RECENT ADVANCES IN IMAGE AND VIDEO RETRIEVAL Semantic classification of movie scenes using finite state machines

@inproceedings{Zhai2000RECENTAI,
  title={RECENT ADVANCES IN IMAGE AND VIDEO RETRIEVAL Semantic classification of movie scenes using finite state machines},
  author={Yun Zhai and Zeeshan Rasheed and Mubarak Shah},
  year={2000}
}
The problem of classifying scenes from feature films into semantic categories is addressed and a robust framework for this problem is proposed. It is proposed that the finite state machines (FSM) are suitable for detecting and classifying scenes and their usage is demonstrated for three types of movie scenes: conversation, suspense and action. This framework utilises the structural information of the scenes together with the low-level and mid-level features. Low level features of the video… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-9 of 9 extracted citations

Using attention for video segmentation

Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. • 2004

Similar Papers

Loading similar papers…