同步公众号(arXiv每日学术速递),欢迎关注,感谢支持哦~
[检测分类相关]:
【1】 Co-Saliency Detection with Co-Attention Fully Convolutional Network
基于共关注全卷积网络的共显著检测
作者: Guangshuai Gao, Yunhong Wang
链接:https://arxiv.org/abs/2008.08909
【2】 Line detection via a lightweight CNN with a Hough Layer
通过带有霍夫层的轻量级CNN进行直线检测
作者: Lev Teplyakov, Dmitry Nikolaev
链接:https://arxiv.org/abs/2008.08884
【3】 Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking
基于运动建模的多目标同时检测与跟踪
作者: ShiJie Sun, Mubarak Shah
备注:25 pages, 9 figures, has been accepted by the ECCCV 2020
链接:https://arxiv.org/abs/2008.08826
【4】 Grasping Detection Network with Uncertainty Estimation for Confidence-Driven Semi-Supervised Domain Adaptation
基于不确定性估计的置信度驱动半监督域自适应抓取检测网络
作者: Haiyue Zhu, Wei Lin
备注:6 pages, 7 figures, accepted in IROS 2020
链接:https://arxiv.org/abs/2008.08817
【5】 Spatial--spectral FFPNet: Attention-Based Pyramid Network for Segmentation and Classification of Remote Sensing Images
空间光谱FFPNet:基于注意力的遥感图像分割分类金字塔网络
作者: Qingsong Xu, Yue Zeng
链接:https://arxiv.org/abs/2008.08775
【6】 Deformable PV-RCNN: Improving 3D Object Detection with Learned Deformations
可变形PV-RCNN:利用学习变形改进三维目标检测
作者: Prarthana Bhattacharyya, Krzysztof Czarnecki
备注:Accepted at ECCV 2020 Workshop on Perception for Autonomous Driving
链接:https://arxiv.org/abs/2008.08766
【7】 iCaps: An Interpretable Classifier via Disentangled Capsule Networks
ICAPS:一种基于解缠胶囊网络的可解释分类器
作者: Dahuin Jung, Sungroh Yoon
备注:ECCV 2020
链接:https://arxiv.org/abs/2008.08756
【8】 $β$-Variational Classifiers Under Attack
$β$-变分分类器受到攻击
作者: Marco Maggipinto, Gian Antonio Susto
链接:https://arxiv.org/abs/2008.09010
【9】 Facial movement synergies and Action Unit detection from distal wearable Electromyography and Computer Vision
基于远端可穿戴肌电图和计算机视觉的面部运动协同效应和动作单元检测
作者: Monica Perusquia-Hernandez, Kenji Suzuki
链接:https://arxiv.org/abs/2008.08791
[分割/语义相关]:
【1】 Generative View Synthesis: From Single-view Semantics to Novel-view Images
生成式视图合成:从单视图语义到新视图图像
作者: Tewodros Habtegebrial, Didier Stricker
链接:https://arxiv.org/abs/2008.09106
【2】 ISSAFE: Improving Semantic Segmentation in Accidents by Fusing Event-based Data
ISSAFE:通过融合基于事件的数据改进事故语义分割
作者: Jiaming Zhang, Rainer Stiefelhagen
链接:https://arxiv.org/abs/2008.08974
【3】 Cross-Modality Multi-Atlas Segmentation Using Deep Neural Networks
基于深度神经网络的跨模态多地图集分割
作者: Wangbin Ding, Liqin Huang
链接:https://arxiv.org/abs/2008.08946
【4】 Image Segmentation of Zona-Ablated Human Blastocysts
去透明带人囊胚的图像分割
作者: Md Yousuf Harun, Aaron T. Ohta
链接:https://arxiv.org/abs/2008.08673
【5】 Inner Cell Mass and Trophectoderm Segmentation in Human Blastocyst Images using Deep Neural Network
基于深度神经网络的人囊胚图像内细胞团和滋养层的分割
作者: Md Yousuf Harun, Aaron T. Ohta
链接:https://arxiv.org/abs/2008.08676
[人脸相关]:
【1】 Unsupervised Learning Facial Parameter Regressor for Action Unit Intensity Estimation via Differentiable Renderer
基于微分渲染器的动作单元强度估计的无监督学习脸部参数回归算法
作者: Xinhui Song, Yi Yuan
链接:https://arxiv.org/abs/2008.08862
【2】 RFNet: Riemannian Fusion Network for EEG-based Brain-Computer Interfaces
