quic/sense

Enhance your application with the ability to see and interact with humans using any RGB camera.

Archived
47
/ 100
Emerging

Provides pre-trained efficient neural networks (MobileNet and EfficientNet backbones) optimized for real-time CPU inference, recognizing 30+ actions, 80+ fitness activities, and hand gestures from video streams. Includes a fine-tuning pipeline for custom action classifiers using transfer learning on your own annotated datasets. Targets Python/PyTorch applications on Linux, macOS, and iOS with demo applications for fitness tracking, gesture control, and activity recognition.

737 stars. No commits in the last 6 months.

Archived Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

737

Forks

109

Language

Python

License

MIT

Category

human-activity-recognition

Last pushed

Dec 07, 2021

Commits (30d)

0

GitHub
Human Activity Recognition · 6 tools

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/quic/sense"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Related tools

CV-ZMH/human-action-recognition

Multi Person Skeleton Based Action Recognition and Tracking

46

AlexanderMelde/SPHAR-Dataset

Surveillance Perspective Human Action Recognition Dataset: 7759 Videos from 14 Action Classes,...

46

Event-AHU/HARDVS

[AAAI-2024] HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors

43

yujmo/CZU_MHAD

CZU-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and 10...

23

AlexanderMelde/S-SPHAR-Dataset

Synthetically Generated Surveillance Perspective Human Action Recognition Dataset: 6901 Videos...

22

Explore Computer Vision Tools

All categories Trending Computer Vision directory Insights