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46篇
[检测分类相关]:
【1】 Part-A^2 Net: 3D Part-Aware and Aggregation Neural Network for Object Detection from Point Cloud
Part-A^2 Net:用于点云目标检测的3D局部感知聚合神经网络
作者: Shaoshuai Shi, Hongsheng Li
链接:https://arxiv.org/abs/1907.03670
【2】 A unified neural network for object detection, multiple object tracking and vehicle re-identification
一种用于目标检测、多目标跟踪和车辆再识别的统一神经网络
作者: Yuhao Xu, Jiakui Wang
链接:https://arxiv.org/abs/1907.03465
【3】 Skin Lesion Analyser: An Efficient Seven-Way Multi-Class Skin Cancer Classification Using MobileNet
皮肤病变分析仪:一种高效的基于MobileNet的七向多类皮肤癌分类方法
作者: Saket S. Chaturvedi, Prakash. S. Prasad
链接:https://arxiv.org/abs/1907.03220
【4】 Revisiting Metric Learning for Few-Shot Image Classification
重新审视度量学习在少镜头图像分类中的应用
作者: Xiaomeng Li, Pheng-Ann Heng
链接:https://arxiv.org/abs/1907.03123
[分割/语义相关]:
【1】 Unified Attentional Generative Adversarial Network for Brain Tumor Segmentation From Multimodal Unpaired Images
基于统一注意生成对抗网络的多模态非配对图像脑肿瘤分割
作者: Wenguang Yuan, Tolga Tasdizen
备注:9 pages, 4 figures, Accepted by MICCAI2019
链接:https://arxiv.org/abs/1907.03548
【2】 Assessing Reliability and Challenges of Uncertainty Estimations for Medical Image Segmentation
医学图像分割不确定度估计的可靠性评估和挑战
作者: Alain Jungo, Mauricio Reyes
备注:Appears in Medical Image Computing and Computer Assisted Interventions (MICCAI), 2019
链接:https://arxiv.org/abs/1907.03338
【3】 Learning joint lesion and tissue segmentation from task-specific hetero-modal datasets
从任务特定的异模数据集中学习关节病变和组织分割
作者: Reuben Dorent, Tom Vercauteren
备注:Accepted as an oral presentation at MIDL 2019 this http URL
链接:https://arxiv.org/abs/1907.03327
【4】 Spacetime Graph Optimization for Video Object Segmentation
视频对象分割的时空图优化
作者: Emanuela Haller, Marius Leordeanu
链接:https://arxiv.org/abs/1907.03326
【5】 SAN: Scale-Aware Network for Semantic Segmentation of High-Resolution Aerial Images
SAN:用于高分辨率航空图像语义分割的尺度感知网络
作者: Jingbo Lin, Houbing Song
链接:https://arxiv.org/abs/1907.03089
【6】 Deep Learning-Based Semantic Segmentation of Microscale Objects
基于深度学习的微尺度对象语义分割
作者: Ekta U. Samani, Ashis G. Banerjee
备注:A condensed version of the paper is published in the Proceedings of the 2019 International Conference on Manipulation, Automation and Robotics at Small Scales
链接:https://arxiv.org/abs/1907.03576
[GAN/对抗式/生成式相关]:
【1】 Correlation via synthesis: end-to-end nodule image generation and radiogenomic map learning based on generative adversarial network
通过合成进行相关性:基于生成性对抗性网络的端到端结节图像生成和放射基因组图学习
作者: Ziyue Xu, Daguang Xu
链接:https://arxiv.org/abs/1907.03728
【2】 Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks
Social-BiGAT:使用Bicycle-gan和Graph注意力网络进行多模态轨迹预测
作者: Vineet Kosaraju, Silvio Savarese
链接:https://arxiv.org/abs/1907.03395
【3】 Dual Adversarial Learning with Attention Mechanism for Fine-grained Medical Image Synthesis
具有注意机制的双对偶对抗学习在精细医学图像合成中的应用
作者: Dong Nie, Dinggang Shen
链接:https://arxiv.org/abs/1907.03297
[行为/时空/光流/姿态/运动]:
【1】 Linking Art through Human Poses
通过人体姿势链接艺术
作者: Tomas Jenicek, Ondřej Chum
链接:https://arxiv.org/abs/1907.03537
【2】 A Deep Learning Approach for Real-Time 3D Human Action Recognition from Skeletal Data
一种从骨骼数据中实时识别三维人体动作的深度学习方法
作者: Huy Hieu Pham, Sergio A Velastin
备注:Accepted by the 16th International Conference on Image Analysis and Recognition (ICIAR2019)
链接:https://arxiv.org/abs/1907.03520
【3】 Multimodal Fusion with Deep Neural Networks for Audio-Video Emotion Recognition
基于深度神经网络的多模态融合在音视频情感识别中的应用
作者: Juan D. S. Ortega, Alessandro L. Koerich
链接:https://arxiv.org/abs/1907.03196
[半/弱/无监督相关]:
【1】 Unsupervised Domain Alignment to Mitigate Low Level Dataset Biases
无监督的域对齐以减轻低级别数据集偏差
作者: Kirthi Shankar Sivamani
备注:10 pages, 4 figures, 6 tables, submitted to ICAAI 2019
链接:https://arxiv.org/abs/1907.03644
【2】 Data Distillation, Face-Related Tasks, Multi Task Learning, Semi-Supervised Learning
数据提取,脸部相关任务,多任务学习,半监督学习
作者: Sepidehsadat Hosseini, Nam Ik Cho
链接:https://arxiv.org/abs/1907.03402
【3】 Unsupervised cycle-consistent deformation for shape matching
用于形状匹配的无监督循环一致变形
作者: Thibault Groueix, Mathieu Aubry
链接:https://arxiv.org/abs/1907.03165
[跟踪相关]:
【1】 TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applications
TrackNet:一个用于跟踪运动应用中的高速和微小对象的深度学习网络
作者: Yu-Chuan Huang, Wen-Chih Peng
链接:https://arxiv.org/abs/1907.03698
[Re-id相关]:
【1】 A Novel Teacher-Student Learning Framework For Occluded Person Re-Identification
一种新的用于阻塞者重新识别的师生学习框架
作者: Jiaxuan Zhuo, Peijia Chen
链接:https://arxiv.org/abs/1907.03253
[其他视频相关]:
【1】 Video Question Generation via Cross-Modal Self-Attention Networks Learning
基于跨模态自我注意网络学习的视频问题生成
作者: Yu-Siang Wang, Winston Hsu
链接:https://arxiv.org/abs/1907.03049
[其他]:
【1】 Point-Voxel CNN for Efficient 3D Deep Learning
点体素CNN用于高效的3D深度学习
作者: Zhijian Liu, Song Han
链接:https://arxiv.org/abs/1907.03739
【2】 Variational Context: Exploiting Visual and Textual Context for Grounding Referring Expressions
变化语境:利用视觉和文本语境为指称表达式奠定基础
作者: Yulei Niu, Shih-Fu Chang
备注:Accepted as regular paper in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). Substantial text overlap with arXiv:1712.01892
链接:https://arxiv.org/abs/1907.03609
【3】 Perceptual representations of structural information in images: application to quality assessment of synthesized view in FTV scenario
图像中结构信息的知觉表示:在FTV场景中综合视图质量评估中的应用
作者: Ling suiyi, Wang Junle
链接:https://arxiv.org/abs/1907.03448
【4】 Bootstrap Model Ensemble and Rank Loss for Engagement Intensity Regression
用于接合强度回归的Bootstrap模型集合和秩损失
作者: Kai Wang, Yu Qiao
备注:This paper is about EmotiW 2019 engagement intensity regression challenge
链接:https://arxiv.org/abs/1907.03422
【5】 Facial Makeup Transfer Combining Illumination Transfer
结合光照转移的面部化妆转移
作者: Xin Jin, Xiaokun Zhang
备注:IEEE Access, conference short version: ISAIR2019
链接:https://arxiv.org/abs/1907.03398
【6】 Learning Structural Graph Layouts and 3D Shapes for Long Span Bridges 3D Reconstruction
大跨度桥梁三维重建中结构图布局和三维形状的学习
作者: Fangqiao Hu, Hui Li
链接:https://arxiv.org/abs/1907.03387
【7】 ELF: Embedded Localisation of Features in pre-trained CNN
精灵:在预先训练的CNN中嵌入特征的本地化
作者: Assia Benbihi, Cédric Pradalier
