Fine-grained badminton video question answering benchmark.
hf_video_clips_qa/: one clip per QA item, named by video_uid (for example video_000001.mp4).
finebadmintonbenchmark/: annotation JSON files.
each item contains video_uid
each QA item maps to exactly one video clip through video_uid
@inproceedings{he2025finebadminton,
title={Finebadminton: A multi-level dataset for fine-grained badminton video… See the full description on the dataset page:
https://huggingface.co/datasets/iLearn-Lab/FineBadmintonBenchmark.
