DORi: Discovering Object Relationships for Moment Localization of a Natural Language Query in a Video
This paper studies the task of temporal moment localization in long untrimmed videos using natural language queries. Given a query sentence, the goal is to determine the start and end of the relevant segment within the video. Our key innovation is to learn a video feature embedding through a languag...
Saved in:
Published in | 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) pp. 1078 - 1087 |
---|---|
Main Authors | , , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
01.01.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | This paper studies the task of temporal moment localization in long untrimmed videos using natural language queries. Given a query sentence, the goal is to determine the start and end of the relevant segment within the video. Our key innovation is to learn a video feature embedding through a language-conditioned message-passing algorithm suitable for temporal moment localization which captures the relationships between humans, objects and activities in the video. These relationships are obtained by a spatial sub-graph that contextualizes the scene representation using detected objects and human features conditioned in the language query. Moreover, a temporal sub-graph captures the activities within the video through time. Our method is evaluated on three standard benchmark datasets, and we also introduce YouCookII as a new benchmark for this task. Experiments show our method outperforms state-of-the-art methods on these datasets, confirming the effectiveness of our approach. |
---|---|
ISSN: | 2642-9381 |
DOI: | 10.1109/WACV48630.2021.00112 |