In this work, we propose and show that, by taking into account global configuration of local features, we can greatly improve recognition performance.

... local features, we can incorporate different spatial and tem- poral feature constraints into the learning tasks of human action classification and localization.

In particular, we tackle the problem of action localization in video using structured learning with two alternatives: one is Dynamic Conditional Random Field ...

This work proposes an approach based on mid-level features representation for human action description using a graph-based video representation using the ...

This paper presents a unified framework for human action classification and localization in video using structured learning of local space-time features.

Jan 1, 2012 · Human action recognition is a promising yet non-trivial computer vision field with many potential applications.

Structured learning of local features for human action classification and localization. Tuan Hue Thi, Li Cheng, Jian Zhang, Li Wang, Shinichi Satoh.

We model both long-term person behaviour and human-human, human-object interactions structurally in a unified framework. The actors across the video are ...

This paper presents a unified framework for human ac-tion classification and localization in video using structured learning of local space-time features.

This paper presents a unified framework for human action classification and localization in video using structured learning of local space-time features.