2019 图像褶皱处理 论文_计算机视觉/图像处理每日论文速递[11.02]

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】 What's in a Loss Function for Image Classification?
图像分类的损失函数是什么?
作者: Simon Kornblith, Mohammad Norouzi
链接:https://arxiv.org/abs/2010.16402

【2】 Small Noisy and Perspective Face Detection using Deformable Symmetric Gabor Wavelet Network
基于可变形对称Gabor小波网络的小噪声透视人脸检测
作者: Sherzod Salokhiddinov, Seungkyu Lee
链接:https://arxiv.org/abs/2010.16164

【3】 Can the state of relevant neurons in a deep neural networks serve as indicators for detecting adversarial attacks?
深层神经网络中相关神经元的状态能否作为检测对抗性攻击的指标?
作者: Roger Granda, Jose Oramas
链接:https://arxiv.org/abs/2010.15974

【4】 Detecting small polyps using a Dynamic SSD-GAN
利用动态SSD-GAN检测小息肉
作者: Daniel C. Ohrenstein, Peter Mountney
备注:Machine Learning for Health (ML4H) at NeurIPS 2020 - Extended Abstract
链接:https://arxiv.org/abs/2010.15937

【5】 Perception Matters: Exploring Imperceptible and Transferable Anti-forensics for GAN-generated Fake Face Imagery Detection
感知问题:为GaN生成的假人脸图像检测探索不可感知和可转移的反取证
作者: Yongwei Wang, Z. Jane Wang
链接:https://arxiv.org/abs/2010.15886

【6】 Development and Evaluation of a Deep Neural Network for Histologic Classification of Renal Cell Carcinoma on Biopsy and Surgical Resection Slides
肾细胞癌活检和手术切片组织学分类的深度神经网络模型的建立与评价
作者: Mengdan Zhu, Saeed Hassanpour
链接:https://arxiv.org/abs/2010.16380

【7】 Classifying Malware Images with Convolutional Neural Network Models
基于卷积神经网络模型的恶意软件图像分类
作者: Ahmed Bensaoud, Jugal Kalita
链接:https://arxiv.org/abs/2010.16108

【8】 FLANNEL: Focal Loss Based Neural Network Ensemble for COVID-19 Detection
基于焦点损失的神经网络集成在冠状病毒检测中的应用
作者: Zhi Qiao, Jimeng Sun
链接:https://arxiv.org/abs/2010.16039

[分割/语义相关]:

【1】 Emotion Understanding in Videos Through Body, Context, and Visual-Semantic Embedding Loss
基于身体、语境和视觉语义嵌入缺失的视频情感理解
作者: Panagiotis Paraskevas Filntisis, Petros Maragos
备注:Winner of the First International Workshop on Bodily Expressed Emotion Understanding Challenge (ECCVW-2020)
链接:https://arxiv.org/abs/2010.16396

【2】 Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation
自动全景图:用于全景图分割的协作式多分量结构搜索
作者: Yangxin Wu, Liang Lin
备注:NeurIPS2020
链接:https://arxiv.org/abs/2010.16119

【3】 Volumetric Medical Image Segmentation: A 3D Deep Coarse-to-fine Framework and Its Adversarial Examples
体医学图像分割:一种由粗到精的三维深度框架及其对抗性实例
作者: Yingwei Li, Alan L. Yuille
备注:arXiv admin note: substantial text overlap with arXiv:1712.00201
链接:https://arxiv.org/abs/2010.16074

【4】 Ink Marker Segmentation in Histopathology Images Using Deep Learning
基于深度学习的组织病理学图像墨迹标记分割
作者: Danial Maleki, H.R. Tizhoosh
备注:Accepted for publication in the 15th International Symposium on Visual Computing (ISVC 2020)
链接:https://arxiv.org/abs/2010.15865

[GAN/对抗式/生成式相关]:

【1】 MichiGAN: Multi-Input-Conditioned Hair Image Generation for Portrait Editing
密歇根州:用于肖像编辑的多输入条件头发图像生成
作者: Zhentao Tan, Nenghai Yu
备注:Siggraph 2020, code is available at this https URL
链接:https://arxiv.org/abs/2010.16417

【2】 An Unsupervised Approach towards Varying Human Skin Tone Using Generative Adversarial Networks
基于产生式对抗网络的人类肤色变化的无监督方法
作者: Debapriya Roy, Bhabatosh Chanda
备注:Accepted in International Conference on Pattern Recognition 2020
链接:https://arxiv.org/abs/2010.16092

[行为/时空/光流/姿态/运动]:

【1】 PyraPose: Feature Pyramids for Fast and Accurate Object Pose Estimation under Domain Shift
金字塔:域移条件下快速准确估计目标位姿的特征金字塔
作者: Stefan Thalhammer, Markus Vincze
链接:https://arxiv.org/abs/2010.16117

[半/弱/无监督相关]:

【1】 Unsupervised Monocular Depth Learning in Dynamic Scenes
动态场景中的无监督单目深度学习
作者: Hanhan Li, Anelia Angelova
备注:Accepted at 4th Conference on Robot Learning (CoRL 2020)
链接:https://arxiv.org/abs/2010.16404

【2】 AutoAtlas: Neural Network for 3D Unsupervised Partitioning and Representation Learning
AutoAtlas:用于三维无监督划分和表示学习的神经网络
作者: K. Aditya Mohan, Alan D. Kaplan
链接:https://arxiv.org/abs/2010.15987

[跟踪相关]:

【1】 SMOT: Single-Shot Multi Object Tracking
SMOT:单镜头多目标跟踪
作者: Wei Li, Wei Xia
链接:https://arxiv.org/abs/2010.16031

[迁移学习/domain/主动学习/自适应]:

【1】 PAL : Pretext-based Active Learning
PAL:基于借口的主动学习
作者: Shubhang Bhatnagar, Amit Sethi
链接:https://arxiv.org/abs/2010.15947

【2】 Domain-Specific Lexical Grounding in Noisy Visual-Textual Documents
噪声视觉文本文档中的特定领域词汇基础
作者: Gregory Yauney, David Mimno
链接:https://arxiv.org/abs/2010.16363

[裁剪/量化/加速相关]:

【1】 Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices
融合催化剪枝优化智能边缘设备的深度学习
作者: Guangli Li, Xiaobing Feng
链接:https://arxiv.org/abs/2010.16165

[视频理解VQA/caption等]:

【1】 Loss-rescaling VQA: Revisiting Language Prior Problem from a Class-imbalance View
损失调整VQA:从班级失衡的角度重新审视语言优先问题
作者: Yangyang Guo, Qi Tian
链接:https://arxiv.org/abs/2010.16010

[深度depth相关]:

【1】 CNN based Multistage Gated Average Fusion (MGAF) for Human Action Recognition Using Depth and Inertial Sensors
基于CNN的多级门控平均融合(MGAF)在深度和惯性传感器人体动作识别中的应用
作者: Zeeshan Ahmad, Naimul khan
备注:arXiv admin note: text overlap with arXiv:1910.11482
链接:https://arxiv.org/abs/2010.16073

[3D/3D重建等相关]:

【1】 3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations
基于对应量化神经网络三维场景表示的三维物体识别
作者: Mihir Prabhudesai, Katerina Fragkiadaki
链接:https://arxiv.org/abs/2010.16279

[其他]:

【1】 Automatic Counting and Identification of Train Wagons Based on Computer Vision and Deep Learning
基于计算机视觉和深度学习的列车车厢自动计数与识别
作者: Rayson Laroca, David Menotti
备注:An article about the proposed system has been published in the October 2020 issue of Railway Gazette International, the leading business journal for the worldwide rail industry
链接:https://arxiv.org/abs/2010.16307

【2】 All-Weather Object Recognition Using Radar and Infrared Sensing
基于雷达和红外传感的全天候目标识别
作者: Marcel Sheeny
备注:201 pages, PhD Thesis, Heriot-Watt University, October 2020. Includes results from arXiv:1804.02576, arXiv:1912.03157, this https URL and arXiv:2010.09076
链接:https://arxiv.org/abs/2010.16285

【3】 Exploring Dynamic Context for Multi-path Trajectory Prediction
多路径轨迹预测的动态上下文探索
作者: Hao Cheng, Bodo Rosenhahn
链接:https://arxiv.org/abs/2010.16267

【4】 Experimental design for MRI by greedy policy search
基于贪婪策略搜索的磁共振实验设计
作者: Tim Bakker, Max Welling
备注:Accepted to NeurIPS 2020 (spotlight)
链接:https://arxiv.org/abs/2010.16262

