-
University of Washington; Microsoft
- Seattle, WA
Highlights
- Pro
Stars
Read Google Cloud Storage, Azure Blobs, and local paths with the same interface
[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"
Making large AI models cheaper, faster and more accessible
Toolkit for Elevater Benchmark
Refine high-quality datasets and visual AI models
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone
An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"
MLP-Like Vision Permutator for Visual Recognition (PyTorch)
Evaluation code and codalab submission examples for the VALUE benchmark.
MERLOT: Multimodal Neural Script Knowledge Models
[CVPR 2021 Best Student Paper Honorable Mention, Oral] Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning on image-text and video-text tasks.
Video Feature Extraction Code for EMNLP 2020 paper "HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training"
A one-stop shop for YouCook2 info such as leaderboard and recent advances on (cooking) video retrieval and captioning.
[EMNLP 2020] What is More Likely to Happen Next? Video-and-Language Future Event Prediction
Research Code for NeurIPS 2020 Spotlight paper "Large-Scale Adversarial Training for Vision-and-Language Representation Learning": UNITER adversarial training part
Research Code for NeurIPS 2020 Spotlight paper "Large-Scale Adversarial Training for Vision-and-Language Representation Learning": LXMERT adversarial training part
Facebook AI Research's Automatic Speech Recognition Toolkit
PyTorch bottom-up attention with Detectron2
Research code for EMNLP 2020 paper "HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training"
Research code for ECCV 2020 paper "UNITER: UNiversal Image-TExt Representation Learning"
A curated list of awesome self-supervised methods
Must-read Papers on Textual Adversarial Attack and Defense
lichengunc / detectron2
Forked from facebookresearch/detectron2Detectron2 is FAIR's next-generation research platform for object detection and segmentation.
pytorch implementation for Patient Knowledge Distillation for BERT Model Compression
Research Code for ICCV 2019 paper "Relation-aware Graph Attention Network for Visual Question Answering"