Early versus late fusion in semantic video analysis

作者: Cees G. M. Snoek , Marcel Worring , Arnold W. M. Smeulders

DOI: 10.1145/1101149.1101236

关键词:

摘要: … In this paper, we compare early fusion and late fusion schemes that aim to learn semantic … cast video using 20 semantic concepts we conclude that a late fusion scheme tends to give …

参考文章(9)
Jean-Luc Gauvain, Lori Lamel, Gilles Adda, The LIMSI Broadcast News transcription system Speech Communication. ,vol. 37, pp. 89- 108 ,(2002) , 10.1016/S0167-6393(01)00061-9
G. Iyengar, H. J. Nock, Discriminative model fusion for semantic concept detection and annotation in video Proceedings of the eleventh ACM international conference on Multimedia - MULTIMEDIA '03. pp. 255- 258 ,(2003) , 10.1145/957013.957065
Yi Wu, Edward Y. Chang, Kevin Chen-Chuan Chang, John R. Smith, Optimal multimodal fusion for multimedia data analysis acm multimedia. pp. 572- 579 ,(2004) , 10.1145/1027527.1027665
Thijs Westerveld, Arjen P. de Vries, Alex van Ballegooij, Franciska de Jong, Djoerd Hiemstra, A Probabilistic Multimedia Retrieval Model and Its Evaluation EURASIP Journal on Advances in Signal Processing. ,vol. 2003, pp. 186- 198 ,(2003) , 10.1155/S111086570321101X
S. Tsekeridou, I. Pitas, Content-based video parsing and indexing based on audio-visual interaction IEEE Transactions on Circuits and Systems for Video Technology. ,vol. 11, pp. 522- 535 ,(2001) , 10.1109/76.915358
Alexander J Smola, Peter Bartlett, Bernhard Schölkopf, Dale Schuurmans, None, Probabilities for SV Machines MIT Press. pp. 61- 73 ,(2000)
Arnon Amir, Janne Argillander, Murray Campbell, Alexander Haubold, Giridharan Iyengar, Shahram Ebadollahi, Feng Kang, Milind R Naphade, Apostol Natsev, John R Smith, Jelena Tesic, Timo Volkmer, IBM Research TRECVID-2003 Video Retrieval System. TRECVID. ,(2003)
Cees Snoek, M. Worring, Jan Mark Geusebroek, Dennis Koelma, Frank Seinstra, None, The MediaMill TRECVID 2004 Semantic Video Search Engine TRECVID Workshop. ,(2004)