Lists (7)
Sort Name ascending (A-Z)
Starred repositories
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
RTMPose series (RTMPose, DWPose, RTMO, RTMW) without mmcv, mmpose, mmdet etc.
Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"
手机品牌型号汇总 | Mobile Models | This repository is licensed under CC BY-NC-SA 4.0
Code release for book "Efficient Training in PyTorch"
SOT画图工具(主要是LaSOT数据集),可以同时画多个跟踪器的跟踪框、蜘蛛网图、花花绿绿曲线图
You can draw the corresponding bounding box into the image and save it according to the result file (txt format) run by the tracker.Moreover, the author will update some of the problems in the pyso…
This repo aims to include materials (papers, codes, slides) about SAM2 (segment anything in images and videos). We are continuously improving the project. Welcome to PR the works (papers, repos) th…
[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence
HunyuanVideo: A Systematic Framework For Large Video Generation Model
Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"
Paper list for single object tracking (State-of-the-art SOT trackers)
[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.
本项目旨在分享大模型相关技术原理以及实战经验(大模型工程化、大模型应用落地)
[CVPR 2025] Multiple Object Tracking as ID Prediction
T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!
Refine high-quality datasets and visual AI models
Efficient Visual Tracking with Exemplar Transformers [WACV2023]
STMTrack: Template-free Visual Tracking with Space-time Memory Networks
SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.
[TPAMI2024 / ICME2023] Codes for my paper "Body-Part Joint Detection and Association via Extended Object Representation"
Whose Hands Are These? Hand Detection and Hand-Body Association in the Wild, CVPR 2022
[ICCV 2023] BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion