JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.

This project uses a variety of advanced voiceprint recognition models such as EcapaTdnn, ResNetSE, ERes2Net, CAM++, etc. It is not excluded that more models will be supported in the future. At the …

face detection face recognition包含人脸检测(retinaface,yolov5face,yolov7face,yolov8face),人脸检测跟踪(ByteTracker)，人脸角度计算（Face_Angle）人脸矫正(Face_Aligner)，人脸识别(Arcface)，口罩检测(MaskRecognitiion)，年龄性别检测(Gender_age)，静…

🔊 Awesome list for Whisper — an open-source AI-powered speech recognition system developed by OpenAI

An open source library for face detection in images. The face detection speed can reach 1000FPS.

The official code of "Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark"

Official PyTorch implementation of UniHCP

Official repository for CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video ta…

The official code of "PLIP: Language-Image Pre-training for Person Representation Learning"

ACM MM 2021: 'Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection'

VCED 可以通过你的文字描述来自动识别视频中相符合的片段进行视频剪辑。该项目基于跨模态搜索与向量检索技术搭建，通过前后端分离的模式，帮助你快速的接触新一代搜索技术。

kmeans clustering with multi-GPU capabilities

Efficient facial landmark detector

Code for CVPR 2022 paper "Scene Consistency Representation Learning for Video Scene Segmentation"

Paper list on Pedestrian Attribute Recognition (PAR) and related tasks (Pattern Recognition 2021)

Automated shot detection software

A treasure chest for visual classification and recognition powered by PaddlePaddle

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

A Simple PointPillars PyTorch Implenmentation for 3D Lidar(KITTI) Detection.

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

Benchmarking Panoptic Scene Graph Generation (PSG), ECCV'22

A simple baseline implemented in PyTorch for pedestrian attribute recognition task, evaluating on Market-1501 and DukeMTMC-reID dataset.

The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation