.06750

【2】 Directionally Constrained Fully Convolutional Neural Network For Airborne Lidar Point Cloud Classification
方向约束完全卷积神经网络用于机载激光雷达点云分类
作者: Congcong Wen, Tianhe Chi
链接:https://arxiv.org/abs/1908.06673

【3】 C-RPNs: Promoting Object Detection in real world via a Cascade Structure of Region Proposal Networks
C-RPN:通过区域提议网络的级联结构促进现实世界中的对象检测
作者: Dongming Yang, Ge Li
链接:https://arxiv.org/abs/1908.06665

【4】 Graph-Based Object Classification for Neuromorphic Vision Sensing
基于图的神经形态视觉感知对象分类
作者: Yin Bi, Yiannis Andreopoulos
备注:13 pages, 4 figures, ICCV 2019
链接:https://arxiv.org/abs/1908.06648

【5】 A Delay Metric for Video Object Detection: What Average Precision Fails to Tell
一种用于视频对象检测的延迟度量:平均精度不能说明什么
作者: Huizi Mao, William J. Dally
备注:ICCV 2019
链接:https://arxiv.org/abs/1908.06368

【6】 Anomaly Detection in Video Sequence with Appearance-Motion Correspondence
基于外观-运动对应的视频序列异常检测
作者: Trong Nguyen Nguyen, Jean Meunier
备注:Paper accepted for ICCV 2019
链接:https://arxiv.org/abs/1908.06351

【7】 Hybrid Deep Network for Anomaly Detection
用于异常检测的混合深度网络
作者: Trong Nguyen Nguyen, Jean Meunier
备注:Paper accepted for BMVC 2019
链接:https://arxiv.org/abs/1908.06347

【8】 Scene Classification in Indoor Environments for Robots using Context Based Word Embeddings
使用基于上下文的单词嵌入的机器人室内环境中的场景分类
作者: Bao Xin Chen, John K. Tsotsos
链接:https://arxiv.org/abs/1908.06422

【9】 Evaluation of an AI System for the Detection of Diabetic Retinopathy from Images Captured with a Handheld Portable Fundus Camera: the MAILOR AI study
从手持便携式眼底相机拍摄的图像中检测糖尿病视网膜病变的AI系统的评估:MAILOR AI研究
作者: T W Rogers, N Jaccard
链接:https://arxiv.org/abs/1908.06399

【10】 Detecting abnormalities in resting-state dynamics: An unsupervised learning approach
检测静息状态动力学中的异常:一种无监督的学习方法
作者: Meenakshi Khosla, Mert R. Sabuncu
链接:https://arxiv.org/abs/1908.06168

[分割/语义相关]:

【1】 A unified representation network for segmentation with missing modalities
一种用于缺失模态分割的统一表示网络
作者: Kenneth Lau, Jens Sjölund
链接:https://arxiv.org/abs/1908.06683

【2】 RANet: Ranking Attention Network for Fast Video Object Segmentation
RANET:用于快速视频对象分割的排名注意力网络
作者: Ziqin Wang, Ling Shao
备注:Accepted by ICCV 2019. 10 pages, 7 figures, 6 tables. The supplementary file can be found at this https URL Code is available at this https URL
链接:https://arxiv.org/abs/1908.06647

【3】 IRNet: Instance Relation Network for Overlapping Cervical Cell Segmentation
IRNet:重叠宫颈细胞分割的实例关系网络
作者: Yanning Zhou, Pheng-Ann Heng
链接:https://arxiv.org/abs/1908.06623

【4】 Seq-SG2SL: Inferring Semantic Layout from Scene Graph Through Sequence to Sequence Learning
SEQ-SG2SL:通过序列到序列学习从场景图推断语义布局
作者: Boren Li, Jian Gu
备注:This paper will appear at ICCV 2019
链接:https://arxiv.org/abs/1908.06592

【5】 Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features
超像素流:多层神经特征的语义对应
作者: Juhong Min, Minsu Cho
备注:Accepted to ICCV 2019
链接:https://arxiv.org/abs/1908.06537

【6】 PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment
Panet:基于原型对齐的少镜头图像语义分割
作者: Kaixin Wang, Jiashi Feng
备注:10 pages, 6 figures, ICCV 2019
链接:https://arxiv.org/abs/1908.06391

【7】 Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization
细粒度分割网络:改进的长期视觉定位的自监督分割
作者: Måns Larsson, Fredrik Kahl
备注:Accepted to ICCV 2019
链接:https://arxiv.org/abs/1908.06387

