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49篇
[检测分类相关]:
【1】 An Integrated Image Filter for Enhancing Change Detection Results
一种用于增强变化检测结果的集成图像滤波器
作者: Dawei Li, Sifan Wang
链接:https://arxiv.org/abs/1907.01301
【2】 Lane Detection and Classification using Cascaded CNNs
基于层叠CNN的车道检测与分类
作者: Fabio Pizzati, Fernando García
备注:Presented at Eurocast 2019
链接:https://arxiv.org/abs/1907.01294
【3】 Multi-Cue Vehicle Detection for Semantic Video Compression In Georegistered Aerial Videos
多线索车辆检测在地籍航空视频语义视频压缩中的应用
作者: Noor Al-Shakarji, Kannappan Palaniappan
备注:CVPR2019 Workshop on Detecting Objects in Aerial Images
链接:https://arxiv.org/abs/1907.01176
【4】 High-speed Railway Fastener Detection and Localization System
高速铁路扣件检测与定位系统
作者: Qing Song, Mengjie Hu
链接:https://arxiv.org/abs/1907.01141
【5】 Symmetry Detection and Classification in Drawings of Graphs
图形绘制中的对称性检测与分类
作者: Felice De Luca, Stephen Kobourov
备注:18 pages
链接:https://arxiv.org/abs/1907.01004
【6】 Speaker-independent classification of phonetic segments from raw ultrasound in child speech
儿童语音中原始超声语音段的非特定人分类
作者: Manuel Sam Ribeiro, Steve Renals
备注:5 pages, 4 figures, published in ICASSP2019 (IEEE International Conference on Acoustics, Speech and Signal Processing, 2019)
链接:https://arxiv.org/abs/1907.01413
[分割/语义相关]:
【1】 Where are the Masks: Instance Segmentation with Image-level Supervision
掩模在哪里:图像级监控的实例分割
作者: Issam H. Laradji, Mark Schmidt
备注:Accepted at BMVC2019
链接:https://arxiv.org/abs/1907.01430
【2】 CSSegNet: Fine-Grained Cardiac Structures Segmentation Using Dilated Pyramid Pooling in U-net
CSSegNet:U-Net中基于扩张金字塔集合的细粒度心脏结构分割
作者: Fei Feng, Jiajia Luo
链接:https://arxiv.org/abs/1907.01390
【3】 The Ethical Dilemma when (not) Setting up Cost-based Decision Rules in Semantic Segmentation
在语义分割中建立基于成本的决策规则时的伦理困境
作者: Robin Chan, Hanno Gottschalk
链接:https://arxiv.org/abs/1907.01342
【4】 Dynamic Face Video Segmentation via Reinforcement Learning
基于强化学习的动态人脸视频分割
作者: Yujiang Wang, Maja Pantic
链接:https://arxiv.org/abs/1907.01296
【5】 Improving the generalizability of convolutional neural network-based segmentation on CMR images
提高基于卷积神经网络的CMR图像分割的泛化能力
作者: Chen Chen, Daniel Rueckert
链接:https://arxiv.org/abs/1907.01268
【6】 Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation
提议、跟踪和分割(PTS):一种用于视频对象分割的级联网络
作者: Qiang Zhou, Wenyu Liu
链接:https://arxiv.org/abs/1907.01203
[GAN/对抗式/生成式相关]:
【1】 Landmark Assisted CycleGAN for Cartoon Face Generation
用于卡通人脸生成的地标辅助CycleGAN
作者: Ruizheng Wu, Jiaya Jia
链接:https://arxiv.org/abs/1907.01424
【2】 A Single Video Super-Resolution GAN for Multiple Downsampling Operators based on Pseudo-Inverse Image Formation Models
基于伪逆成像模型的多个下采样算子的单视频超分辨率GaN
作者: Santiago López-Tapia, Aggelos K. Katsaggelos
链接:https://arxiv.org/abs/1907.01399
【3】 Multi-scale GANs for Memory-efficient Generation of High Resolution Medical Images
多尺度遗传算法在高分辨率医学图像存储中的应用
作者: Hristina Uzunova, Jan Ehrhardt
链接:https://arxiv.org/abs/1907.01376
【4】 Disentangled Makeup Transfer with Generative Adversarial Network
基于生成性对抗网络的解缠化妆迁移
作者: Honglun Zhang, Yaohui Jin
链接:https://arxiv.org/abs/1907.01144
【5】 Diminishing the Effect of Adversarial Perturbations via Refining Feature Representation
通过细化特征表示消除对抗性扰动的影响
