UNIGE document Chapitre d'actes
previous document  unige:47728  next document
add to browser collection
Title

Learning User Queries in Multimodal Dissimilarity Spaces

Authors
Published in Adaptive Multimedia Retrieval: User, Context, and Feedback : 3rd International Workshop, AMR 2005. Revised Selected Papers. Glasgow (UK) - Jul. 28-19 - Springer. 2005, p. 168-179
Collection Lecture Notes in Computer Science; 3877
Abstract Different strategies to learn user semantic queries from dissimilarity representations of audio-visual content are presented. When dealing with large corpora of videos documents, using a feature representation requires the on-line computation of distances between all documents and a query. Hence, a dissimilarity representation may be preferred because its offline computation speeds up the retrieval process. We show how distances related to visual and audio video features can directly be used to learn complex concepts from a set of positive and negative examples provided by the user. Based on the idea of dissimilarity spaces, we derive three algorithms to fuse modalities and therefore to enhance the precision of retrieval results. The evaluation of our technique is performed on artificial data and on the annotated TRECVID corpus.
Keywords Data Structures, Cryptology and Information TheoryInformation Storage and RetrievalMultimedia Information SystemsInformation Systems Applications (incl. Internet)Image Processing and Computer VisionArtificial Intelligence (incl. Robotics)
Identifiers
Full text
Structures
Research groups Computer Vision and Multimedia Laboratory
Viper group
Citation
(ISO format)
BRUNO, Eric, MOENNE-LOCCOZ, Nicolas, MARCHAND-MAILLET, Stéphane. Learning User Queries in Multimodal Dissimilarity Spaces. In: Adaptive Multimedia Retrieval: User, Context, and Feedback : 3rd International Workshop, AMR 2005. Revised Selected Papers. Glasgow (UK). [s.l.] : Springer, 2005. p. 168-179. (Lecture Notes in Computer Science; 3877) https://archive-ouverte.unige.ch/unige:47728

142 hits

21 downloads

Update

Deposited on : 2015-03-06

Export document
Format :
Citation style :