Online Macro-segmentation of Television Streams
MMM '09 Proceedings of the 15th International Multimedia Modeling Conference on Advances in Multimedia Modeling
Labeling TV stream segments with conditional random fields
MUSCLE'11 Proceedings of the 2011 international conference on Computational Intelligence for Multimedia Understanding
| Hi-index | 0.00 |
This paper proposes a method for classifying TV stream segments as long programs or inter-programs (IP). As almost all IPs are broadcasted several times in the TV stream, a first segmentation step based on a repeated sequence detection is performed. Resulting segments (the occurrences of repeated sequences and the rest of the stream) have to be classified. The proposed solution for that is based on Inductive Logic Programming. In addition to intrinsic features of each segment (e.g.duration), our technique makes use of the relational and contextual information of the segments in the stream. The effectiveness of our solution has been shown on a real TV stream of 6~days and a comparative study with an SVM-based classification approach has been performed.