Abstract
Recent improvements in content-based video search have led to systems with promising accuracy, thus opening up the possibility for interactive content-based video search to the general public. We present an interactive system based on a state-of-the-art content-based video search pipeline which enables users to do multimodal text-to-video and video-tovideo search in large video collections, and to incrementally refine queries through relevance feedback and model visualization. Also, the comprehensive functionalities enhance a flexible formulation of multimodal queries with different characteristics. Quantitative and qualitative analysis shows that our system is capable of assisting users to incrementally build effective queries over complex event topics.
Original language | English |
---|---|
Title of host publication | ICMR’15 - Proceedings of the 2015 ACM International Conference on Multimedia Retrieval |
Subtitle of host publication | June 23–26, 2015 Shanghai, China |
Editors | Yu-Gang Jiang, Cees Snoek, Nuno Vasconcelos |
Place of Publication | New York NY USA |
Publisher | Association for Computing Machinery (ACM) |
Pages | 675-678 |
Number of pages | 4 |
ISBN (Electronic) | 9781450332743 |
DOIs | |
Publication status | Published - 2015 |
Externally published | Yes |
Event | ACM International Conference on Multimedia Retrieval 2015 - Shanghai, China Duration: 23 Jun 2015 → 26 Jun 2015 Conference number: 5th https://dl.acm.org/doi/proceedings/10.1145/2671188 (Proceedings) |
Conference
Conference | ACM International Conference on Multimedia Retrieval 2015 |
---|---|
Abbreviated title | ICMR 2015 |
Country/Territory | China |
City | Shanghai |
Period | 23/06/15 → 26/06/15 |
Internet address |
|
Keywords
- Content-based video search
- Multimedia event detection
- Multimodal query generation