yhzhai Goto Github PK

atom

[ACM MM 2023] Official implementation of paper "Language-guided Human Motion Synthesis with Atomic Actions".

basnet-pytorch

Pytorch Implementation of 'Background Suppression Network for Weakly-supervised Temporal Action Localization' (AAAI-20)

bmn-boundary-matching-network

A pytorch-version implementation codes of paper: "BMN: Boundary-Matching Network for Temporal Action Proposal Generation", which is accepted in ICCV 2019.

bsn-boundary-sensitive-network.pytorch

Codes of our paper: "BSN: Boundary Sensitive Network for Temporal Action Proposal Generation"

cgdl-for-open-set-recognition

Code for CVPR2020 paper: Conditional Gaussian Distribution Learning for Open Set Recognition

cost-volume-model

Temporal Segment Networks (TSN) in PyTorch

deepul

depthstillation

Demo code for paper "Learning optical flow from still images", CVPR 2021.

detad

This repository is intended to host the diagnosis tool for analyzing temporal action localization algorithms. This tool is first presented as part of our DETAD paper.

detr

End-to-End Object Detection with Transformers

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

dotfiles

endoassistant

gpu-load-watcher

Simple script for watching GPU usage on both system-wide and per-user basis.

hacs-dataset

HACS: Human Action Clips and Segments Dataset

ict_deepfake

idol

[ECCV 2024] IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation

matlab-forensics

MATLAB implementations of popular Image Forensic algorithms

maze

mcm

Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation

mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

open_clip

An open source implementation of CLIP.

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

poseformerv2

The project is an official implementation of our paper "PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation".

prodl

[Doc] Productive Deep Learner

raft

selfblendedimages

[CVPR 2022 Oral] Detecting Deepfakes with Self-Blended Images https://arxiv.org/abs/2204.08376

sladd

Official code for Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection (CVPR 2022 oral)

sleek-beamer

LaTeX sleek beamer template

soar

[ICCV 2023] Official implementation of paper "SOAR: Scene-debiasing Open-set Action Recognition".