RFNet:基于脑电的脑机接口黎曼融合网络
作者: Guangyi Zhang, Ali Etemad
链接:https://arxiv.org/abs/2008.08633
[GAN/对抗式/生成式相关]:
【1】 Generating Adjacency Matrix for Video-Query based Video Moment Retrieval
基于视频查询的视频时刻检索邻接矩阵生成
作者: Yuan Zhou, Shuwei Huo
备注:arXiv admin note: substantial text overlap with arXiv:2007.09877
链接:https://arxiv.org/abs/2008.08977
【2】 Direct Adversarial Training for GANs
甘斯的直接对抗性训练
作者: Ziqiang Li
链接:https://arxiv.org/abs/2008.09041
【3】 Regularization And Normalization For Generative Adversarial Networks: A Review
生成性对抗性网络的正则化与正规化研究综述
作者: Ziqiang Li, Bin Li
链接:https://arxiv.org/abs/2008.08930
【4】 iPhantom: a framework for automated creation of individualized computational phantoms and its application to CT organ dosimetry
iPhantom:个性化计算模体自动生成框架及其在CT器官剂量学中的应用
作者: Wanyi Fu, Ehsan Samei
链接:https://arxiv.org/abs/2008.08730
[行为/时空/光流/姿态/运动]:
【1】 Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose
Pose2Mesh:三维人体姿态的图卷积网络及二维人体姿态的网格恢复
作者: Hongsuk Choi, Kyoung Mu Lee
备注:Published at ECCV 2020
链接:https://arxiv.org/abs/2008.09047
【2】 Accuracy and Performance Comparison of Video Action Recognition Approaches
视频动作识别方法的准确率和性能比较
作者: Matthew Hutchinson, Vijay Gadepally
备注:Accepted for publication at IEEE HPEC 2020
链接:https://arxiv.org/abs/2008.09037
【3】 Object Properties Inferring from and Transfer for Human Interaction Motions
人体交互运动的客体性质推断与传递
作者: Qian Zheng, Hui Huang
链接:https://arxiv.org/abs/2008.08999
【4】 PhysCap: Physically Plausible Monocular 3D Motion Capture in Real Time
PhysCap:物理上可信的实时单目3D运动捕获
作者: Soshi Shimada, Christian Theobalt
链接:https://arxiv.org/abs/2008.08880
【5】 Simultaneously-Collected Multimodal Lying Pose Dataset: Towards In-Bed Human Pose Monitoring under Adverse Vision Conditions
同时采集的多模态卧姿数据集:面向视觉不良条件下的床上人体姿势监测
作者: Shuangjun Liu, Sarah Ostadabbas
链接:https://arxiv.org/abs/2008.08735
[半/弱/无监督相关]:
【1】 Weakly-supervised 3D Shape Completion in the Wild
野外弱监督3D形状补全
作者: Jiayuan Gu, Raquel Urtasun
备注:Accepted by ECCV 2020
链接:https://arxiv.org/abs/2008.09110
【2】 Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation
Meta-SIM2:用于合成数据生成的场景结构无监督学习
作者: Jeevan Devaranjan, Sanja Fidler
备注:ECCV 2020
链接:https://arxiv.org/abs/2008.09092
【3】 Self-Supervised Ultrasound to MRI Fetal Brain Image Synthesis
自监督超声在磁共振胎儿脑图像合成中的应用
作者: Jianbo Jiao, J. Alison Noble
备注:IEEE Transactions on Medical Imaging 2020
链接:https://arxiv.org/abs/2008.08698
[裁剪/量化/加速相关]:
【1】 Utilizing Explainable AI for Quantization and Pruning of Deep Neural Networks
利用可解释人工智能对深度神经网络进行量化和修剪
作者: Muhammad Sabih, Juergen Teich
链接:https://arxiv.org/abs/2008.09072
[数据集dataset]:
【1】 DronePose: Photorealistic UAV-Assistant Dataset Synthesis for 3D Pose Estimation via a Smooth Silhouette Loss
DronePose:基于平滑轮廓损失的三维姿态估计的真实感无人机辅助数据集合成
作者: Georgios Albanis, Petrod Daras
备注:Accepted in ECCVW 2020
链接:https://arxiv.org/abs/2008.08823
[超分辨率]:
【1】 Single Image Super-Resolution via a Holistic Attention Network
基于整体注意力网络的单幅图像超分辨率
作者: Ben Niu, Haifeng Shen
链接:https://arxiv.org/abs/2008.08767
