Paper Info
Title
Dori: Discovering Object Relationships For Moment Localization Of A Natural Language Query In A Video
Abstract
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.
Year
DOI
Venue
2021
10.1109/WACV48630.2021.00112
2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021)
DocType
ISSN
Citations 
Conference
2472-6737
0
PageRank 
References 
Authors
0.34
0
5
Name
Order
Citations
PageRank
Cristian Rodriguez101.69
Edison Marrese-Taylor200.68
Basura Fernando300.34
Hongdong Li41724101.81
Stephen Gould5137887.70