# siyuanliii/masa

Official Implementation of CVPR24 highlight paper: Matching Anything by Segmenting Anything

Repository: https://github.com/siyuanliii/masa
Canonical: https://ross.abutalabs.com/products/masa
Homepage: https://matchinganything.github.io
Language: Python
License: Apache-2.0
License Family: permissive
Topics: self-supervision, tracking-everything
Last push: 2025-05-01T06:32:27+00:00

## Health v2 (maintenance only)
Score: 33/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 19, release rhythm 35, longevity 63
- inputs: {"age_days": 888, "days_push": 489, "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 1377, forks 90 (observed 2026-08-28T04:04:33.339108+00:00)

## What it is
Official PyTorch implementation of MASA (CVPR 2024 Highlight), a universal instance appearance model that learns to match any objects across video frames using Segment Anything Model outputs, without tracking labels. It includes a universal adapter that adds zero-shot multi-object tracking and segmentation capabilities to existing detection or segmentation models.

## Use cases
- track any object in video without domain-specific training labels
- add multi-object tracking to an existing detector like YOLO-World
- segment and track objects jointly in videos with SAM
- zero-shot open-vocabulary multiple object tracking
- evaluate on MOT and MOTS benchmarks like TAO TETA and BDD100K
- learn instance appearance embeddings from unlabeled static images

## When to choose
- you need cross-domain or open-vocabulary object tracking without labeled video data
- you want to bolt tracking onto an existing detection or segmentation model
- you are researching instance association and appearance matching

## When to avoid
- you need a production-ready turnkey video analytics product
- you lack GPU resources for inference or training
- you need simple single-object tracking only

## Facets
- artifact type: library
- maturity: active
- function: computer-vision, machine-learning, image-processing, deep-learning
- domain: computer-vision, machine-learning, artificial-intelligence
- platform: python
- tags: object-tracking, multiple-object-tracking, segment-anything, zero-shot-tracking, instance-association, cvpr-2024, research-code, video-analysis, linux, gpu

## Member repositories
- siyuanliii/masa (main) score 33

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:33.339108+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 2026-08-30T04:40:27.608405+00:00, confidence not recorded.
  - readme: https://github.com/siyuanliii/masa (fetched 2026-08-28T04:04:33.339108+00:00, sha 3154a3ae4169)
  - homepage: https://matchinganything.github.io (fetched 2026-08-29T11:56:39.359094+00:00, sha 6a4283db39ee)
- Data as of 2026-08-30T08:39:29.467469+00:00.