同步wx公众号(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。* ̄rǒ ̄)
cs.CV 方向,今日共计70篇
[检测分类相关]:
【1】 Towards Deep Learning-Based EEG Electrode Detection Using Automatically Generated Labels
基于深度学习的脑电电极自动生成标记检测方法
作者: Nils Gessert, Alexander Schlaefer
备注:Accepted at the CURAC 2019 Conference
链接:https://arxiv.org/abs/1908.04186
【2】 Semi-Supervised Video Salient Object Detection Using Pseudo-Labels
基于伪标签的半监督视频运动目标检测
作者: Pengxiang Yan, Liang Lin
备注:Accepted by ICCV 2019
链接:https://arxiv.org/abs/1908.04051
【3】 Is it Raining Outside? Detection of Rainfall using General-Purpose Surveillance Cameras
外面下雨了吗?使用通用监视摄像机检测降雨量
作者: Joakim Bruslund Haurum, Thomas B. Moeslund
备注:10 pages, 7 figures, CVPR2019 V4AS workshop
链接:https://arxiv.org/abs/1908.04034
【4】 Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach
深入研究无人驾驶飞行器的鲁棒目标检测:一种深度干扰解缠方法
作者: Zhenyu Wu, Zhangyang Wang
备注:Accepted to International Conference on Computer Vision (ICCV) 2019
链接:https://arxiv.org/abs/1908.03856
【5】 IoU Loss for 2D/3D Object Detection
2D/3D对象检测的IOU丢失
作者: Dingfu Zhou, Ruigang Yang
备注:Accepted by international conference on 3d vision 2019
链接:https://arxiv.org/abs/1908.03851
【6】 Object-Aware Instance Labeling for Weakly Supervised Object Detection
弱监督对象检测中的对象感知实例标记
作者: Satoshi Kosugi, Kiyoharu Aizawa
备注:Accepted to ICCV 2019 (oral)
链接:https://arxiv.org/abs/1908.03792
【7】 Recent Advances in Deep Learning for Object Detection
用于目标检测的深度学习的最新进展
作者: Xiongwei Wu, Steven C.H. Hoi
链接:https://arxiv.org/abs/1908.03673
【8】 Deep ensemble network with explicit complementary model for accuracy-balanced classification
具有显式互补模型的深度集成网络用于精度平衡分类
作者: Dohyun Kim, Joongheon Kim
链接:https://arxiv.org/abs/1908.03671
【9】 Star-convex Polyhedra for 3D Object Detection and Segmentation in Microscopy
用于显微镜中三维物体检测和分割的星形凸多面体
作者: Martin Weigert, Gene Myers
链接:https://arxiv.org/abs/1908.03636
【10】 Learning morphological operators for skin detection
学习形态学算子进行皮肤检测
作者: Alessandra Lumini, Filippo Berno
链接:https://arxiv.org/abs/1908.03630
【11】 A Mask-RCNN Baseline for Probabilistic Object Detection
一种用于概率目标检测的MASK-RCNN基线
作者: Phil Ammirato, Alexander C. Berg
备注:2nd place in 1st PODC at CVPR 2019
链接:https://arxiv.org/abs/1908.03621
[分割/语义相关]:
【1】 Explicit Shape Encoding for Real-Time Instance Segmentation
用于实时实例分割的显式形状编码
作者: Wenqiang Xu, Cewu Lu
备注:to appear in ICCV2019
链接:https://arxiv.org/abs/1908.04067
【2】 An overlapping-free leaf segmentation method for plant point clouds
一种无重叠的植物点云叶片分割方法
作者: Dawei Li, Siyuan Yan
备注:24 Pages, 18 Figures, 7 Tables. Intends to submit to an open-access journal
链接:https://arxiv.org/abs/1908.04018
【3】 Automated Brain Tumour Segmentation Using Deep Fully Convolutional Residual Networks
