LAVIS - A One-stop Library for Language-Vision Intelligence

Video Graph Transformer for Video Question Answering (ECCV'22)

A list of Human-Object Interaction Learning.

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

[TPAMI Special Issue on ICCV 2021 Best Papers, Oral] Just Ask: Learning to Answer Questions from Millions of Narrated Videos

Shanghai Jiao Tong University XeLaTeX Thesis Template

Code release for "MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound"

Video Swin Transformer - PyTorch

Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

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

Person Search with Natural Language Description

Grid features pre-training code for visual question answering

Video Generation from Single Semantic Label Map

my public website

novel deep learning research works with PaddlePaddle

proof of concept for a transformer-based time series prediction model

A curated list of research papers in Vision-Language Navigation (VLN)

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

A curated list of awesome anomaly detection resources

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System