Yi Zhu

Use agent to learn agent - A skeleton course on how to design, build, and operate production AI agents

深度学习经典、新论文逐段精读

AutoGluon: AutoML for Image, Text, and Tabular Data

Gluon CV Toolkit

Improving Semantic Segmentation via Video Propagation and Label Relaxation

PyTorch implementation of two-stream networks for video action recognition

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

A Comprehensive Tutorial on Video Modeling

Caffe implementation for "Guided Optical Flow Learning"

TensorFlow implementation for "Guided Optical Flow Learning"

No description.

Text-audio foundation model from Boson AI

🔊 Text-Prompted Generative Audio Model

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

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

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

Better Harness Tools, not merely storing the archive of leaked Claude Code but also make shit things done. Now rewriting in Rust.

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

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

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

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

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

Official DeiT repository

MXNet Blog in Chinese

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

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

ResNeSt: Split-Attention Network

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

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