[3D/3D重建等相关]:
【1】 Hidden Footprints: Learning Contextual Walkability from 3D Human Trails
隐藏的足迹:从3D人类足迹中学习上下文步行能力
作者: Jin Sun, Noah Snavely
备注:European Conference on Computer Vision (ECCV) 2020
链接:https://arxiv.org/abs/2008.08701
[其他视频相关]:
【1】 Location-aware Graph Convolutional Networks for Video Question Answering
位置感知图卷积网络在视频问答中的应用
作者: Deng Huang, Chuang Gan
链接:https://arxiv.org/abs/2008.09105
【2】 A Plug-and-play Scheme to Adapt Image Saliency Deep Model for Video Data
一种适应视频数据图像显著性深度模型的即插即用方案
作者: Yunxiao Li, Hong Qin
链接:https://arxiv.org/abs/2008.09103
【3】 Localizing Anomalies from Weakly-Labeled Videos
从弱标签视频中定位异常
作者: Hui Lv, Jian Yang
链接:https://arxiv.org/abs/2008.08944
【4】 Text-based Localization of Moments in a Video Corpus
视频语料库中基于文本的矩定位
作者: Sudipta Paul, Amit K. Roy-Chowdhury
链接:https://arxiv.org/abs/2008.08716
[其他]:
【1】 A review of deep learning in medical imaging: Image traits, technology trends, case studies with progress highlights, and future promises
医学影像学中深度学习的回顾:影像特征、技术趋势、具有进展亮点的案例研究和未来前景
作者: S. Kevin Zhou, Ronald M. Summers
备注:19 pages, 7 figures
链接:https://arxiv.org/abs/2008.09104
【2】 DeepGMR: Learning Latent Gaussian Mixture Models for Registration
DeepGMR:用于配准的学习潜在高斯混合模型
作者: Wentao Yuan, Jan Kautz
备注:ECCV 2020 spotlight
链接:https://arxiv.org/abs/2008.09088
【3】 Monocular Expressive Body Regression through Body-Driven Attention
身体驱动注意的单眼表达身体回归
作者: Vasileios Choutas, Michael J. Black
备注:Accepted in ECCV'20. Project page: this http URL
链接:https://arxiv.org/abs/2008.09062
【4】 Improving Text to Image Generation using Mode-seeking Function
使用模式搜索功能改进文本到图像的生成
作者: Naitik Bhise, Tien D. Bui
备注:arXiv admin note: text overlap with arXiv:1904.01310, arXiv:1903.05628 by other authors
链接:https://arxiv.org/abs/2008.08976
【5】 Investigating the Effect of Intraclass Variability in Temporal Ensembling
探讨类内变异在时间整合中的作用
作者: Siddharth Vohra, Manikandan Ravikiran
链接:https://arxiv.org/abs/2008.08956
【6】 Document Visual Question Answering Challenge 2020
记录2020年视觉答疑挑战赛
作者: Minesh Mathew, C.V. Jawahar
备注:to be published as a short paper in DAS 2020
链接:https://arxiv.org/abs/2008.08899
【7】 Yet Another Intermediate-Level Attack
又一次中级攻击
作者: Qizhang Li, Hao Chen
备注:Accepted by ECCV 2020
链接:https://arxiv.org/abs/2008.08847
【8】 On Qualitative Shape Inferences: a journey from geometry to topology
论定性形状推理:从几何到拓扑学的旅程
作者: Steven W Zucker
链接:https://arxiv.org/abs/2008.08622
【9】 Does MAML really want feature reuse only?
MAML真的只想要特性重用吗?
作者: Jaehoon Oh, Se-Young Yun
链接:https://arxiv.org/abs/2008.08882
【10】 Deep learning-based transformation of the H&E stain into special stains improves kidney disease diagnosis
基于深度学习的H&E染色转化为特殊染色提高肾脏疾病诊断水平
作者: Kevin de Haan, Aydogan Ozcan
链接:https://arxiv.org/abs/2008.08871
【11】 Uncertainty Estimation in Medical Image Denoising with Bayesian Deep Image Prior
贝叶斯深度图像先验在医学图像去噪中的不确定性分析
作者: Max-Heinrich Laves, Tobias Ortmaier
备注:Accepted at UNSURE workshop (MICCAI 2020)
链接:https://arxiv.org/abs/2008.08837
机器翻译,仅供参考