Exploring Anchor-based Detection for Ego4D Natural Language Query
This work addresses natural language query for ego-centric video analysis, but it appears incremental as it adapts existing methods to a new dataset.
The paper tackles the challenge of natural language query in ego-centric videos, specifically for the Ego4D dataset, by addressing issues like short query durations and complex temporal understanding, proposing an anchor-based detection solution.
In this paper we provide the technique report of Ego4D natural language query challenge in CVPR 2022. Natural language query task is challenging due to the requirement of comprehensive understanding of video contents. Most previous works address this task based on third-person view datasets while few research interest has been placed in the ego-centric view by far. Great progress has been made though, we notice that previous works can not adapt well to ego-centric view datasets e.g., Ego4D mainly because of two reasons: 1) most queries in Ego4D have a excessively small temporal duration (e.g., less than 5 seconds); 2) queries in Ego4D are faced with much more complex video understanding of long-term temporal orders. Considering these, we propose our solution of this challenge to solve the above issues.