Abstract | ||
---|---|---|
We develop a general framework to automatically match electronic slides to the videos of the corresponding presentations. The synchronized slides support indexing and browsing of educational and corporate digital video libraries. Our approach extends previous work that matches slides based on visual features alone, and integrates multiple cues to further improve performance in more difficult cases. We model slide change in a presentation with a dynamic hidden Markov model (HMM) that captures the temporal notion of slide change and whose transition probabilities are adapted locally by using the camera events in the inference process. Our results show that combining multiple cues in a state model can greatly improve the performance in ambiguous cases. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1109/ICASSP.2007.366076 | ICASSP (1) |
Keywords | Field | DocType |
dynamic hidden markov model,video signal processing,presentation videos,image matching,inference process,hmm,digital video libraries,cameras,electronic slides,visual features,image sequences,slide change,algorithm,temporal modeling,hidden markov models,indexing,transition probability,hidden markov model,switches,computer science,layout | Computer vision,Digital video,Pattern recognition,Inference,Image matching,Computer science,Search engine indexing,State model,Artificial intelligence,Temporal modeling,Hidden Markov model | Conference |
Volume | ISSN | ISBN |
1 | 1520-6149 | 1-4244-0727-3 |
Citations | PageRank | References |
10 | 0.76 | 5 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Quanfu Fan | 1 | 504 | 32.69 |
Arnon Amir | 2 | 751 | 69.90 |
K. Barnard | 3 | 2564 | 269.41 |
Ranjini Swaminathan | 4 | 35 | 4.95 |
Alon Efrat | 5 | 1312 | 93.92 |