illusa Goto Github PK

3d-pose-baseline

A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.

3dmppe_posenet_release

Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019

auto-gpt

An experimental open-source attempt to make GPT-4 fully autonomous.

chineseocr_lite

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

d2l-zh

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被60多个国家的400多所大学用于教学。

detectandtrack

The implementation of an algorithm presented in the CVPR18 paper: "Detect-and-Track: Efficient Pose Estimation in Videos"

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

drl-ice-hockey

fitting_human_smpl_model

Estimating human pose and shape by fitting SMPL model with the dense points position and key points position

githubtest

jarvis

JARVIS, a system to connect LLMs with ML community

lhy_machine_learning

李宏毅2021春季机器学习课程课件及作业

mixsort

[ICCV2023] MixSort: The Customized Tracker in SportsMOT

narya

The Narya API allows you track soccer player from camera inputs, and evaluate them with an Expected Discounted Goal (EDG) Agent. This repository contains the implementation of the flowing paper https://arxiv.org/abs/2101.05388. We also make available all of our pretrained agents, and the datasets we used as well.

paddlesports

pytorch_stacked_hourglass

Pytorch implementation of "Stacked Hourglass Networks for Human Pose Estimation"

segment-and-track-anything

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.

soccer-analytics-resources

Collection of references, datasets and software libraries for soccer analytics.

soccer.sys

socceraction

Convert soccer event stream data to SPADL and value player actions using VAEP or xT

soccerontable

Upconverting YouTube soccer videos in 3D for viewing in AR/VR devices.Soccer On Your Tabletop

track-anything

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

videopose3d

Efficient 3D human pose estimation in video using 2D keypoint trajectories

visual-chatgpt

Official repo for the paper: Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models

yolov5_deepsort_pytorch

Real-time multi-object tracker using YOLO v5 and deep sort