【8】 3D Rigid Motion Segmentation with Mixed and Unknown Number of Models
混合未知数量模型的三维刚体运动分割
作者: Xun Xu, Zhuwen Li
备注:IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2019. arXiv admin note: substantial text overlap with arXiv:1804.02142
链接:https://arxiv.org/abs/1908.06087

【9】 Deep Active Lesion Segmentation
深层主动病变分割
作者: Ali Hatamizadeh, Demetri Terzopoulos
备注:Accepted to Machine Learning in Medical Imaging (MLMI 2019)
链接:https://arxiv.org/abs/1908.06933

【10】 Weakly Supervised Segmentation by A Deep Geodesic Prior
基于深度测地先验的弱监督分割
作者: Aliasghar Mortazi, Ulas Bagci
备注:Accepted to Machine Learning in Medical Imaging (MLMI 2019)
链接:https://arxiv.org/abs/1908.06498

【11】 GRIP: Generative Robust Inference and Perception for Semantic Robot Manipulation in Adversarial Environments
GRIP:对抗性环境中语义机器人操作的生成性稳健推理和感知
作者: Xiaotong Chen, Odest Chadwicke Jenkins
备注:9 pages, 7 figures, accepted by IROS 2019. contact: [email protected]
链接:https://arxiv.org/abs/1903.08352

[GAN/对抗式/生成式相关]:
【1】 Fully Automated Image De-fencing using Conditional Generative Adversarial Networks
使用条件生成对抗性网络的全自动图像去围栏
作者: Divyanshu Gupta, Lipo Wang
链接:https://arxiv.org/abs/1908.06837

【2】 SPA-GAN: Spatial Attention GAN for Image-to-Image Translation
SPA-GAN:用于图像到图像翻译的空间注意GaN
作者: Hajar Emami, Ratna Babu Chinnam
链接:https://arxiv.org/abs/1908.06616

【3】 Adversarial Defense by Suppressing High-frequency Components
抑制高频成分的对抗性防御
作者: Zhendong Zhang, Xiaolong Liang
备注:3 pages. This paper is a technical report of the 5th place solution in the IJCAI-2019 Alibaba Adversarial AI Challenge. This paper has been accepted by the corresponding workshop
链接:https://arxiv.org/abs/1908.06566

【4】 RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution
RankSRGAN:具有排序器的生成对抗性网络图像超分辨率
作者: Wenlong Zhang, Yu Qiao
备注:ICCV 2019 (Oral) camera-ready + supplementary; Project page: this https URL
链接:https://arxiv.org/abs/1908.06382

【5】 Neural Re-Simulation for Generating Bounces in Single Images
神经网络重新模拟生成单幅图像中的反弹
作者: Carlo Innamorati, and Niloy J. Mitra
备注:Accepted to ICCV 2019
链接:https://arxiv.org/abs/1908.06217

【6】 Applying Adversarial Auto-encoder for Estimating Human Walking Gait Abnormality Index
应用对抗性自动编码器估计人体行走步态异常指数
作者: Trong-Nguyen Nguyen, Jean Meunier
链接:https://arxiv.org/abs/1908.06188

【7】 TunaGAN: Interpretable GAN for Smart Editing
TunaGAN:用于智能编辑的可解释GAN
作者: Weiquan Mao, Jiyao Yuan
链接:https://arxiv.org/abs/1908.06163

【8】 Towards Generating Ambisonics Using Audio-Visual Cue for Virtual Reality
利用视听提示生成虚拟现实中的变声学
作者: Aakanksha Rana, Aljoscha Smolic
备注:ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
链接:https://arxiv.org/abs/1908.06752

[图像/视频检索]:
【1】 Genetic Algorithms for the Optimization of Diffusion Parameters in Content-Based Image Retrieval
基于内容的图像检索中扩散参数优化的遗传算法
作者: Federico Magliani, Andrea Prati
链接:https://arxiv.org/abs/1908.06896

[行为/时空/光流/姿态/运动]:
【1】 A Software to Detect OCC Emotion, Big-Five Personality and Hofstede Cultural Dimensions of Pedestrians from Video Sequences
从视频序列中检测行人的OCC情绪、大五人格和Hofstede文化维度的软件
作者: Rodolfo Migon Favaretto, Angelo Brandelli Costa
链接:https://arxiv.org/abs/1908.06484

【2】 On the Robustness of Human Pose Estimation
人体姿态估计的稳健性研究
作者: Sahil Shah, Arjun Jain
链接:https://arxiv.org/abs/1908.06401

