Title | ||
---|---|---|
Technicolor challenge: an event classification framework by probabilistic context modeling of multimodal features |
Abstract | ||
---|---|---|
Semantic high-level event recognition of videos is one of most interesting issues for multimedia searching and indexing. Since high-level events are usually domain-specific, a generic framework which can adapt itself to new domains without or with a few modifications is needed. To this end, this paper presents a generic framework for video event classification using temporal context of interval-based multimodal features. In the framework, a co-occurrence symbol transformation method is proposed to explore full temporal relations among multiple modalities in probabilistic HMM event classification. The results of our experiments on baseball video event classification demonstrate the superiority of the proposed approach. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1145/2393347.2396481 | ACM Multimedia 2001 |
Keywords | Field | DocType |
temporal context,technicolor challenge,full temporal relation,generic framework,probabilistic context modeling,probabilistic hmm event classification,video event classification,co-occurrence symbol transformation method,baseball video event classification,multimodal feature,semantic high-level event recognition,event classification framework,high-level event,hmm,semantics | Technicolor,Computer science,Symbol,Search engine indexing,Context model,Artificial intelligence,Probabilistic logic,Hidden Markov model,Event recognition,Machine learning,Semantics | Conference |
Citations | PageRank | References |
0 | 0.34 | 3 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hsuan-Sheng Chen | 1 | 115 | 7.36 |
Wen-Jiin Tsai | 2 | 174 | 19.57 |