Semantic context transfer across heterogeneous sources for domain adaptive video search
- 19 October 2009
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 155-164
- https://doi.org/10.1145/1631272.1631296
Abstract
Automatic video search based on semantic concept detectors has recently received significant attention. Since the number of available detectors is much smaller than the size of human vocabulary, one major challenge is to select appropriate detectors to response user queries. In this paper, we propose a novel approach that leverages heterogeneous knowledge sources for domain adaptive video search. First, instead of utilizing WordNet as most existing works, we exploit the context information associated with Flickr images to estimate query-detector similarity. The resulting measurement, named Flickr context similarity (FCS), reflects the co-occurrence statistics of words in image context rather than textual corpus. Starting from an initial detector set determined by FCS, our approach novelly transfers semantic context learned from test data domain to adaptively refine the query-detector similarity. The semantic context transfer process provides an effective means to cope with the domain shift between external knowledge source (e.g., Flickr context) and test data, which is a critical issue in video search. To the best of our knowledge, this work represents the first research aiming to tackle the challenging issue of domain change in video search. Extensive experiments on 120 textual queries over TRECVID 2005-2008 data sets demonstrate the effectiveness of semantic context transfer for domain adaptive video search. Results also show that the FCS is suitable for measuring query-detector similarity, producing better performance to various other popular measures.Keywords
This publication has 27 references indexed in Scilit:
- Resolving tag ambiguityPublished by Association for Computing Machinery (ACM) ,2008
- Online Manifold Regularization: A New Learning Setting and Empirical StudyLecture Notes in Computer Science, 2008
- Web-based information content and its application to concept-based video retrievalPublished by Association for Computing Machinery (ACM) ,2008
- Cross-domain video concept detection using adaptive svmsPublished by Association for Computing Machinery (ACM) ,2007
- Towards optimal bag-of-features for object categorization and semantic video retrievalPublished by Association for Computing Machinery (ACM) ,2007
- To search or to label?Published by Association for Computing Machinery (ACM) ,2006
- Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive StudyInternational Journal of Computer Vision, 2006
- Video Retrieval Using High Level Features: Exploiting Query Matching and Confidence-Based WeightingLecture Notes in Computer Science, 2006
- Content-based image retrieval at the end of the early yearsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Verbs semantics and lexical selectionPublished by Association for Computational Linguistics (ACL) ,1994