[半/弱/无监督相关]:
【1】 Weakly-supervised Action Localization with Background Modeling
基于背景建模的弱监督动作定位
作者: Phuc Xuan Nguyen, Charless C. Fowlkes
备注:To appear at ICCV 2019
链接:https://arxiv.org/abs/1908.06552

【2】 Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Translation
通过分离聚集:使用半监督样式转换增强面部地标检测器
作者: Shengju Qian, Jiaya Jia
备注:Accepted to ICCV 2019
链接:https://arxiv.org/abs/1908.06440

【3】 Unsupervised Learning of Landmarks by Descriptor Vector Exchange
基于描述符向量交换的地标无监督学习
作者: James Thewlis, Andrea Vedaldi
备注:ICCV 2019
链接:https://arxiv.org/abs/1908.06427

【4】 Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning
从NRSfM中提取弱监督3D姿态学习的知识
作者: Chaoyang Wang, Simon Lucey
链接:https://arxiv.org/abs/1908.06377

【5】 Conv2Warp: An unsupervised deformable image registration with continuous convolution and warping
Conv2Warp:一种具有连续卷积和翘曲的无监督可变形图像配准
作者: Sharib Ali, Jens Rittscher
备注:8 pages (accepted at 10th International Workshop on Machine Learning in Medical Imaging, in conjunction with MICCAI2019)
链接:https://arxiv.org/abs/1908.06194

[跟踪相关]:
【1】 Some Aspects of Geometric Computer Vision for Analysing Dynamical Scenes focusing Automotive Applications
用于分析聚焦汽车应用的动态场景的几何计算机视觉的一些方面
作者: Volker Willert, Martin Buczko
链接:https://arxiv.org/abs/1908.06726

【2】 Multi Target Tracking by Learning from Generalized Graph Differences
基于广义图差学习的多目标跟踪
作者: Håkan Ardö, Mikael Nilsson
链接:https://arxiv.org/abs/1908.06646

【3】 Long-Duration Fully Autonomous Operation of Rotorcraft Unmanned Aerial Systems for Remote-Sensing Data Acquisition
用于遥感数据采集的旋翼机无人机空中系统的长时间全自主操作
作者: Danylo Malyuta, Roland Brockers
链接:https://arxiv.org/abs/1908.06381

[迁移学习/domain/主动学习/自适应]:
【1】 SDIT: Scalable and Diverse Cross-domain Image Translation
SDIT:可扩展和多样化的跨域图像翻译
作者: Yaxing Wang, Luis Herranz
备注:ACM-MM2019 camera ready
链接:https://arxiv.org/abs/1908.06881

【2】 Improved Techniques for Training Adaptive Deep Networks
自适应深度网络训练的改进技术
作者: Hao Li, Gao Huang
链接:https://arxiv.org/abs/1908.06294

[裁剪/量化/加速相关]:
【1】 Bayesian Optimized 1-Bit CNNs
贝叶斯优化的1位CNN
作者: Jiaxin Gu, Rongrong Ji
链接:https://arxiv.org/abs/1908.06314

[视频理解VQA/caption等]:
【1】 Attention on Attention for Image Captioning
图像字幕注意事项
作者: Lun Huang, Xiao-Yong Wei
备注:Accepted to ICCV 2019 (Oral)
链接:https://arxiv.org/abs/1908.06954

【2】 What is needed for simple spatial language capabilities in VQA?
VQA中的简单空间语言功能需要什么?
作者: Alexander Kuhnle, Ann Copestake
链接:https://arxiv.org/abs/1908.06336

[数据集dataset]:
【1】 Multiple Light Source Dataset for Colour Research
用于颜色研究的多光源数据集
作者: Anna Smagina, Anton Grigoryev
链接:https://arxiv.org/abs/1908.06126

[超分辨率]:
【1】 Image Formation Model Guided Deep Image Super-Resolution
图像形成模型引导的深度图像超分辨率
作者: Jinshan Pan, Jinhui Tang
链接:https://arxiv.org/abs/1908.06444

[点云]:
【1】 Rotation Invariant Convolutions for 3D Point Clouds Deep Learning
三维点云深度学习的旋转不变卷积
作者: Zhiyuan Zhang, Sai-Kit Yeung
备注:International Conference on 3D Vision (3DV) 2019
链接:https://arxiv.org/abs/1908.06297

【2】 ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics
ShellNet:使用同心壳统计的高效点云卷积神经网络
作者: Zhiyuan Zhang, Sai-Kit Yeung
备注:International Conference on Computer Vision (ICCV) 2019 Oral
链接:https://arxiv.org/abs/1908.06295

