Stars
[ICCV 2025] Implementation for Describe Anything: Detailed Localized Image and Video Captioning
[NeurIPS 2025] YOLOv12: Attention-Centric Real-Time Object Detectors
[ICCV 2023] MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking
The official code of "Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark"
A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
The official pytorch implementation of our AAAI 2024 paper "Unifying Visual and Vision-Language Tracking via Contrastive Learning"
[ECCV 2024] Elysium: Exploring Object-level Perception in Videos via MLLM
[NeurIPS 2024] VastTrack: Vast Category Visual Object Tracking
A vision-language tracking paper list, articles related to visual language tracking have been documented.
[CVPR 2022] Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding
[TMM 2023] Self-paced Curriculum Adapting of CLIP for Visual Grounding.
[NeurIPS2024] - SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion
Bag of Tricks and A Strong Baseline for Deep Person Re-identification
SOTA Re-identification Methods and Toolbox
code for CVPR2024 paper: DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction
A Confidence-Aware Matching Strategy For Generalized Multi-Object Tracking
MOT using deepsort and yolov3 with pytorch
[CVPR 2025] Multiple Object Tracking as ID Prediction
Code for RA-L paper "PKF: Probabilistic Data Association Kalman Filter for Multi-Object Tracking"
[CVPR 2024] iKUN: Speak to Trackers without Retraining
Attentive Generative Adversarial Network for Raindrop Removal from A Single Image (CVPR 2018)
[CVPR2022] DanceTrack: Multiple Object Tracking in Uniform Appearance and Diverse Motion