CV Code | 计算机视觉开源周报 20190602期

目标检测 | Grid R-CNN 升级版，更快也更好！出自商汤

Grid R-CNN Plus: Faster and Better

Xin Lu, Buyu Li, Yuxin Yue, Quanquan Li, Junjie Yan

https://arxiv.org/abs/1906.05688v1

https://github.com/STVIR/Grid-R-CNN

相关解读：

UC伯克利黑科技：用语音数据预测说话人手势

CVPR 2019

视频识别 | 融合局部与全局信心的时空表示学习

Learning Spatio-Temporal Representation with Local and Global Diffusion

Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Xinmei Tian, Tao Mei

https://arxiv.org/abs/1906.05571v1

https://github.com/ZhaofanQiu/local-and-global-diffusion-networks

网络训练正则化 | 数据驱动的正则化方法

CoopSubNet: Cooperating Subnetwork for Data-Driven Regularization of Deep Networks under Limited Training Budgets

Riddhish Bhalodia, Shireen Elhabian, Ladislav Kavan, Ross Whitaker

https://arxiv.org/abs/1906.05441v1

https://github.com/riddhishb/CoopSubNet

多视图学习 | 目标分类 | 对比多视图编码

Contrastive Multiview Coding

Yonglong Tian, Dilip Krishnan, Phillip Isola

https://arxiv.org/abs/1906.05849v1

http://github.com/HobbitLong/CMC/

CVPR Workshop on Visual Odometry & Computer Vision Applications Based on Location Clues (VOCVALC), 2019

通过结构和语义信息的非监督深度和自运动学习

Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semantics

Vincent Casser, Soeren Pirk, Reza Mahjourian, Anelia Angelova

https://arxiv.org/abs/1906.05717v1

https://sites.google.com/corp/view/struct2depth

iProStruct2D: Identifying protein structural classes by deep learning via 2D representations

通过2D表示深度学习识别蛋白质结构类别

Loris Nanni, Alessandra Lumini, Federica Pasquali, Sheryl Brahnam

https://arxiv.org/abs/1906.04407v1

https://github.com/LorisNanni

快速精确的多尺度端到端去雾网络

FAMED-Net: A Fast and Accurate Multi-scale End-to-end Dehazing Network

Jing Zhang, Dacheng Tao

https://arxiv.org/abs/1906.04334v1

（代码将开源，还未公布地址）

对抗学习 | 子空间攻击，清华、Intel

Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks

Ziang Yan, Yiwen Guo, Changshui Zhang

https://arxiv.org/abs/1906.04392v1

利用全局上下文信息进行人体姿态估计，Intel

Global Context for Convolutional Pose Machines

Daniil Osokin

https://arxiv.org/abs/1906.04104v1

https://github.com/opencv/openvino_training_extensions/tree/develop/pytorch_toolkit/human_pose_estimation

ICML 2019

自监督学习

Self-Supervised Exploration via Disagreement

Deepak Pathak, Dhiraj Gandhi, Abhinav Gupta

https://arxiv.org/abs/1906.04161v1

https://pathak22.github.io/exploration-by-disagreement/

目标检测模型蒸馏

Distilling Object Detectors with Fine-grained Feature Imitation

Tao Wang, Li Yuan, Xiaopeng Zhang, Jiashi Feng

https://arxiv.org/abs/1906.03609v1

https://github.com/twangnh/Distilling-Object-Detectors

视频中镜头过度的快速检测

TransNet: A deep network for fast detection of common shot transitions

Tomáš Souček, Jaroslav Moravec, Jakub Lokoč

https://arxiv.org/abs/1906.03363v1

https://github.com/soCzech/TransNet

维度卷积用于高效网络设计

DiCENet: Dimension-wise Convolutions for Efficient Networks

Sachin Mehta, Hannaneh Hajishirzi, Mohammad Rastegari

https://arxiv.org/abs/1906.03516v1

https://github.com/sacmehta/EdgeNets

文本视频信息嵌入

HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips

Antoine Miech, Dimitri Zhukov, Jean-Baptiste Alayrac, Makarand Tapaswi, Ivan Laptev, Josef Sivic

https://arxiv.org/abs/1906.03327v1

http://www.di.ens.fr/willow/research/howto100m/

基于组合层的GAN模型

How to make a pizza: Learning a compositional layer-based GAN model

Dim P. Papadopoulos, Youssef Tamaazousti, Ferda Ofli, Ingmar Weber, Antonio Torralba

https://arxiv.org/abs/1906.02839v1

http://pizzagan.csail.mit.edu/

医学图像分割 | 多尺度引导注意力模型

Multi-scale guided attention for medical image segmentation

Ashish Sinha, Jose Dolz

https://arxiv.org/abs/1906.02849v1

https://github.com/sinAshish/Multi-Scale-Attention

A deep learning approach for automated detection of geographic atrophy from color fundus photographs 医学图像处理识别 | 眼底病变检测

Tiarnan D. Keenan, Shazia Dharssi, Yifan Peng, Qingyu Chen, Elvira Agrón, Wai T. Wong, Zhiyong Lu, Emily Y. Chew

https://arxiv.org/abs/1906.03153v1

https://github.com/ncbi-nlp/DeepSeeNet

IEEE ITSC 2019

变道视频中风险动作识别

Risky Action Recognition in Lane Change Video Clips using Deep Spatiotemporal Networks with Segmentation Mask Transfer

Ekim Yurtsever, Yongkang Liu, Jacob Lambert, Chiyomi Miyajima, Eijiro Takeuchi, Kazuya Takeda, John H. L. Hansen

https://arxiv.org/abs/1906.02859v1

https://github.com/Ekim-Yurtsever/DeepTL-Lane-Change-Classification

图像聚类自动编码器

An Image Clustering Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids and MMD Distance

Qiuyu Zhu, Zhengyong Wang

https://arxiv.org/abs/1906.03905v1

https://github.com/yuanbao888/Clustering

转载请注明：《CV Code | 计算机视觉开源周报 20190602期》