[深度depth相关]:
【1】 Matching-based Depth Camera and Mirrors for 3D Reconstruction
基于匹配的深度相机和反射镜三维重建
作者: Trong Nguyen Nguyen, Jean Meunier
链接:https://arxiv.org/abs/1908.06342

【2】 Mono-SF: Multi-View Geometry Meets Single-View Depth for Monocular Scene Flow Estimation of Dynamic Traffic Scenes
Mono-SF:多视图几何与单视深度相遇的单目场景流量估计动态交通场景
作者: Fabian Brickwedde, Rudolf Mester
备注:accepted to IEEE International Conference on Computer Vision 2019 (ICCV 2019)
链接:https://arxiv.org/abs/1908.06316

[人脸相关]:
【1】 Occlusion Robust Face Recognition Based on Mask Learning with PairwiseDifferential Siamese Network
基于PairwiseDifferential Siamese网络掩模学习的遮挡鲁棒人脸识别
作者: Lingxue Song, Wei Liu
链接:https://arxiv.org/abs/1908.06290

【2】 Attentional Feature-Pair Relation Networks for Accurate Face Recognition
用于精确人脸识别的注意特征对关系网络
作者: Bong-Nam Kang, Daijin Kim
备注:To appear in ICCV 2019
链接:https://arxiv.org/abs/1908.06255

[3D/3D重建等相关]:
【1】 Multi-Garment Net: Learning to Dress 3D People from Images
Multi-Garment Net:学习从图像中为3D人着装
作者: Bharat Lal Bhatnagar, Gerard Pons-Moll
备注:International Conference in Computer Vision (ICCV), 2019
链接:https://arxiv.org/abs/1908.06903

【2】 Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild
深入挖掘混合注释用于野外3D人类恢复
作者: Yu Rong, Chen Change Loy
备注:To appear in ICCV 2019. Code and models are available at penincillin.github.io/dct_iccv2019
链接:https://arxiv.org/abs/1908.06442

【3】 RIO: 3D Object Instance Re-Localization in Changing Indoor Environments
RIO:在不断变化的室内环境中重新定位3D对象实例
作者: Johanna Wald, Matthias Nießner
备注:ICCV 2019 (Oral) video this https URL
链接:https://arxiv.org/abs/1908.06109

【4】 Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysis
Models Genesis:用于3D医学图像分析的通用自动教学模型
作者: Zongwei Zhou, Jianming Liang
链接:https://arxiv.org/abs/1908.06912

【5】 Asynchronous Single-Photon 3D Imaging
异步单光子3D成像
作者: Anant Gupta, Mohit Gupta
链接:https://arxiv.org/abs/1908.06372

[其他视频相关]:
【1】 Video synthesis of human upper body with realistic fac
具有真实感的人体上身视频合成
作者: Zhaoxiang Liu, Shiguo Lian
链接:https://arxiv.org/abs/1908.06607

[其他]:
【1】 Dynamic Graph Message Passing Networks
动态图消息传递网络
作者: Li Zhang, Philip H.S. Torr
链接:https://arxiv.org/abs/1908.06955

【2】 Algorithm Selection for Image Quality Assessment
图像质量评价的算法选择
作者: Markus Wagner, Dietmar Saupe
备注:Presented at the Seventh Workshop on COnfiguration and SElection of ALgorithms (COSEAL), Potsdam, Germany, August 26--27, 2019
链接:https://arxiv.org/abs/1908.06911

【3】 GLAMpoints: Greedily Learned Accurate Match points
GLAMpoint:贪婪地学习精确匹配点
作者: Prune Truong, Sandro De Zanet
链接:https://arxiv.org/abs/1908.06812

【4】 Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path
Floor-SP:按顺序房间方向最短路径进行平面布置图的逆向CAD
作者: Jiacheng Chen, Yasutaka Furukawa
备注:10 pages, 9 figures, accepted to ICCV 2019
链接:https://arxiv.org/abs/1908.06702

【5】 Adaptative Inference Cost With Convolutional Neural Mixture Models
卷积神经混合模型的自适应推理代价
作者: Adria Ruiz, Jakob Verbeek
链接:https://arxiv.org/abs/1908.06694

【6】 In defense of OSVOS
为OSVOS辩护
作者: Yu Liu, Ian Reid
链接:https://arxiv.org/abs/1908.06692

【7】 A Co-analysis Framework for Exploring Multivariate Scientific Data
用于探索多变量科学数据的协同分析框架
作者: Xiangyang He, Hai Lin
链接:https://arxiv.org/abs/1908.06576