基于深度完全卷积残差网络的脑肿瘤自动分割
作者: Indrajit Mazumdar
链接:https://arxiv.org/abs/1908.04250
【4】 Left Ventricle Quantification Using Direct Regression with Segmentation Regularization and Ensembles of Pretrained 2D and 3D CNNs
使用分段正则化和预训练的2D和3D CNN集合的直接回归进行左心室定量
作者: Nils Gessert, Alexander Schlaefer
备注:Accepted at the MICCAI Workshop STACOM 2019
链接:https://arxiv.org/abs/1908.04181
【5】 Improving Robustness of Deep Learning Based Knee MRI Segmentation: Mixup and Adversarial Domain Adaptation
提高基于深度学习的膝关节MRI分割的鲁棒性:混合和对抗性域自适应
作者: Egor Panfilov, Simo Saarakkala
链接:https://arxiv.org/abs/1908.04126
【6】 Automated retinal vessel segmentation based on morphological preprocessing and 2D-Gabor wavelets
基于形态学预处理和2D-Gabor小波的视网膜血管自动分割
作者: Kundan Kumar, Suraj
链接:https://arxiv.org/abs/1908.04123
【7】 Visual and Semantic Prototypes-Jointly Guided CNN for Generalized Zero-shot Learning
视觉和语义原型-联合指导的CNN用于广义零射击学习
作者: Chuanxing Geng, Songcan Chen
链接:https://arxiv.org/abs/1908.03983
【8】 Automatic acute ischemic stroke lesion segmentation using semi-supervised learning
基于半监督学习的急性缺血性卒中病变自动分割
作者: Bin Zhao, Shuxue Ding
链接:https://arxiv.org/abs/1908.03735
【9】 Distance Map Loss Penalty Term for Semantic Segmentation
用于语义分割的距离图丢失惩罚项
作者: Francesco Caliva, Valentina Pedoia
备注:Medical Imaging with Deep Learning (MIDL2019) Conference [arXiv:1907.08612], Extended Abstract
链接:https://arxiv.org/abs/1908.03679
[GAN/对抗式/生成式相关]:
【1】 GAN-Tree: An Incrementally Learned Hierarchical Generative Framework for Multi-Modal Data Distributions
GAN-Tree:一种增量学习的多模态数据分布层次生成框架
作者: Jogendra Nath Kundu, R. Venkatesh Babu
备注:Accepted at ICCV 2019
链接:https://arxiv.org/abs/1908.03919
【2】 UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation
UM-Adapt:使用对抗性跨任务精馏的无监督多任务适应
作者: Jogendra Nath Kundu, R. Venkatesh Babu
备注:Oral Paper in ICCV 2019
链接:https://arxiv.org/abs/1908.03884
【3】 Semi-Supervised Self-Growing Generative Adversarial Networks for Image Recognition
用于图像识别的半监督自增长生成对抗性网络
作者: Haoqian Wang, Qionghai Dai
链接:https://arxiv.org/abs/1908.03850
【4】 AutoGAN: Neural Architecture Search for Generative Adversarial Networks
AutoGAN:生成性对抗网络的神经结构搜索
作者: Xinyu Gong, Zhangyang Wang
备注:accepted by ICCV 2019
链接:https://arxiv.org/abs/1908.03835
【5】 DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
deblurGAN-v2:去模糊(数量级)更快更好
作者: Orest Kupyn, Zhangyang Wang
备注:Accepted in ICCV 2019
链接:https://arxiv.org/abs/1908.03826
【6】 Conditional Generative Adversarial Networks for Data Augmentation and Adaptation in Remotely Sensed Imagery
遥感图像数据增强和适应的条件生成对抗网络
作者: Jonathan Howe, Aaron A. Reite
链接:https://arxiv.org/abs/1908.03809
【7】 Efficient Structurally-Strengthened Generative Adversarial Network for MRI Reconstruction
