Title
Blind late fusion in multimedia event retrieval
Author
de Boer, M.H.T.
Schutte, K.
Zhang, H.
Lu, Y.J.
Ngo, C.W.
Kraaij, W.
Publication year
2016
Abstract
One of the challenges in Multimedia Event Retrieval is the integration of data from multiple modalities. A modality is defined as a single channel of sensory input,such as visual or audio. We also refer to this as data source. Previous research has shown that the integration of different data sources can improve performance compared to only using one source, but a clear insight of success factors of alternative fusion methods is still lacking. We introduce several new blind late fusion methods based on inversions and ratios of the state-of-the-art blind fusion methods and compare performance in both simulations and an international benchmark data set in multimedia event retrieval named TRECVID MED.The results showthat five of the proposed methods outperform the state-of-the-art methods in a case with sufficient training examples (100 examples). The novel fusion method named JRER is not only the best method with dependent data sources, but this method is also a robust method in all simulations with sufficient training examples.
Subject
Observation, Weapon & Protection Systems
II - Intelligent Imaging
TS - Technical Sciences
Defence Research
Defence, Safety and Security
Multimedia event retrieval
Multimodal
Integration
Late fusion
To reference this document use:
http://resolver.tudelft.nl/uuid:ad8f3e10-59e8-4994-ab7c-c2a08c4d033e
TNO identifier
574204
Source
Int J Mediamed Retr (5), 203-217
Document type
article