In this paper, we introduce a multi-user hierarchical video search tool called VIDEOFALL. Our objective, in the Video Browser Showdown (VBS) 2022, is to explore if VIDEOFALL interactive video retrieval under time constraints is a useful approach to take, given the overhead of requiring multiple users. It is our conjecture that combining the different skills of normal users can support a master user to retrieve target videos efficiently. The system is designed on top of the CLIP pre-trained model and the video keyframes are embedded into a vector space in which queries would also be encoded to facilitate retrieval.
Metadata
Item Type:
Conference or Workshop Item (Paper)
Event Type:
Conference
Refereed:
Yes
Uncontrolled Keywords:
video search; Video Browser Showdown; Interactive Video Retrieval; Hierarchical Engine; Multi-user Search Engine
Science Foundation Ireland under Grant Agreement No. 18/CRT/6223, and 13/RC/2106_P2 at the ADAPT SFI Research Centre at DCU, ADAPT, the SFI Research Centre for AI-Driven Digital Content Technology, is funded by Science Foundation Ireland through the SFI Research Centres Programme.
ID Code:
27036
Deposited On:
20 Apr 2022 11:51 by
Thao-Nhu Nguyen
. Last Modified 03 Mar 2023 12:52