# ifzhang/FairMOT

[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

Repository: https://github.com/ifzhang/FairMOT
Canonical: https://ross.abutalabs.com/products/fairmot
Language: Python
License: MIT
License Family: permissive
Topics: multi-object-tracking, one-shot-tracker, joint-detection-and-tracking, real-time
Last push: 2023-09-19T07:48:24+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2342, "days_push": 1079, "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 4244, forks 924 (observed 2026-08-28T04:08:40.333897+00:00)

## What it is
FairMOT is a research implementation of a one-shot multi-object tracking model that jointly performs object detection and re-identification in a single network. It achieves state-of-the-art results on MOT challenge benchmarks at around 30 FPS.

## Use cases
- track multiple objects in video in real time
- jointly detect and re-identify pedestrians in surveillance footage
- reproduce state-of-the-art results on MOT16/MOT17/MOT20 benchmarks
- run multi-object tracking at 30 FPS on GPU
- fine-tune a tracker on custom video datasets
- compare one-shot tracking baselines for research

## When to choose
- you need a well-cited, proven multi-object tracking baseline with strong MOT benchmark accuracy
- you want joint detection and re-identification in one network for real-time tracking
- you are doing computer vision research on tracking and need a reproducible reference implementation

## When to avoid
- you need a production-maintained tracker with active updates and easy pip installation
- you work outside Python/PyTorch or lack a GPU
- you need lightweight tracking on CPU or edge devices without tuning

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, machine-learning, deep-learning, image-processing
- domain: computer-vision, artificial-intelligence, deep-learning
- platform: python
- tags: multi-object-tracking, object-detection, re-identification, one-shot-tracker, real-time, research-code, pytorch, linux, gpu

## Member repositories
- ifzhang/FairMOT (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:40.333897+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 2026-08-29T18:22:13.502783+00:00, confidence not recorded.
  - readme: https://github.com/ifzhang/FairMOT (fetched 2026-08-28T04:08:40.333897+00:00, sha a767870cb9a8)
- Data as of 2026-08-30T08:39:29.467469+00:00.