activity
20162020
most citedUnderstanding Top-k Sparsification in Distributed Deep Learning

67 citations · 86 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV20202 cited

Effective Action Recognition with Embedded Key Point Shifts

Haozhi Cao, Yuecong Xu, Jianfei Yang +3

Temporal feature extraction is an essential technique in video-based action recognition. Key points have been utilized in skeleton-based action recognition methods but they require…

math.NA20203 cited

A deep learning based nonlinear upscaling method for transport equations

Tak Shing Au Yeung, Eric T. Chung, Simon See

We will develop a nonlinear upscaling method for nonlinear transport equation. The proposed scheme gives a coarse scale equation for the cell average of the solution. In order to c…

cs.CV2020

PNL: Efficient Long-Range Dependencies Extraction with Pyramid Non-Local Module for Action Recognition

Yuecong Xu, Haozhi Cao, Jianfei Yang +3

Long-range spatiotemporal dependencies capturing plays an essential role in improving video features for action recognition. The non-local block inspired by the non-local means is…

cs.CV20202 cited

Exploiting Inter-Frame Regional Correlation for Efficient Action Recognition

Yuecong Xu, Jianfei Yang, Kezhi Mao +2

Temporal feature extraction is an important issue in video-based action recognition. Optical flow is a popular method to extract temporal feature, which produces excellent performa…

cs.LG201967 cited

Understanding Top-k Sparsification in Distributed Deep Learning

Shaohuai Shi, Xiaowen Chu, Ka Chun Cheung +1

Distributed stochastic gradient descent (SGD) algorithms are widely deployed in training large-scale deep learning models, while the communication overhead among workers becomes th…

cs.CV201612 cited

Learning Common and Specific Features for RGB-D Semantic Segmentation with Deconvolutional Networks

Jinghua Wang, Zhenhua Wang, Dacheng Tao +2

In this paper, we tackle the problem of RGB-D semantic segmentation of indoor images. We take advantage of deconvolutional networks which can predict pixel-wise class labels, and d…