r-kellerm's repositories
DIG
A library for graph deep learning research
Language:PythonGPL-3.0000
medAlpaca
LLM finetuned for medical question answering
Language:PythonGPL-3.0000
MeMViT
Code Release for MeMViT Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition, CVPR 2022
Language:PythonNOASSERTION000
Motionformer
Code + pre-trained models for the paper Keeping Your Eye on the Ball Trajectory Attention in Video Transformers
Language:Jupyter Notebook000
TimeSformer
The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"
Language:PythonMIT000