← Search

Zhilan Hu

2 accepted papers

2022

Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos

CVPR 2022poster

Action recognition models have shown a promising capability to classify human actions in short video clips. In a real scenario, multiple correlated human actions commonly occur in particular orders, forming semantically meaningful human activities. Conventional action recognition approaches focus on…

Cited by 88PDF ↗code ↗Scholar ↗
2019

Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration

CVPR 2019oral

Previous works utilized "smaller-norm-less-important" criterion to prune filters with smaller norm values in a convolutional neural network. In this paper, we analyze this norm-based criterion and point out that its effectiveness depends on two requirements that are not always met: (1) the norm de…

Cited by 1523PDF ↗code ↗Scholar ↗