Abstract: The problem of recognizing actions in realistic videos is challenging yet absorbing owing to its great potentials in many practical applications.

The problem of recognizing actions in realistic videos is challenging yet absorbing owing to its great potentials in many practical applications.

This paper proposes to model the spatio-temporal context information in a hierarchical way, where three levels of context are exploited in ascending order ...

Building on the multichannel nonlinear SVMs, we validate this proposed hierarchical framework on the realistic action (HOHA) and event (LSCOM) recognition ...

Building on the multichannel nonlinear SVMs, we validate this proposed hierarchical framework on the realistic action (HOHA) and event (LSCOM) recognition ...

The proposed theory explores processes of recognition, quantitative descriptions and representations of that are possible. According to this theory, object ...

Hierarchical spatio-temporal context modeling for action recognition. J. Sun, X. Wu, S. Yan, L. Cheong, T. Chua, and J. Li. CVPR, page 2004-2011. IEEE ...

This convolutional stacking idea enables the algorithm to learn a hierarchical representation of the data suitable for recognition [22]. We evaluate our method ...

Modeling person interactions with their surroundings has proven to be effective for recognizing and localizing human actions in videos.

We develop a structured model that cap- tures a rich set of spatial, temporal and hierarchical rela- tions among the segments, where the action label and multi-.