stdKonjac

mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

DALI

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

nccl

Optimized primitives for collective multi-GPU communication

RepDistiller

[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

fvcore

Collection of common code that's shared among different research projects in FAIR computer vision team.

decord

An efficient video loader for deep learning with smart shuffling that's super easy to digest

V2Ray-Desktop

最优雅的跨平台代理客户端，支持Shadowsocks(R)，V2Ray和Trojan协议。The most elegant cross-platform proxy GUI client that supports Shadowsocks(R), V2Ray, and Trojan. Built with Qt5 and QML2.

PaddleVideo

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video tagging and sport action detection.

VideoMAE

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

moco-v3

PyTorch implementation of MoCo v3 https//arxiv.org/abs/2104.02057

VideoX

VideoX: a collection of video cross-modal models

VL-BERT

Code for ICLR 2020 paper "VL-BERT: Pre-training of Generic Visual-Linguistic Representations".

omnivore

Omnivore: A Single Model for Many Visual Modalities

ActionCLIP

This is the official implement of paper "ActionCLIP: A New Paradigm for Action Recognition"

UniCL

[CVPR 2022] Official code for "Unified Contrastive Learning in Image-Text-Label Space"

frozen-in-time

Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval [ICCV'21]

LearningToCountEverything

bit-diffusion

Implementation of Bit Diffusion, Hinton's group's attempt at discrete denoising diffusion, in Pytorch

all-in-one

[CVPR2023] All in One: Exploring Unified Video-Language Pre-training

pims

Python Image Sequence: Load video and sequential images in many formats with a simple, consistent interface.

merlot

MERLOT: Multimodal Neural Script Knowledge Models

deffcode

A cross-platform High-performance FFmpeg based Real-time Video Frames Decoder in Pure Python 🎞️⚡

BMVCTemplate

Paper template and author instructions for BMVC

merlot_reserve

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

singularity

[ACL 2023] Official PyTorch code for Singularity model in "Revealing Single Frame Bias for Video-and-Language Learning"

TVLT

PyTorch code for “TVLT: Textless Vision-Language Transformer” (NeurIPS 2022 Oral)

qb-norm

Cross Modal Retrieval with Querybank Normalisation

svo_probes

The SVO-Probes Dataset for Verb Understanding

CKMN

DALI

A library containing both highly optimized building blocks and an execution engine for data pre-processing in deep learning applications