The Web framework for perfectionists with deadlines.

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

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

Image processing in Python

Deep Learning Tutorial notes and code. See the wiki for more info.

Lightweight library to build and train neural networks in Theano

A deep learning library for video understanding research.

A Simple and Versatile Framework for Object Detection and Instance Recognition

Hiera: A fast, powerful, and simple hierarchical vision transformer.

Official Open Source code for "Scaling Language-Image Pre-training via Masking"

Code Release for MViTv2 on Image Recognition.

Quickly download, clean up, and install public datasets into a database management system

Kayak is a library for automatic differentiation with applications to deep neural networks.

Appearance-and-Relation Networks

Efficient 3D Backbone Network for Temporal Modeling

MXNet Code For Demystifying Neural Style Transfer (IJCAI 2017)

FBN: Factorized Bilinear Models for Image Recognition (ICCV 2017)

Code accompanying Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos (CVPR 2021)