Stable Diffusion web UI

The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"

Implementation of ViViT: A Video Vision Transformer

Official implementation of PVT series

北邮研究生毕业论文模板以及各种校内信息

Pure Pytorch Docker Images.

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

Boosting your Web Services of Deep Learning Applications.

Code Release for MViTv2 on Image Recognition.

Torchreid: Deep learning person re-identification in PyTorch.

This repository host the code for real-time action detection paper

[NeurIPS 2021 Spotlight] Official implementation of Long Short-Term Transformer for Online Action Detection

This is an official implementation of TubeR: Tubelet Transformer for Video Action Detection

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

[ECCV 2020] Actions as Moving Points

[ICCV 2023] SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes

lstm-rnn, seq2seq model and attention-seq2seq model for vessel trajectory prediction.

深度学习入门教程, 优秀文章, Deep Learning Tutorial

[ICCV 2021] MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions

This is an official implementation of our CVPR 2021 paper "Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression" (https://arxiv.org/abs/2104.02300)

A fork of FairMOT used to do vehicle MOT.用于跟踪车辆的多目标跟踪, 自定义数据进行单类别多目标实时跟踪

Paper ibrahim et al, cvpr 2016 - A Hierarchical Deep Temporal Model for Group Activity Recognition -

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

State-of-the-art 2D and 3D Face Analysis Project

Simultaneous object detection and tracking using center points.

BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models

CV integrated project. Including MOT to track cars and pedestrians, object detection and image classification to get license plate content, semantic segmentation to get zebra crossing, tradition me…

A tutorial for training YOLOv3 to detect traffic lights using BOSCH small traffic light dataset.