TVQA Dataset

by Jie LeiResearch Only

TVQA Dataset

TVQA is a large-scale video QA dataset based on 6 popular TV shows (Friends, The Big Bang Theory, How I Met Your Mother, House M.D., Grey's Anatomy, Castle). It consists of 152.5K QA pairs from 21.8K video clips, spanning over 460 hours of video. The questions are designed to be compositional, requiring systems to jointly localize relevant moments within a clip, comprehend subtitles-based dialogue, and recognize relevant visual concepts. TVQA+ is a subset of TVQA dataset, additionally augmented with 310.8k bounding boxes, linking depicted objects to visual concepts in questions and answers.

Dataset Attributes

Label SVG
TasksVisual Reasoning
Label SVG
CategoriesPop Culture
Label SVG
SensorRGB Camera