用于MRI重建的高效结构增强的生成性对抗网络
作者: Wenzhong Zhou, Liping Fang
链接:https://arxiv.org/abs/1908.03858
[行为/时空/光流/姿态/运动]:
【1】 Multi-Frame Content Integration with a Spatio-Temporal Attention Mechanism for Person Video Motion Transfer
具有时空注意机制的多帧内容集成用于个人视频运动转移
作者: Kun Cheng, Wei Liu
链接:https://arxiv.org/abs/1908.04013
【2】 ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks
ACNet:通过非对称卷积块增强强大CNN的核心骨架
作者: Xiaohan Ding, Jungong Han
备注:Accepted to ICCV 2017
链接:https://arxiv.org/abs/1908.03930
【3】 Lightweight and Scalable Particle Tracking and Motion Clustering of 3D Cell Trajectories
轻量级和可伸缩的3D细胞轨迹的粒子跟踪和运动聚类
作者: Mojtaba S. Fazli, Shannon Quinn
备注:Accepted to 2019 IEEE International Conference on Data Science and Advanced Analytics
链接:https://arxiv.org/abs/1908.03775
【4】 User independent Emotion Recognition with Residual Signal-Image Network
基于残差信号-图像网络的独立于用户的情感识别
作者: Guanghao Yin, Ning Zou
链接:https://arxiv.org/abs/1908.03692
【5】 DynaNet: Neural Kalman Dynamical Model for Motion Estimation and Prediction
DynaNet:用于运动估计和预测的神经Kalman动力学模型
作者: Changhao Chen, Andrew Markham
链接:https://arxiv.org/abs/1908.03918
【6】 Emotionless: Privacy-Preserving Speech Analysis for Voice Assistants
无情感:语音助理隐私保护语音分析
作者: Ranya Aloufi, David Boyle
备注:5 pages, 4 figures, privacy Preserving Machine Learning Workshop, CCS 2019
链接:https://arxiv.org/abs/1908.03632
[半/弱/无监督相关]:
【1】 Self-supervised Data Bootstrapping for Deep Optical Character Recognition of Identity Documents
用于身份文件深度光学字符识别的自监督数据自举
作者: Oliver Mothes, Joachim Denzler
链接:https://arxiv.org/abs/1908.04027
【2】 Unsupervised Neural Quantization for Compressed-Domain Similarity Search
压缩域相似性搜索的无监督神经量化
作者: Stanislav Morozov, Artem Babenko
链接:https://arxiv.org/abs/1908.03883
【3】 Semi-Supervised Multi-Task Learning With Chest X-Ray Images
基于胸部X光图像的半监督多任务学习
作者: Abdullah-Al-Zubaer Imran, Demetri Terzopoulos
链接:https://arxiv.org/abs/1908.03693
[跟踪相关]:
【1】 Robust Online Multi-target Visual Tracking using a HISP Filter with Discriminative Deep Appearance Learning
基于区分深度外观学习的HISP滤波器鲁棒在线多目标视觉跟踪
作者: Nathanael L. Baisa
链接:https://arxiv.org/abs/1908.03945
【2】 Attentive Deep Regression Networks for Real-Time Visual Face Tracking in Video Surveillance
用于视频监控中实时视觉人脸跟踪的关注深度回归网络
作者: Safa Alver, Ugur Halici
链接:https://arxiv.org/abs/1908.03812
【3】 Boundary Effect-Aware Visual Tracking for UAV with Online Enhanced Background Learning and Multi-Frame Consensus Verification
基于在线增强背景学习和多帧一致性验证的无人机边界效应感知视觉跟踪
作者: Changhong Fu, Peng Lu
备注:IROS 2019 accepted, 8 pages, 9 figures
链接:https://arxiv.org/abs/1908.03701
[迁移学习/domain/主动学习/自适应]:
【1】 Domain-Specific Embedding Network for Zero-Shot Recognition
用于零炮识别的域特定嵌入网络