作者: Nader Asadi, Mahdi Eftekhari
链接:https://arxiv.org/abs/1907.01023
[行为/时空/光流/姿态/运动]:
【1】 Attribute-Driven Spontaneous Motion in Unpaired Image Translation
非成对图像翻译中的属性驱动自发运动
作者: Ruizheng Wu, Jiaya Jia
链接:https://arxiv.org/abs/1907.01452
【2】 FastDVDnet: Towards Real-Time Video Denoising Without Explicit Motion Estimation
FastDVDnet:无需显式运动估计的实时视频去噪
作者: Matias Tassano, Thomas Veit
备注:Code for this algorithm and results can be found in this https URL arXiv admin note: text overlap with arXiv:1906.11890
链接:https://arxiv.org/abs/1907.01361
[半/弱/无监督相关]:
【1】 Unsupervised Deformable Image Registration Using Cycle-Consistent CNN
基于循环一致CNN的无监督变形图像配准
作者: Boah Kim, Jong Chul Ye
备注:accepted for MICCAI 2019
链接:https://arxiv.org/abs/1907.01319
[数据集dataset]:
【1】 HO-3D: A Multi-User, Multi-Object Dataset for Joint 3D Hand-Object Pose Estimation
HO-3D:一种用于手-物体联合姿态估计的多用户多目标数据集
作者: Shreyas Hampali, Vincent Lepetit
链接:https://arxiv.org/abs/1907.01481
【2】 Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer
稳健的单目深度估计:用于零射交叉数据集传输的混合数据集
作者: Katrin Lasinger, Vladlen Koltun
链接:https://arxiv.org/abs/1907.01341
【3】 Brno Mobile OCR Dataset
Brno Mobile OCR数据集
作者: Martin Kišš, Oldřich Kodym
链接:https://arxiv.org/abs/1907.01307
[其他视频相关]:
【1】 Procedure Planning in Instructional Videos
教学视频中的程序规划
作者: Chien-Yi Chang, Juan Carlos Niebles
链接:https://arxiv.org/abs/1907.01172
【2】 Learnable Gated Temporal Shift Module for Deep Video Inpainting
用于深度视频修复的可学习门控时序移位模块
作者: Ya-Liang Chang, Winston Hsu
备注:Accepted to BMVC 2019
链接:https://arxiv.org/abs/1907.01131
[其他]:
【1】 Obj-GloVe: Scene-Based Contextual Object Embedding
OBJ手套:基于场景的上下文对象嵌入
作者: Canwen Xu, Chenliang Li
链接:https://arxiv.org/abs/1907.01478
【2】 An End-to-End Neural Network for Image Cropping by Learning Composition from Aesthetic Photos
从审美照片中学习构图的端到端图像裁剪神经网络
作者: Peng Lu, Xiaofu Jin
链接:https://arxiv.org/abs/1907.01432
【3】 Improving Borderline Adulthood Facial Age Estimation through Ensemble Learning
利用集成学习改进成人边缘年龄估计
作者: Felix Anda, Mark Scanlon
链接:https://arxiv.org/abs/1907.01427
【4】 A Closest Point Proposal for MCMC-based Probabilistic Surface Registration
基于MCMC的概率曲面配准的最近点方案
作者: Dennis Madsen, Marcel Lüthi
链接:https://arxiv.org/abs/1907.01414
【5】 Training Auto-encoder-based Optimizers for Terahertz Image Reconstruction
训练基于自动编码器的太赫兹图像重建优化器
作者: Tak Ming Wong, Michael Möller
链接:https://arxiv.org/abs/1907.01377
【6】 Pathologist-Level Grading of Prostate Biopsies with Artificial Intelligence
人工智能在前列腺活检病理分级中的应用
作者: Peter Ström (1), Sweden)
链接:https://arxiv.org/abs/1907.01368
【7】 Semi-Bagging Based Deep Neural Architecture to Extract Text from High Entropy Images
基于半套袋的深神经结构在高熵图像文本提取中的应用
作者: Pranay Dugar, Saswata Sahoo
链接:https://arxiv.org/abs/1907.01284
【8】 An Analysis of Deep Neural Networks with Attention for Action Recognition from a Neurophysiological Perspective
具有注意力的深层神经网络用于动作识别的神经生理学分析
作者: Swathikiran Sudhakaran, Oswald Lanz
备注:Presented as an extended abstract in the Mutual benefits of cognitive and computer vision (MBCCV) workshop, CVPR 2019
链接:https://arxiv.org/abs/1907.01273
【9】 TedEval: A Fair Evaluation Metric for Scene Text Detectors
TedEval:一种用于场景文本检测器的公平评价指标
作者: Chae Young Lee, Hwalsuk Lee
