In-the-Wild Video Question Answering
Santiago Castro, Naihao Deng, Pingxuan Huang, Mihai Burzo, Rada Mihalcea
Abstract
Existing video understanding datasets mostly focus on human interactions, with little attention being paid to the “in the wild” settings, where the videos are recorded outdoors. We propose WILDQA, a video understanding dataset of videos recorded in outside settings. In addition to video question answering (Video QA), we also introduce the new task of identifying visual support for a given question and answer (Video Evidence Selection). Through evaluations using a wide range of baseline models, we show that WILDQA poses new challenges to the vision and language research communities. The dataset is available at https: //lit.eecs.umich.edu/wildqa/.- Anthology ID:
- 2022.coling-1.496
- Volume:
- Proceedings of the 29th International Conference on Computational Linguistics
- Month:
- October
- Year:
- 2022
- Address:
- Gyeongju, Republic of Korea
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 5613–5635
- Language:
- URL:
- https://aclanthology.org/2022.coling-1.496
- DOI:
- Cite (ACL):
- Santiago Castro, Naihao Deng, Pingxuan Huang, Mihai Burzo, and Rada Mihalcea. 2022. In-the-Wild Video Question Answering. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5613–5635, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
- Cite (Informal):
- In-the-Wild Video Question Answering (Castro et al., COLING 2022)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/2022.coling-1.496.pdf
- Data
- MovieQA, TVQA, TVQA+