作者: Shaobo Min, Yongdong Zhang
链接:https://arxiv.org/abs/1908.04174
【2】 Dynamic Region Division for Adaptive Learning Pedestrian Counting
自适应学习行人计数的动态区域划分
作者: Gaoqi He, Yubo Yuan
备注:accepted by IEEE International Conference on Multimedia and Expo (ICME) 2019
链接:https://arxiv.org/abs/1908.03978
【3】 Instance Enhancement Batch Normalization: an Adaptive Regulator of Batch Noise
实例增强批次归一化:一种批次噪声的自适应调节器
作者: Senwei Liang, Haizhao Yang
链接:https://arxiv.org/abs/1908.04008
[裁剪/量化/加速相关]:
【1】 Human Perceptual Evaluations for Image Compression
人类对图像压缩的感知评估
作者: Yash Patel, R. Manmatha
备注:arXiv admin note: text overlap with arXiv:1907.08310
链接:https://arxiv.org/abs/1908.04187
【2】 Decision Trees for Complexity Reduction in Video Compression
视频压缩中降低复杂度的决策树
作者: Natasha Westland, Marta Mrak
链接:https://arxiv.org/abs/1908.04168
【3】 DSIC: Deep Stereo Image Compression
DSIC:深度立体声图像压缩
作者: Jerry Liu, Raquel Urtasun
备注:Accepted at International Conference on Computer Vision 2019
链接:https://arxiv.org/abs/1908.03631
[Re-id相关]:
【1】 Temporal Knowledge Propagation for Image-to-Video Person Re-identification
用于图像到视频人再识别的时间知识传播
作者: Xinqian Gu, Xilin Chen
备注:Accepted by ICCV 2019
链接:https://arxiv.org/abs/1908.03885
[深度depth相关]:
【1】 Exploiting temporal consistency for real-time video depth estimation
利用时间一致性进行实时视频深度估计
作者: Haokui Zhang, Youliang Yan
备注:Accepted to Proc. Int. Conf. Computer Vision 2019
链接:https://arxiv.org/abs/1908.03706
[人脸相关]:
【1】 MobileFAN: Transferring Deep Hidden Representation for Face Alignment
MobileFAN:传递用于面部对齐的深度隐藏表示
作者: Yang Zhao, Shengwu Xiong
链接:https://arxiv.org/abs/1908.03839
[3D/3D重建等相关]:
【1】 Enhanced 3D convolutional networks for crowd counting
用于人群计数的增强型3D卷积网络
作者: Zhikang Zou, Pan Zhou
备注:Accepted to BMVC 2019
链接:https://arxiv.org/abs/1908.04121
[其他视频相关]:
【1】 Sentence Specified Dynamic Video Thumbnail Generation
句子指定的动态视频缩略图生成
作者: Yiitan Yuan, Wenwu Zhu
链接:https://arxiv.org/abs/1908.04052
【2】 Exploiting Temporal Relationships in Video Moment Localization with Natural Language
利用自然语言开发视频矩定位中的时间关系
作者: Songyang Zhang, Jiebo Luo
链接:https://arxiv.org/abs/1908.03846
[其他]:
【1】 LIP: Local Importance-based Pooling
LIP:基于局部重要性的池
作者: Ziteng Gao, Gangshan Wu
备注:Accepted by ICCV 2019
链接:https://arxiv.org/abs/1908.04156
【2】 Jointly Aligning Millions of Images with Deep Penalised Reconstruction Congealing
用深度惩罚重建凝聚联合对齐数百万幅图像
作者: Roberto Annunziata, Jacques Cali
备注:International Conference on Computer Vision 2019 (ICCV 2019), Seoul, Korea
链接:https://arxiv.org/abs/1908.04130
【3】 Multimodal Unified Attention Networks for Vision-and-Language Interactions
视觉与语言交互的多模态统一注意网络
作者: Zhou Yu, Qi Tian
链接:https://arxiv.org/abs/1908.04107
