bryanyzhu

two-stream-pytorch

PyTorch implementation of two-stream networks for video action recognition

Hidden-Two-Stream

Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"

Video-Tutorial-CVPR2020

A Comprehensive Tutorial on Video Modeling

GuidedNet

Caffe implementation for "Guided Optical Flow Learning"

deepOF

TensorFlow implementation for "Guided Optical Flow Learning"

paper-reading

深度学习经典、新论文逐段精读

tiny-ucf101

autogluon

AutoGluon: AutoML for Image, Text, and Tabular Data

semantic-segmentation

Improving Semantic Segmentation via Video Propagation and Label Relaxation

SlowFast

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

Video-Swin-Transformer

This is an official implementation for "Video Swin Transformers".

ViLT

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

bark

🔊 Text-Prompted Generative Audio Model

bigdetection

BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training

blog

MXNet Blog in Chinese

CorrFlow

Self-supervised Learning for Video Correspondence Flow (BMVC 2019)

deit

Official DeiT repository

detectron2

Detectron2 is FAIR's next-generation platform for object detection and segmentation.

Detic

Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".

digital_video_introduction

A hands-on introduction to video technology: image, video, codec (av1, vp9, h265) and more (ffmpeg encoding).

gluon-cv

Gluon CV Toolkit

PuLID

[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

ResNeSt

ResNeSt: Split-Attention Network

stable-diffusion-videos

Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts

web-data

The repo to host all the web data including images for documents in dmlc projects.