WildQA: In-the-Wild Video Question Answering
This addresses a gap in vision and language research by providing a dataset for outdoor video understanding, though it is incremental as it extends existing video QA tasks to new settings.
The authors tackled the lack of video understanding datasets for outdoor settings by introducing WILDQA, a dataset for in-the-wild video question answering, and showed that it poses new challenges to baseline models.
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/.