Codesota · Computer Vision · Video classification · Something-Something V2Tasks/Computer Vision/Video classification
Video classification · benchmark dataset · 2017 · EN

Something-Something V2.

Fine-grained temporal action understanding with objects

Submit a result ↵
§ 01 · Leaderboard

Best published scores.

5 results indexed across 1 metric. Shaded row marks current SOTA; ties broken by submission date.

Primary
top-1-accuracy · higher is better
accuracy
5 rows
#ModelOrgSubmittedPaper / codeaccuracy
01V-JEPA 2 ViT-g (1B, 384px)—Jun 2025V-JEPA 2: Self-Supervised Video Models Enable Understand… · code77.30
02VideoMAE ViT-L—Mar 2022VideoMAE: Masked Autoencoders are Data-Efficient Learner… · code75.40
03DINOv3 (7B)—Aug 2025DINOv3 · code70.80
04VideoPrism-g—Feb 2024VideoPrism: A Foundational Visual Encoder for Video Unde… · code68.50
05DINOv2 (ViT-g/14)—Apr 2023DINOv2: Learning Robust Visual Features without Supervis… · code38.30
Fig 2 · Rows sorted by score within each metric. Shaded row marks SOTA. Dates reflect model or paper release where available, otherwise the date Codesota accessed the source.
§ 04 · Literature

5 papers
tied to this benchmark.

Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.

§ 06 · Contribute

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

Submit a result ↵Read submission guide
What a submission needs
  • 01A public checkpoint or API endpoint
  • 02A reproduction script with frozen commit + seed
  • 03Declared evaluation environment (Python, deps)
  • 04One row per metric declared by this dataset
  • 05A contact so we can follow up on discrepancies