ViTAE-Transformer/APTv2

The official repo for the extension of [NeurIPS'22] "APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking": https://github.com/pandorgan/APT-36K

23
/ 100
Experimental

This project offers a comprehensive benchmark dataset and evaluation tools for tracking animal movements and identifying key body points across video frames. It takes video clips of various animal species and outputs precise annotations of animal poses and their trajectories. This is ideal for researchers, zoologists, and ethologists studying animal behavior or developing advanced computer vision models for animal monitoring.

No commits in the last 6 months.

Use this if you need a high-quality, large-scale dataset to train or test algorithms for accurately detecting and tracking animal body keypoints in video.

Not ideal if your focus is on static image analysis or if you only need general animal detection rather than detailed pose estimation and tracking over time.

animal-behavior ethology wildlife-monitoring video-analysis zoology
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

28

Forks

Language

Python

License

Apache-2.0

Last pushed

May 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ViTAE-Transformer/APTv2"

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