WildQA: In-the-Wild Video Question Answering

Santiago Castro; Naihao Deng; Pingxuan Huang; Mihai Burzo; Rada Mihalcea

WildQA: In-the-Wild Video Question Answering

Computer Vision and Pattern Recognition 2022-09-15 v1 Computation and Language

Authors: 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/.

Keywords

visual question answering question answering video retrieval

Cite

@article{arxiv.2209.06650,
  title  = {WildQA: In-the-Wild Video Question Answering},
  author = {Santiago Castro and Naihao Deng and Pingxuan Huang and Mihai Burzo and Rada Mihalcea},
  journal= {arXiv preprint arXiv:2209.06650},
  year   = {2022}
}

Comments

*: Equal contribution; COLING 2022 oral; project webpage: https://lit.eecs.umich.edu/wildqa/

WildQA: In-the-Wild Video Question Answering

Abstract

Keywords

Cite

Comments

Related papers