Sparse autoencoders

👋 Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)

Visual Concept Connectome

👋 Influenciae is a Tensorflow Toolbox for Influence Functions

Official implementation of MAIA, A Multimodal Automated Interpretability Agent

Code for the VOST dataset

Chu-Liu-Edmonds maximum spanning algorithm from TurboParser for use within Python

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

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

A latent text-to-image diffusion model

[ECCV 2022] Is Appearance Free Action Recognition Possible?

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

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-…

Geometric Computer Vision Library for Spatial AI

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

Training code for "SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation"

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

Simple key frame annotator for videos of actions

PyTorch implementation of I3D model for video classification, mixed with the CRF smoothing layer for multi-label classification.

Differentiable architecture search for convolutional and recurrent networks