链接:https://arxiv.org/abs/1907.03261
【8】 Tree-gated Deep Regressor Ensemble For Face Alignment In The Wild
用于野外人脸对齐的树门控深度回归集成
作者: Estephe Arnaud, Kevin Bailly
链接:https://arxiv.org/abs/1907.03248
【9】 ASCNet: Adaptive-Scale Convolutional Neural Networks for Multi-Scale Feature Learning
ASCNet:用于多尺度特征学习的自适应尺度卷积神经网络
作者: Mo Zhang, Quanzheng Li
链接:https://arxiv.org/abs/1907.03241
【10】 FCN: Fully Channel-Concatenated Network for Single Image Super-Resolution
FCN:用于单图像超分辨率的全通道级联网络
作者: Xiaole Zhao, Xueming Zou
备注:19 pages, 14 figures and 5 tables
链接:https://arxiv.org/abs/1907.03221
【11】 Multi-level Wavelet Convolutional Neural Networks
多级小波卷积神经网络
作者: Pengju Liu, Wangmeng Zuo
链接:https://arxiv.org/abs/1907.03128
【12】 Fast Universal Style Transfer for Artistic and Photorealistic Rendering
用于艺术和照片真实感渲染的快速通用样式转换
作者: Jie An, Jinwen Ma
链接:https://arxiv.org/abs/1907.03118
【13】 Bilevel Integrative Optimization for Ill-posed Inverse Problems
不适定反问题的两层综合优化
作者: Risheng Liu, Jin Zhang
链接:https://arxiv.org/abs/1907.03083
【14】 AMD Severity Prediction And Explainability Using Image Registration And Deep Embedded Clustering
利用图像配准和深度嵌入聚类的AMD严重性预测和可解释性
作者: Dwarikanath Mahapatra
链接:https://arxiv.org/abs/1907.03075
【15】 Deep Learning for Fine-Grained Image Analysis: A Survey
用于细粒度图像分析的深度学习:综述
作者: Xiu-Shen Wei, Quan Cui
链接:https://arxiv.org/abs/1907.03069
【16】 Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets
基于依赖感知的图像集无约束人脸识别注意控制
作者: Xiaofeng Liu, Jane You
链接:https://arxiv.org/abs/1907.03030
【17】 Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning
基于高斯噪声水平学习的盲泛贝叶斯图像去噪
作者: Majed El Helou, Sabine Susstrunk
链接:https://arxiv.org/abs/1907.03029
【18】 Embodied Vision-and-Language Navigation with Dynamic Convolutional Filters
具有动态卷积滤波器的具体化视觉和语言导航
作者: Federico Landi, Rita Cucchiara
备注:BMVC 2019 (Oral)
链接:https://arxiv.org/abs/1907.02985
【19】 Prediction of Soil Moisture Content Based On Satellite Data and Sequence-to-Sequence Networks
基于卫星数据和Sequence-to-Sequence网络的土壤含水量预测
作者: Natalia Efremova, Gleb Antipov
备注:Presented on NeurIPS 2018 WiML workshop
链接:https://arxiv.org/abs/1907.03697
【20】 Segway DRIVE Benchmark: Place Recognition and SLAM Data Collected by A Fleet of Delivery Robots
Segway驱动基准:地点识别和SLAM数据由交付机器人车队收集
作者: Jianzhu Huai, Zichong Chen
链接:https://arxiv.org/abs/1907.03424
【21】 Travel Time Estimation without Road Networks: An Urban Morphological Layout Representation Approach
无路网的出行时间估算:一种城市形态布局表示方法
作者: Wuwei Lan, Bin Zhao
备注:Accepted at IJCAI 2019
链接:https://arxiv.org/abs/1907.03381
【22】 Adaptive Weighting Depth-variant Deconvolution of Fluorescence Microscopy Images with Convolutional Neural Network
基于卷积神经网络的荧光显微图像自适应加权深度可变反褶积
作者: Da He, Sung-Liang Chen
链接:https://arxiv.org/abs/1907.03217
【23】 Regularizing linear inverse problems with convolutional neural networks
用卷积神经网络正则化线性反问题
作者: Reinhard Heckel
链接:https://arxiv.org/abs/1907.03100
【24】 Generative Counterfactual Introspection for Explainable Deep Learning
可解释深度学习的生成性反事实反思
作者: Shusen Liu, Yong Han
链接:https://arxiv.org/abs/1907.03077