# OpenGVLab/VideoMamba

[ECCV2024] VideoMamba: State Space Model for Efficient Video Understanding

Repository: https://github.com/OpenGVLab/VideoMamba
Canonical: https://ross.abutalabs.com/products/videomamba
Homepage: https://arxiv.org/abs/2403.06977
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2024-07-06T11:07:17+00:00

## Health v2 (maintenance only)
Score: 25/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 64
- inputs: {"age_days": 905, "days_push": 788, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1125, forks 96 (observed 2026-08-28T04:03:40.955078+00:00)

## What it is
VideoMamba is a state space model (Mamba-based) architecture for efficient video understanding, released with code and pretrained models from an ECCV 2024 paper. It supports image classification, short- and long-term video understanding, masked pretraining, and video-text retrieval.

## Use cases
- classify videos into action categories
- understand long videos efficiently with linear complexity
- recognize fine-grained short-term actions
- retrieve videos using text queries
- pretrain video models with masked modeling
- classify images with a Mamba backbone

## When to choose
- you need efficient long-term video modeling without quadratic transformer cost
- you want pretrained Mamba-based video models and training scripts
- you are researching state space models for vision

## When to avoid
- you need a production-ready video analytics service rather than research code
- you require broad ecosystem tooling or frequent updates
- your task is unrelated to video or image understanding

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, video-processing, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: mamba, state-space-model, video-understanding, eccv-2024, model-zoo, video-retrieval, action-recognition, video, gpu

## Member repositories
- OpenGVLab/VideoMamba (main) score 25

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:40.955078+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:39:21.840348+00:00, confidence not recorded.
  - readme: https://github.com/OpenGVLab/VideoMamba (fetched 2026-08-28T04:03:40.955078+00:00, sha dba38c36122a)
  - homepage: https://arxiv.org/abs/2403.06977 (fetched 2026-08-29T12:44:02.769814+00:00, sha 25c491a5bce2)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T12:44:02.778901+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T12:44:02.782769+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T12:44:02.784727+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T12:44:02.780751+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.