AI Vtuber是一个由 【ChatterBot/ChatGPT/claude/langchain/chatglm/text-gen-webui/闻达/千问/kimi/ollama】 驱动的虚拟主播【Live2D/UE/xuniren】，可以在 【Bilibili/抖音/快手/微信视频号/拼多多/斗鱼/YouTube/twitch/TikTok】 直播中与观众实时互动 或 直接在本地进行聊…

A python package to build AI-powered real-time audio applications

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

Robust Speech Recognition via Large-Scale Weak Supervision

The code for "Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions (AAAI 2022)"

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

Offical implementation of CVPR2024 paper ADA-Track: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association.

Simultaneous object detection and tracking using center points.

Implementation for Learning to Track with Object Permanence

Breaking Modality Gap in RGBT Tracking: Coupled Knowledge Distillation ACMMM2024

整合所有的前端项目案例模板，包括前端炫酷特效页面、海量博客模板、大数据可视化页面、各种导航页面、vue项目模板，React项目模板，UI设计交互，产品研发等。

Transformer related optimization, including BERT, GPT

E2E-MFD-OOD

[ICCV 2023] MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking

Multiple Object Tracking as ID Prediction

High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance

[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

SimpleTrack: Rethinking and Improving a JDE Approach for Multi-Object Tracking

BoT-SORT: Robust Associations Multi-Pedestrian Tracking

SeqTrackv2: Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking

Free football data from StatsBomb

The papers and results about RGB-T fusion tracking

Torchreid: Deep learning person re-identification in PyTorch.

[ICCV-2021] TransReID: Transformer-based Object Re-Identification

[ICCV 2023] ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking

[CVPR2023] MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors