Datasets › MAD
MAD
MAD (Movie Audio Descriptions) is an automatically curated large-scale dataset for the task of natural language grounding in videos or natural language moment retrieval. MAD exploits available audio descriptions of mainstream movies. Such audio descriptions are redacted for visually impaired audiences and are therefore highly descriptive of the visual content being displayed. MAD contains over 384,000 natural language sentences grounded in over 1,200 hours of video, and provides a unique setup for video grounding as the visual stream is truly untrimmed with an average video duration of 110 minutes. 2 orders of magnitude longer than legacy datasets.
Take a look at the paper for additional information.
From the authors on availability: "Due to copyright constraints, MAD’s videos will not be publicly released. However, we will provide all necessary features for our experiments’ reproducibility and promote future research in this direction"
Benchmarks archive 2025-07-28
All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Natural Language Moment Retrieval | MAD | ReVisionLLM R@1,IoU=0.1 17.3 | ReVisionLLM: Recursive Vision-Language Model for... | tanveer81/revisionllm | 8 | Compare |
| Video Grounding | MAD | DeCafNet R@1,IoU=0.1 13.25 | DeCafNet: Delegate and Conquer for Efficient Temporal... | zijialewislu/cvpr2025-decafnet | 2 | Compare |
Papers archive 2025-07-28
6 shown of 6 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 36. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos | 1 | 2 | 22 May 2025 | not harvested |
| ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos | 1 | 1 | 22 Nov 2024 | not harvested |
| RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos | 2 | 1 | 11 Dec 2023 | not harvested |
| Boundary-Denoising for Video Activity Localization | 1 | 1 | 6 Apr 2023 | not harvested |
| Localizing Moments in Long Video Via Multimodal Guidance | 1 | 2 | 26 Feb 2023 | not harvested |
| MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions | 1 | 3 | 1 Dec 2021 | ran 1 of 1 samples (0 unverified; 1 pointer-only for licence) |
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
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
Languages archive 2025-07-28
Variants archive 2025-07-28
- MAD
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