Abstract | ||
---|---|---|
This paper addresses the challenge of Multimedia Event Detection by proposing a novel method for high-level and low-level features fusion based on collective classification. Generally, the method consists of three steps: training a classifier from low-level features; encoding high-level features into graphs; and diffusing the scores on the established graph to obtain the final prediction. The final prediction is derived from multiple graphs each of which corresponds to a high-level feature. The paper investigates two graph construction methods using logarithmic and exponential loss functions, respectively and two collective classification algorithms, i.e. Gibbs sampling and Markov random walk. The theoretical analysis demonstrates that the proposed method converges and is computationally scalable and the empirical analysis on TRECVID 2011 Multimedia Event Detection dataset validates its outstanding performance compared to state-of-the-art methods, with an added benefit of interpretability. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1145/2393347.2393412 | ACM Multimedia 2001 |
Keywords | Field | DocType |
multimedia event detection,novel method,multimedia event detection dataset,low-level features fusion,final prediction,collective classification,proposed method converges,graph construction method,high-level feature,state-of-the-art method | Data mining,Computer science,Random walk,Artificial intelligence,Classifier (linguistics),Gibbs sampling,Interpretability,Computer vision,Pattern recognition,TRECVID,Markov chain,Multimedia,Scalability,Encoding (memory) | Conference |
Citations | PageRank | References |
38 | 1.13 | 13 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiang Lu | 1 | 755 | 37.16 |
Alexander G. Hauptmann | 2 | 7472 | 558.23 |
Guang Xiang | 3 | 382 | 18.31 |