Datasets › TV-AD

TV-AD (Audio Description dataset for TV series)

Introduced by Junyu Xie et al. in AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description22 Jul 2024 archive 2025-07-28

TV-AD is a dataset that provides ground truth AD annotations that are aligned with TV series video, featuring episodes across multiple TV series including “The Big Bang Theory”, “Friends”, “Frasier”, “Seinfeld”, etc. The dataset is divided into training (TV-AD-Train, ∼31k ADs) and evaluation splits (TV-AD-Eval, ∼3k ADs), ensuring that the TV series do not overlap between the two splits. The evaluation split contains AD annotations for TV videos that are publicly available.

Benchmarks archive 2025-07-28

No leaderboard in the archive resolves to this dataset.

Papers archive 2025-07-28

No paper in the archive has a leaderboard row on this dataset; the archive counts 3 papers for it but never published that list.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

No task tagged in the archive.

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • TV-AD

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections