Computer vision & multimodal· 2024
SAM 2: Segment Anything in Images and Videos
On the reading lists
- #499 in the Top 500 (2026 edition)
- #73 in Computer vision & multimodal (2026 edition)
Why it matters
Unified promptable segmentation for images and video.
Condensed from the expert lists' notes.
The record
- First released
- 2024 (from arXiv 2408.00714)
- Citations
- 4,567 citations, as counted by Papers With Code (CC BY-SA 4.0)
- Named by
- the grok list only
- Score
- 0.343 · computed rank 499 · consensus 0.01, must-read 0.5, citations percentile 0.827 (2020s · vision), awards 0, existing lists 0. Method
Data sources
Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.