Datasets › ActivityNet Captions
ActivityNet Captions
The ActivityNet Captions dataset is built on ActivityNet v1.3 which includes 20k YouTube untrimmed videos with 100k caption annotations. The videos are 120 seconds long on average. Most of the videos contain over 3 annotated events with corresponding start/end time and human-written sentences, which contain 13.5 words on average. The number of videos in train/validation/test split is 10024/4926/5044, respectively.
Source: Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning Image Source: https://cs.stanford.edu/people/ranjaykrishna/densevid/
Benchmarks archive 2025-07-28
All 6 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 | ||||
|---|---|---|---|---|---|---|
| Dense Video Captioning | ActivityNet Captions | Vid2Seq METEOR 17 | Vid2Seq: Large-Scale Pretraining of a Visual Language... | google-research/scenic +2 | 12 | Compare |
| Natural Language Moment Retrieval | ActivityNet Captions | GVL (paragraph-level) R@1,IoU=0.5 60.67 | Learning Grounded Vision-Language Representation for... | zjr2000/gvl | 8 | Compare |
| Video Captioning | ActivityNet Captions | VideoCoCa BLEU4 14.7 | VideoCoCa: Video-Text Modeling with Zero-Shot Transfer... | — | 5 | Compare |
| Live Video Captioning | ActivityNet Captions | LVC Live Score 20.81 | Live Video Captioning | gramuah/lvc | 1 | Compare |
| Partially Relevant Video Retrieval | ActivityNet Captions | ms-sl Recall@Sum 140.1 | Partially Relevant Video Retrieval | HuiGuanLab/ms-sl | 1 | Compare |
| Temporal Action Proposal Generation | ActivityNet Captions | BMT Average F1 60.27 | A Better Use of Audio-Visual Cues: Dense Video... | v-iashin/video_features +1 | 1 | Compare |
Papers archive 2025-07-28
24 shown of 24 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 255. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
Unknown
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- ActivityNet Captions
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