计算机视觉每日论文速递[06.20]

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31篇

[检测分类相关]:

【1】 Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss
基于交叉点超过联合损失的单目三维目标检测和盒拟合训练
作者: Eskil Jörgensen, Fredrik Kahl
链接:https://arxiv.org/abs/1906.08070

【2】 Cloud-based Image Classification Service Is Not Robust To Simple Transformations: A Forgotten Battlefield
基于云的图像分类服务对简单的转换不是很健壮:一个被遗忘的战场
作者: Dou Goodman, Tao Wei
链接:https://arxiv.org/abs/1906.07997

【3】 A simple and effective postprocessing method for image classification
一种简单有效的图像分类后处理方法
作者: Yan Liu, jipeng qiang
链接:https://arxiv.org/abs/1906.07934

【4】 SAR Image Change Detection via Spatial Metric Learning with an Improved Mahalanobis Distance
基于改进马氏距离空间度量学习的SAR图像变化检测
作者: Rongfang Wang, Mi Wang
链接:https://arxiv.org/abs/1906.07930

【5】 Imbalanced Learning-based Automatic SAR Images Change Detection by Morphologically Supervised PCA-Net
基于不平衡学习的基于形态监督PCA网的SAR图像变化自动检测
作者: Rongfang Wang, Mi Wang
链接:https://arxiv.org/abs/1906.07923

【6】 ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection
VIP:用于加速CNN图像分类和目标检测的虚拟池
作者: Zhuo Chen, Diana Marculescu
链接:https://arxiv.org/abs/1906.07912

【7】 Quantifying and Leveraging Classification Uncertainty for Chest Radiograph Assessment
量化和利用分类不确定度用于胸片评估
作者: Florin C. Ghesu, Dorin Comaniciu
备注:Accepted for presentation at MICCAI 2019
链接:https://arxiv.org/abs/1906.07775

[分割/语义相关]:

【1】 Key Instance Selection for Unsupervised Video Object Segmentation
无监督视频对象分割的关键实例选择
作者: Donghyeon Cho, Jiwon Kim
备注:Ranked 3rd on the leaderboard of 'Unsupervised DAVIS Challenge' (CVPR 2019)
链接:https://arxiv.org/abs/1906.07851

【2】 SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing
语义添加:通过属性条件图像编辑生成对抗性示例
作者: Haonan Qiu, Bo Li
链接:https://arxiv.org/abs/1906.07927

[行为/时空/光流/姿态/运动]:

【1】 PoseConvGRU: A Monocular Approach for Visual Ego-motion Estimation by Learning
PoseConvGRU:一种基于学习的视觉自我运动估计的单目方法
作者: Guangyao Zhai, Yong Liu
链接:https://arxiv.org/abs/1906.08095

【2】 Automatic Scale Estimation of Structure from Motion based 3D Models using Laser Scalers
基于运动的三维模型激光标度自动尺度估计
作者: Klemen Istenic, Rafael Garcia
链接:https://arxiv.org/abs/1906.08019

【3】 An Action Recognition network for specific target based on rMC and RPN
基于RMC和RPN的特定目标动作识别网络
作者: Mingjie Li, Yuhao Dong
链接:https://arxiv.org/abs/1906.07944

【4】 Analytical Derivatives for Differentiable Renderer: 3D Pose Estimation by Silhouette Consistency
可微渲染器的解析导数:基于轮廓一致性的3D姿势估计
作者: Zaiqiang Wu, Wei Jiang
备注:19 pages, 8 figures
链接:https://arxiv.org/abs/1906.07870

[半/弱/无监督相关]:

【1】 A generative approach to unsupervised deep local learning
无监督深度局部学习的生成性方法
作者: Changlu Chen, Kun Zhan
链接:https://arxiv.org/abs/1906.07947

【2】 Unsupervised Learning of Object Structure and Dynamics from Videos
视频中物体结构和动力学的无监督学习
作者: Matthias Minderer, Honglak Lee
链接:https://arxiv.org/abs/1906.07889

[跟踪相关]:

【1】 Event-based Star Tracking via Multiresolution Progressive Hough Transforms
基于事件的多分辨率渐进Hough变换的星跟踪
作者: Tat-Jun Chin, Samya Bagchi
链接:https://arxiv.org/abs/1906.07866

[裁剪/量化/加速相关]:

【1】 Model-based Deep MR Imaging: the roadmap of generalizing compressed sensing model using deep learning
基于模型的深度MR成像:利用深度学习推广压缩感知模型的路线图
作者: Jing Cheng, Dong Liang
链接:https://arxiv.org/abs/1906.08143

[数据集dataset]:

【1】 SEN12MS -- A Curated Dataset of Georeferenced Multi-Spectral Sentinel-1/2 Imagery for Deep Learning and Data Fusion
SEN12MS-用于深度学习和数据融合的地理参考多光谱哨兵-1/2图像的策划数据集
作者: Michael Schmitt, Xiao Xiang Zhu
备注:accepted for publication in the ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences (online from September 2019)
链接:https://arxiv.org/abs/1906.07789

[其他视频相关]:

【1】 Multimodal Abstractive Summarization for How2 Videos
HOW2视频的多模态抽象总结
作者: Shruti Palaskar, Florian Metze
备注:To appear in ACL 2019
链接:https://arxiv.org/abs/1906.07901

[其他]:

【1】 Neural Point-Based Graphics
基于神经点的图形
作者: Kara-Ali Aliev, Victor Lempitsky
链接:https://arxiv.org/abs/1906.08240

【2】 Artistic Enhancement and Style Transfer of Image Edges using Directional Pseudo-coloring
基于方向伪着色的图像边缘艺术增强与风格转换
作者: Shouvik Mani
链接:https://arxiv.org/abs/1906.07981

【3】 Extended probabilistic Rand index and the adjustable moving window-based pixel-pair sampling method
扩展概率Rand指数和基于可调移动窗口的像素对采样方法
作者: Hisashi Shimodaira
链接:https://arxiv.org/abs/1906.07893

【4】 Learning to Reconstruct and Understand Indoor Scenes from Sparse Views
学习从稀疏视图重建和理解室内场景
作者: Jingyu Yang, Yebin Liu
链接:https://arxiv.org/abs/1906.07892

【5】 Image Super Resolution via Bilinear Pooling: Application to Confocal Endomicroscopy
基于双线性池的图像超分辨率:在共聚焦显微镜中的应用
作者: Saeed Izadi, Ghassan Hamarneh
链接:https://arxiv.org/abs/1906.07802

【6】 Crop Lodging Prediction from UAV-Acquired Images of Wheat and Canola using a DCNN Augmented with Handcrafted Texture Features
基于手工纹理特征增强的DCNN从无人机获取的小麦和油菜图像中预测作物倒伏
作者: Sara Mardanisamani, Mark Eramian
链接:https://arxiv.org/abs/1906.07771

【7】 Tumor Saliency Estimation for Breast Ultrasound Images via Breast Anatomy Modeling
基于乳腺解剖建模的乳腺超声图像肿瘤显著性估计
作者: Fei Xu, Ying Wang
链接:https://arxiv.org/abs/1906.07760

【8】 PyRobot: An Open-source Robotics Framework for Research and Benchmarking
PyRobot:一种用于研究和标杆的开源机器人框架
作者: Adithyavairavan Murali, Abhinav Gupta
链接:https://arxiv.org/abs/1906.08236

【9】 Automated Definition of Skeletal Disease Burden in Metastatic Prostate Carcinoma: a 3D analysis of SPECT/CT images
转移性前列腺癌骨骼疾病负担的自动定义:SPECT/CT图像的三维分析
作者: Francesco Fiz, Christian la Fougère
链接:https://arxiv.org/abs/1906.08200

【10】 XNAS: Neural Architecture Search with Expert Advice
XNAs:带专家建议的神经结构搜索
作者: Niv Nayman, Lihi Zelnik-Manor
链接:https://arxiv.org/abs/1906.08031

【11】 Automatic estimation of heading date of paddy rice using deep learning
基于深度学习的水稻抽穗期自动估计
作者: Sai Vikas Desai, Wei Guo
链接:https://arxiv.org/abs/1906.07917

【12】 Neural Volumes: Learning Dynamic Renderable Volumes from Images
神经体积:从图像中学习动态可渲染体积
作者: Stephen Lombardi, Yaser Sheikh
备注:Accepted to SIGGRAPH 2019
链接:https://arxiv.org/abs/1906.07751

翻译:腾讯翻译君

你可能感兴趣的:(计算机视觉每日论文速递[06.20])