备注:7 pages, 10 figures, Accepted by Workshop on Industrial Applications of Document Analysis and Recognition 2019
链接:https://arxiv.org/abs/1907.01227
【10】 Inverse Attention Guided Deep Crowd Counting Network
逆向注意引导深度人群计数网络
作者: Vishwanath A. Sindagi, Vishal M. Patel
备注:Accepted at 16th IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS) 2019
链接:https://arxiv.org/abs/1907.01193
【11】 Generative Guiding Block: Synthesizing Realistic Looking Variants Capable of Even Large Change Demands
生成性指导块:综合具有现实外观的变体,甚至可以满足较大的变化需求
作者: Minho Park, Yong Man Ro
备注:This work is accepted in ICIP 2019
链接:https://arxiv.org/abs/1907.01187
【12】 Multi-scale Template Matching with Scalable Diversity Similarity in an Unconstrained Environment
无约束环境下具有可缩放分集相似性的多尺度模板匹配
作者: Yi Zhang, Takuya Akashi
备注:British Machine Vision Conference (BMVC2019)
链接:https://arxiv.org/abs/1907.01150
【13】 Language2Pose: Natural Language Grounded Pose Forecasting
语言2Pose:基于自然语言的姿态预测
作者: Chaitanya Ahuja, Louis-Philippe Morency
链接:https://arxiv.org/abs/1907.01108
【14】 Nature Inspired Dimensional Reduction Technique for Fast and Invariant Visual Feature Extraction
自然激励降维技术在快速不变视觉特征提取中的应用
作者: Ravimal Bandara, Nor Aniza Abdullah
链接:https://arxiv.org/abs/1907.01102
【15】 Multiview Aggregation for Learning Category-Specific Shape Reconstruction
学习类别特定形状重建的多视图聚合
作者: Srinath Sridhar, Leonidas J. Guibas
链接:https://arxiv.org/abs/1907.01085
【16】 DeepTEGINN: Deep Learning Based Tools to Extract Graphs from Images of Neural Networks
DeepTEGINN:基于深度学习的神经网络图像提取工具
作者: Gustavo Borges Moreno e Mello, Stefano Nichele
备注:5 pages, 2 figures, ICDL IEEE conference 2019
链接:https://arxiv.org/abs/1907.01062
【17】 Associative Embedding for Game-Agnostic Team Discrimination
基于联想嵌入的博弈论团队识别
作者: Maxime Istasse, Christophe De Vleeschouwer
备注:Published in CVPR 2019 workshop Computer Vision in Sports, under the name "Associative Embedding for Team Discrimination" (this http URL)
链接:https://arxiv.org/abs/1907.01058
【18】 Learning to aggregate feature representations
学习聚合特征表示
作者: Guy Gaziv
备注:4 pages, 2 figures, Algonauts2019
链接:https://arxiv.org/abs/1907.01034
【19】 Method of diagnosing heart disease based on deep learning ECG signal
基于深度学习ECG信号的心脏病诊断方法
作者: Jie Zhang, Xuegang Shi
链接:https://arxiv.org/abs/1907.01514
【20】 Bayesian Optimization on Large Graphs via a Graph Convolutional Generative Model: Application in Cardiac Model Personalization
基于图卷积生成模型的大图贝叶斯优化:在心脏模型个性化中的应用
作者: Jwala Dhamala, Linwei Wang
链接:https://arxiv.org/abs/1907.01406
【21】 Dual Network Architecture for Few-view CT --Trained on ImageNet Data and Transferred for Medical Imaging
用于少视CT的双网结构-基于ImageNet数据的训练和医学成像传输
作者: Huidong Xie, Ge Wang
链接:https://arxiv.org/abs/1907.01262
【22】 Kite: Automatic speech recognition for unmanned aerial vehicles
KIT:无人驾驶飞行器的自动语音识别
作者: Dan Oneata, Horia Cucu
备注:5 pages, accepted at Interspeech 2019
链接:https://arxiv.org/abs/1907.01195
【23】 Robust Tensor Completion Using Transformed Tensor SVD
基于变换张量奇异值分解的鲁棒张量完备化
作者: Guangjing Song, Xiongjun Zhang
链接:https://arxiv.org/abs/1907.01113
【24】 Accurate, reliable and fast robustness evaluation
准确、可靠、快速的鲁棒性评价
作者: Wieland Brendel, Matthias Bethge
链接:https://arxiv.org/abs/1907.01003
翻译:腾讯翻译君