A Multimodal and Multilevel Ranking Framework for Large-Scale Video Retrieval
A critical issue of large-scale multimedia retrieval is how to develop an effective framework for ranking the search results. This problem is particularly challenging for content-based video retrieval due to some issues such as short text queries, insufficient sample learning, fusion of multimodal contents, and large-scale learning with huge media data. In this paper, we propose a novel multimodal and multilevel (MMML) ranking framework to attack the challenging ranking problem of content-based video retrieval. We represent the video retrieval task by graphs and suggest a graph based semi-supervised ranking (SSR) scheme, which can learn with small samples effectively and integrate multimodal resources for ranking smoothly. To make the semi-supervised ranking solution practical for large-scale retrieval tasks, we propose a multilevel ranking framework that unifies several different ranking approaches in a cascade fashion. We have conducted empirical evaluations of our proposed solution for automatic search tasks on the benchmark testbed of TRECVID2005. The promising empirical results show that our ranking solutions are effective and very competitive with the state-of-the-art solutions in the TRECVID evaluations.
Content-based video retrieval, graph representation, multilevel ranking, multimedia retrieval, multimodal fusion, semi-supervised ranking, support vector machines
Artificial Intelligence and Robotics
IEEE Transactions on Multimedia (IEEE TMM)
HOI, Steven and Lyu, Michael R..
A Multimodal and Multilevel Ranking Framework for Large-Scale Video Retrieval. (2008). IEEE Transactions on Multimedia (IEEE TMM). 10, (4), 607-619. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/2313
This document is currently not available here.