【4】 Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold
变分自编码回归:复流形上视觉数据的高维回归
作者: YoungJoon Yoo, Jin Young Choi
备注:Published in CVPR 2017
链接:https://arxiv.org/abs/1908.04015
【5】 Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking
基于多模态张量融合和重新排序的图像和文本匹配
作者: Tan Wang, Jingkuan Song
备注:9 pages, 7 figures, ACM Multimedia 2019
链接:https://arxiv.org/abs/1908.04011
【6】 Efficiency and Scalability of Multi-Lane Capsule Networks (MLCN)
多通道胶囊网络(MLCN)的效率和可扩展性
作者: Vanderson M. do Rosario, Edson Borin
链接:https://arxiv.org/abs/1908.03935
【7】 HBONet: Harmonious Bottleneck on Two Orthogonal Dimensions
HBONet:两个正交维度上的和谐瓶颈
作者: Duo Li, Anbang Yao
备注:Accepted by ICCV 2019. Code and pretrained models are available at this https URL
链接:https://arxiv.org/abs/1908.03888
【8】 To Beta or Not To Beta: Information Bottleneck for DigitaL Image Forensics
到Beta还是不Beta:数字图像取证的信息瓶颈
作者: Aurobrata Ghosh, Maneesh Singh
链接:https://arxiv.org/abs/1908.03864
【9】 StructureFlow: Image Inpainting via Structure-aware Appearance Flow
StructureFlow:通过结构感知的外观流进行图像修复
作者: Yurui Ren, Ge Li
链接:https://arxiv.org/abs/1908.03852
【10】 SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Counting
SCAR:用于人群计数的空间/通道注意回归网络
作者: Junyu Gao, Yuan Yuan
链接:https://arxiv.org/abs/1908.03716
【11】 Bayesian Loss for Crowd Count Estimation with Point Supervision
点监督下人群计数估计的贝叶斯损失
作者: Zhiheng Ma, Yihong Gong
备注:Accepted by ICCV 2019 as an oral presentation
链接:https://arxiv.org/abs/1908.03684
【12】 Unconstrained Foreground Object Search
无约束前景对象搜索
作者: Yinan Zhao, Danna Gurari
备注:To appear in ICCV 2019
链接:https://arxiv.org/abs/1908.03675
【13】 A Distraction Score for Watermarks
水印的分心分数
作者: Aurelia Guy, Sema Berkiten
链接:https://arxiv.org/abs/1908.03651
【14】 Understanding Optical Music Recognition
了解光学音乐识别
作者: Jorge Calvo Zaragoza, Alexander Pacha
链接:https://arxiv.org/abs/1908.03608
【15】 Deep Tone Mapping Operator for High Dynamic Range Images
高动态范围图像的深度色调映射算子
作者: Aakanksha Rana, Aljosa Smolic
链接:https://arxiv.org/abs/1908.04197
【16】 Douglas-Quaid -- Open Source Image Matching Library
Douglas-Quaid-开源图像匹配库
作者: Vincent Falconieri
链接:https://arxiv.org/abs/1908.04014
【17】 Structural Similarity based Anatomical and Functional Brain Imaging Fusion
基于结构相似性的解剖脑功能成像融合
作者: Nishant Kumar, Stefan Gumhold
备注:9 pages, 3 figures, MICCAI-MBIA 2019
链接:https://arxiv.org/abs/1908.03958
【18】 Natural-Logarithm-Rectified Activation Function in Convolutional Neural Networks
卷积神经网络中的自然对数校正激活函数
作者: Yang Liu, Jinghua Qu
链接:https://arxiv.org/abs/1908.03682
【19】 Synthetic Elastography using B-mode Ultrasound through a Deep Fully-Convolutional Neural Network
基于深度全卷积神经网络的B型超声综合弹性成像
作者: R. R. Wildeboer, M. Mischi
链接:https://arxiv.org/abs/1908.03573
翻译:腾讯翻译君