Learning human actions via information maximization

  title={Learning human actions via information maximization},
  author={Jingen Liu and Mubarak Shah},
  journal={2008 IEEE Conference on Computer Vision and Pattern Recognition},
In this paper, we present a novel approach for automatically learning a compact and yet discriminative appearance-based human action model. A video sequence is represented by a bag of spatiotemporal features called video-words by quantizing the extracted 3D interest points (cuboids) from the videos. Our proposed approach is able to automatically discover the optimal number of video-word clusters by utilizing maximization of mutual information(MMI). Unlike the k-means algorithm, which is… CONTINUE READING
Highly Influential
This paper has highly influenced 60 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 597 citations. REVIEW CITATIONS

8 Figures & Tables



Citations per Year

598 Citations

Semantic Scholar estimates that this publication has 598 citations based on the available data.

See our FAQ for additional information.