Geometric Computer Vision Library for Spatial AI

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Differentiable architecture search for convolutional and recurrent networks

Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch

Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA

Sparse autoencoders

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

[ECCV 2022] Is Appearance Free Action Recognition Possible?

👋 Influenciae is a Tensorflow Toolbox for Influence Functions

Official implementation of MAIA, A Multimodal Automated Interpretability Agent

Tracking through Containers and Occluders in the Wild (CVPR 2023) - Official Implementation

Code for the VOST dataset

Explaining Deep Convolutional Neural Networks via Unsupervised Visual-Semantic Filter Attention (CVPR 2022)

Visual Concept Connectome

Simple key frame annotator for videos of actions