# jfzhang95/pytorch-video-recognition

PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.

Repository: https://github.com/jfzhang95/pytorch-video-recognition
Canonical: https://ross.abutalabs.com/products/pytorch-video-recognition
Language: Python
License: MIT
License Family: permissive
Topics: c3d, r2plus1d, r3d, video-activity-recognition
Last push: 2023-12-27T04:31:36+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": 2955, "days_push": 980, "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 1236, forks 252 (observed 2026-08-28T04:04:05.235904+00:00)

## What it is
A PyTorch library implementing C3D, R3D, and R2Plus1D models for video action recognition, with training scripts for UCF101 and HMDB51 datasets. It includes a pretrained C3D model and dataset preprocessing utilities.

## Use cases
- train a C3D model on UCF101
- classify human actions in videos
- fine-tune R2Plus1D on my own video dataset
- get a pretrained video recognition model in PyTorch
- reproduce video action recognition experiments
- extract video features with C3D

## When to choose
- you need classic 3D CNN baselines (C3D, R3D, R2Plus1D) in PyTorch
- you want to train or fine-tune action recognition on UCF101/HMDB51-style datasets
- you need a simple, readable research codebase to modify

## When to avoid
- you need state-of-the-art video transformers or modern architectures
- you want production-ready inference pipelines or active maintenance
- you need pretrained models beyond C3D or datasets beyond UCF101/HMDB51

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, video-processing, computer-vision
- domain: computer-vision, deep-learning, machine-learning
- platform: python, cross-platform
- tags: pytorch, video-action-recognition, c3d, r3d, r2plus1d, ucf101, hmdb51, research-code, video, gpu, linux

## Member repositories
- jfzhang95/pytorch-video-recognition (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:05.235904+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 2026-08-30T08:21:59.190734+00:00, confidence not recorded.
  - readme: https://github.com/jfzhang95/pytorch-video-recognition (fetched 2026-08-28T04:04:05.235904+00:00, sha 070af9f973cf)
- Data as of 2026-08-30T08:39:29.467469+00:00.