Official implementation of the paper "MotionAGFormer: Enhancing 3D Pose Estimation with a Transformer-GCNFormer Network" (WACV 2024).

This is an official PyTorch implementation of "Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition" in AAAI2022.

Supercharged BLIP-2 that can handle videos

A simple script that reads a directory of videos, grabs a random frame, and automatically discovers a prompt for it