Referring to Objects in Videos Using Spatio-Temporal Identifying Descriptions

Peratham Wiriyathammabhum, Abhinav Shrivastava, Vlad Morariu, Larry Davis


Abstract
This paper presents a new task, the grounding of spatio-temporal identifying descriptions in videos. Previous work suggests potential bias in existing datasets and emphasizes the need for a new data creation schema to better model linguistic structure. We introduce a new data collection scheme based on grammatical constraints for surface realization to enable us to investigate the problem of grounding spatio-temporal identifying descriptions in videos. We then propose a two-stream modular attention network that learns and grounds spatio-temporal identifying descriptions based on appearance and motion. We show that motion modules help to ground motion-related words and also help to learn in appearance modules because modular neural networks resolve task interference between modules. Finally, we propose a future challenge and a need for a robust system arising from replacing ground truth visual annotations with automatic video object detector and temporal event localization.
Anthology ID:
W19-1802
Volume:
Proceedings of the Second Workshop on Shortcomings in Vision and Language
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Raffaella Bernardi, Raquel Fernandez, Spandana Gella, Kushal Kafle, Christopher Kanan, Stefan Lee, Moin Nabi
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14–25
Language:
URL:
https://aclanthology.org/W19-1802
DOI:
10.18653/v1/W19-1802
Bibkey:
Cite (ACL):
Peratham Wiriyathammabhum, Abhinav Shrivastava, Vlad Morariu, and Larry Davis. 2019. Referring to Objects in Videos Using Spatio-Temporal Identifying Descriptions. In Proceedings of the Second Workshop on Shortcomings in Vision and Language, pages 14–25, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Referring to Objects in Videos Using Spatio-Temporal Identifying Descriptions (Wiriyathammabhum et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-1802.pdf
Supplementary:
 W19-1802.Supplementary.pdf
Data
TEMPO