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19篇
[检测分类相关]:
【1】 Multi-Instance Multi-Scale CNN for Medical Image Classification
用于医学图像分类的多实例多尺度CNN
作者: Shaohua Li, Rick Siow Mong Goh
备注:Accepted by MICCAI 2019
链接:https://arxiv.org/abs/1907.02413
【2】 FPCNet: Fast Pavement Crack Detection Network Based on Encoder-Decoder Architecture
FPCNet:基于编解码器架构的快速路面裂缝检测网络
作者: Wenjun Liu, Qi Chen
链接:https://arxiv.org/abs/1907.02248
[分割/语义相关]:
【1】 Analyzing the Cross-Sensor Portability of Neural Network Architectures for LiDAR-based Semantic Labeling
基于LiDAR的语义标注神经网络结构的交叉传感器可移植性分析
作者: Florian Piewak, Marius Zöllner
链接:https://arxiv.org/abs/1907.02149
【2】 DeepMRSeg: A convolutional deep neural network for anatomy and abnormality segmentation on MR images
DeepMRSeg:一种用于MR图像解剖和异常分割的卷积深度神经网络
作者: Jimit Doshi, Christos Davatzikos
备注:18 pages, 8 figures, 3 tables
链接:https://arxiv.org/abs/1907.02110
[行为/时空/光流/姿态/运动]:
【1】 Sim2real transfer learning for 3D pose estimation: motion to the rescue
Sim2real迁移学习用于3D姿态估计:运动救援
作者: Carl Doersch, Andrew Zisserman
链接:https://arxiv.org/abs/1907.02499
【2】 Seeing Under the Cover: A Physics Guided Learning Approach for In-Bed Pose Estimation
掩护下看:一种用于床上姿态估计的物理引导学习方法
作者: Shuangjun Liu, Sarah Ostadabbas
链接:https://arxiv.org/abs/1907.02161
[裁剪/量化/加速相关]:
【1】 Non-structured DNN Weight Pruning Considered Harmful
非结构化DNN权重修剪被认为是有害的
作者: Yanzhi Wang, Kaisheng Ma
链接:https://arxiv.org/abs/1907.02124
[视频理解VQA/caption等]:
【1】 Neural Image Captioning
神经图像字幕
作者: Elaina Tan, Lakshay Sharma
链接:https://arxiv.org/abs/1907.02065
[其他视频相关]:
【1】 Video Crowd Counting via Dynamic Temporal Modeling
基于动态时间建模的视频人群计数
作者: Xingjiao Wu, Liang He
链接:https://arxiv.org/abs/1907.02198
【2】 LumièreNet: Lecture Video Synthesis from Audio
LumièRenet:从音频合成讲座视频
作者: Byung-Hak Kim, Varun Ganapathi
链接:https://arxiv.org/abs/1907.02253
[其他]:
【1】 Guided Image Generation with Conditional Invertible Neural Networks
基于条件可逆神经网络的引导图像生成
作者: Lynton Ardizzone, Ullrich Köthe
链接:https://arxiv.org/abs/1907.02392
【2】 Believe It or Not, We Know What You Are Looking at!
信不信由你,我们知道你在看什么!
作者: Dongze Lian, Shenghua Gao
备注:ACCV2018
链接:https://arxiv.org/abs/1907.02364
【3】 Deep Saliency Models : The Quest For The Loss Function
深度显着性模型:对损失函数的探索
作者: Alexandre Bruckert, Olivier Le Meur
链接:https://arxiv.org/abs/1907.02336
【4】 Edge-Aware Deep Image Deblurring
边缘感知的深度图像去模糊
作者: Zhichao Fu, Liang He
链接:https://arxiv.org/abs/1907.02282
【5】 Searching for Apparel Products from Images in the Wild
从野外图像中搜索服装产品
作者: Son Tran, Cj Taylor
链接:https://arxiv.org/abs/1907.02244
【6】 RFBTD: RFB Text Detector
RFBTD:RFB文本检测器
作者: Christen M, AB Saravanan
链接:https://arxiv.org/abs/1907.02228
【7】 Slim-CNN: A Light-Weight CNN for Face Attribute Prediction
SLIM-CNN:一种用于人脸属性预测的轻量级CNN
作者: Ankit Sharma, Hassan Foroosh
链接:https://arxiv.org/abs/1907.02157
【8】 The Indirect Convolution Algorithm
间接卷积算法
作者: Marat Dukhan
备注:Presented on Efficient Deep Learning for Computer Vision workshop at CVPR 2019
链接:https://arxiv.org/abs/1907.02129
【9】 A comprehensive evaluation of full-reference image quality assessment algorithms on KADID-10k
KADID-10k上全参考图像质量评估算法的综合评价
作者: Domonkos Varga
链接:https://arxiv.org/abs/1907.02096
翻译:腾讯翻译君