TVQA+

Introduced by Lei et al. in TVQA+: Spatio-Temporal Grounding for Video Question Answering

TVQA+ contains 310.8K bounding boxes, linking depicted objects to visual concepts in questions and answers.

Source: TVQA+: Spatio-Temporal Grounding for Video Question Answering

Homepage

No benchmarks yet. Start a new benchmark or link an existing one.

Paper	Code	Results	Date	Stars

120

Violin

Source: https://github.com/jayleicn/TVQAplus.