Strategies for Searching Video Content with Text Queries or Video Examples
This work addresses the metadata-scarcity issue for user-generated videos, enabling more effective search in commercial engines, though it appears incremental as it builds on existing CBVR topics.
The paper tackled the problem of searching user-generated videos lacking metadata by developing content-based video retrieval strategies, achieving top performance in the TRECVID 2014 evaluation for both text and video example queries.
The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search. However, metadata is often lacking for user-generated videos, thus these videos are unsearchable by current search engines. Therefore, content-based video retrieval (CBVR) tackles this metadata-scarcity problem by directly analyzing the visual and audio streams of each video. CBVR encompasses multiple research topics, including low-level feature design, feature fusion, semantic detector training and video search/reranking. We present novel strategies in these topics to enhance CBVR in both accuracy and speed under different query inputs, including pure textual queries and query by video examples. Our proposed strategies have been incorporated into our submission for the TRECVID 2014 Multimedia Event Detection evaluation, where our system outperformed other submissions in both text queries and video example queries, thus demonstrating the effectiveness of our proposed approaches.