[Preprint] AIPO: Improving Training Objective for Iterative Preference Optimization

An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"

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

Official Implementation of CVPR24 highligt paper: Matching Anything by Segmenting Anything

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

🔥中文 prompt 精选🔥，ChatGPT 使用指南，提升 ChatGPT 可玩性和可用性！🚀

一个用于在 macOS 上平滑你的鼠标滚动效果或单独设置滚动方向的小工具, 让你的滚轮爽如触控板 | A lightweight tool used to smooth scrolling and set scroll direction independently for your mouse on macOS

Maintain a consistent development environment.

Using HRNet for CVWC 2019 Tiger Pose Track Challenge.

Offical PyTorch implementation of Clover: Towards A Unified Video-Language Alignment and Fusion Model (CVPR2023)

A deep learning training framework/template for vision and language tasks based on Hydra

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

[ECCV 2024] Beyond MOT: Semantic Multi-Object Tracking

[CVPR2023] Referring Multi-Object Tracking

[ECCV 2024] Beyond MOT: Semantic Multi-Object Tracking

[T-NNLS 2024] AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributes

【2024年新版】国科大 陈云霁 智能计算系统AICS实验代码

Global Tracking Transformers, CVPR 2022

Compare performances of algorithms on Objcet Tracking Benchmarks (SOT/MOT...)

OVTrack: Open-Vocabulary Multiple Object Tracking [CVPR 2023]

Code for the paper "Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization", ICCV 2019, https://arxiv.org/abs/1910.04562.