【8】 HumanMeshNet: Polygonal Mesh Recovery of Humans
HumanMeshNet:人体多边形网格恢复
作者: Abbhinav Venkat, Avinash Sharma
备注:to appear in ICCV-W, 2019. Project: this https URL
链接:https://arxiv.org/abs/1908.06544

【9】 A New Technique of Camera Calibration: A Geometric Approach Based on Principal Lines
一种新的摄像机标定技术:基于主线的几何方法
作者: Jen-Hui Chuang, Tai-An Chen
链接:https://arxiv.org/abs/1908.06539

【10】 From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer
从开集到闭集:空间分治计数对象
作者: Haipeng Xiong, Chunhua Shen
备注:Accepted by ICCV2019
链接:https://arxiv.org/abs/1908.06473

【11】 Training Deep Learning Models via Synthetic Data: Application in Unmanned Aerial Vehicles
通过合成数据训练深度学习模型:在无人机中的应用
作者: Andreas Kamilaris, Savvas Karatsiolis
备注:Workshop on Deep-learning based computer vision for UAV in conjunction with CAIP 2019, Salerno, italy, September 2019
链接:https://arxiv.org/abs/1908.06472

【12】 Convolutional Neural Network with Median Layers for Denoising Salt-and-Pepper Contaminations
具有中值层的卷积神经网络用于盐和胡椒污染的去噪
作者: Luming Liang, Jing Qin
链接:https://arxiv.org/abs/1908.06452

【13】 Geometric Disentanglement for Generative Latent Shape Models
生成潜形模型的几何解缠
作者: Tristan Aumentado-Armstrong, Sven Dickinson
备注:ICCV 2019
链接:https://arxiv.org/abs/1908.06386

【14】 A Fast and Accurate One-Stage Approach to Visual Grounding
一种快速准确的视觉接地一步法
作者: Zhengyuan Yang, Jiebo Luo
备注:ICCV 2019 Oral
链接:https://arxiv.org/abs/1908.06354

【15】 Language Features Matter: Effective Language Representations for Vision-Language Tasks
语言特征很重要:视觉语言任务的有效语言表征
作者: Andrea Burns, Bryan A. Plummer
备注:ICCV 2019 accepted paper
链接:https://arxiv.org/abs/1908.06327

【16】 Multi-Kernel Filtering: An Extension of Bilateral Filtering Using Image Context
多核滤波:使用图像上下文的双边滤波的扩展
作者: Feihong Liu, Dinggang Shen
链接:https://arxiv.org/abs/1908.06307

【17】 U-CAM: Visual Explanation using Uncertainty based Class Activation Maps
U-CAM:使用基于不确定性的类激活映射的可视解释
作者: Badri N. Patro, Vinay P. Namboodiri
备注:ICCV 2019 (accepted)
链接:https://arxiv.org/abs/1908.06306

【18】 Deep Meta Functionals for Shape Representation
用于形状表示的深元泛函
作者: Gidi Littwin, Lior Wolf
链接:https://arxiv.org/abs/1908.06277

【19】 OmniMVS: End-to-End Learning for Omnidirectional Stereo Matching
OmniMVS:全向立体匹配的端到端学习
作者: Changhee Won, Jongwoo Lim
备注:Accepted by ICCV 2019
链接:https://arxiv.org/abs/1908.06257

【20】 CompenNet++: End-to-end Full Projector Compensation
CompenNet+:端到端全投影仪补偿
作者: Bingyao Huang, Haibin Ling
备注:To appear in ICCV 2019. High-res supplementary material: this https URL Code: this https URL
链接:https://arxiv.org/abs/1908.06246

【21】 Zero Shot Learning for Multi-Modal Real Time Image Registration
用于多模态实时图像配准的零激发学习
作者: Avinash Kori, Ganapathi Krishnamurthi
链接:https://arxiv.org/abs/1908.06213

【22】 Cascaded Parallel Filtering for Memory-Efficient Image-Based Localization
级联并行滤波用于内存高效的基于图像的定位
作者: Wentao Cheng, Xinfeng Zhang
备注:Accepted at ICCV 2019
链接:https://arxiv.org/abs/1908.06141

【23】 Symmetric Cross Entropy for Robust Learning with Noisy Labels
带噪声标签的对称交叉熵鲁棒学习
作者: Yisen Wang, James Bailey
备注:ICCV2019
链接:https://arxiv.org/abs/1908.06112

你可能感兴趣的:(计算机视觉每日论文速递[08.20])