【5】 HOI Analysis: Integrating and Decomposing Human-Object Interaction
HOI分析:人-物交互的整合与分解
作者: Yong-Lu Li, Cewu Lu
备注:Accepted in NeurIPS 2020. Code: this https URL), Project: this https URL
链接:https://arxiv.org/abs/2010.16219

【6】 Statistical Analysis of Signal-Dependent Noise: Application in Blind Localization of Image Splicing Forgery
信号相关噪声统计分析在拼接伪造图像盲定位中的应用
作者: Mian Zou, Xinpeng Zhang
链接:https://arxiv.org/abs/2010.16211

【7】 End-to-end Animal Image Matting
端到端的动物图像遮片
作者: Jizhizi Li, Dacheng Tao
链接:https://arxiv.org/abs/2010.16188

【8】 Correspondence Matrices are Underrated
对应矩阵被低估了
作者: Tejas Zodage, Howie Choset
备注:Accepted in the conference, 3DV 2020. 8 pages + 2 supplementary pages + 2 reference papers
链接:https://arxiv.org/abs/2010.16085

【9】 LIFI: Towards Linguistically Informed Frame Interpolation
LIFI:走向语言信息帧内插
作者: Aradhya Neeraj Mathur, Amanda Stent
链接:https://arxiv.org/abs/2010.16078

【10】 A Comprehensive Comparison of End-to-End Approaches for Handwritten Digit String Recognition
端到端手写数字串识别方法的综合比较
作者: Andre G. Hochuli, Luiz S. Oliveira
链接:https://arxiv.org/abs/2010.15904

【11】 DeepWay: a Deep Learning Estimator for Unmanned Ground Vehicle Global Path Planning
DeepWay:一种无人地面车辆全局路径规划的深度学习估值器
作者: Vittorio Mazzia, Marcello Chiaberge
链接:https://arxiv.org/abs/2010.16322

【12】 Learning Vision-based Reactive Policies for Obstacle Avoidance
基于学习视觉的反应性避障策略
作者: Elie Aljalbout, Sami Haddadin
备注:Accepted for publication at CoRL 2020
链接:https://arxiv.org/abs/2010.16298

【13】 Automatic Myocardial Infarction Evaluation from Delayed-Enhancement Cardiac MRI using Deep Convolutional Networks
基于深度卷积网络的心脏MRI延迟增强自动心肌梗死评估
作者: Kibrom Berihu Girum, Alain Lalande
链接:https://arxiv.org/abs/2010.16198

【14】 Bayesian Optimization Meets Laplace Approximation for Robotic Introspection
机器人自省的贝叶斯优化与拉普拉斯逼近
作者: Matthias Humt, Rudolph Triebel
备注:Accepted to the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2020 Long-Term Autonomy Workshop
链接:https://arxiv.org/abs/2010.16141

【15】 CT-CAPS: Feature Extraction-based Automated Framework for COVID-19 Disease Identification from Chest CT Scans using Capsule Networks
CT-CAPS:基于特征提取的基于胶囊网络的胸部CT冠状病毒病自动识别框架
作者: Shahin Heidarian, Farnoosh Naderkhani
链接:https://arxiv.org/abs/2010.16043

【16】 COVID-FACT: A Fully-Automated Capsule Network-based Framework for Identification of COVID-19 Cases from Chest CT scans
COVID-FACT:一种基于全自动胶囊网络的胸部CT冠状病毒病例识别框架
作者: Shahin Heidarian, Moezedin Javad Rafiee
链接:https://arxiv.org/abs/2010.16041

【17】 PIINET: A 360-degree Panoramic Image Inpainting Network Using a Cube Map
PIINET:一种基于立方体地图的360度全景图像修复网络
作者: Seo Woo Han, Doug Young Suh
链接:https://arxiv.org/abs/2010.16003

【18】 Human versus Machine Attention in Deep Reinforcement Learning Tasks
深度强化学习任务中人与机器注意的比较
作者: Ruohan Zhang, Peter Stone
链接:https://arxiv.org/abs/2010.15942

【19】 Multi-agent Trajectory Prediction with Fuzzy Query Attention
具有模糊查询关注度的多智能体轨迹预测
作者: Nitin Kamra, Yan Liu
备注:NeurIPS 2020 Camera-ready version. Code: this https URL
链接:https://arxiv.org/abs/2010.15891

机器翻译,仅供参考

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值