The official implementation for the paper [ODTrack: Online Dense Temporal Token Learning for Visual Tracking].

Video Grounding and Captioning

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

This repository contains the necessary tools for RGBT tracking, including datasets（GTOT, RGBT234, LasHeR）, evaluation tools, visualization tools, and results of existing works.

[NeurIPS 2024] VastTrack: Vast Category Visual Object Tracking

7-Zip

MV-VTON: Multi-View Virtual Try-On with Diffusion Models

[IEEE TCYB 2023] The first large-scale tracking dataset by fusing RGB and Event cameras.

A Large-scale High-diversity Benchmark for RGBT Tracking

Dataset and Code for the paper "DepthTrack: Unveiling the Power of RGBD Tracking" (ICCV2021), and "Depth-only Object Tracking" (BMVC2021)

[CVPR23] Visual Prompt Multi-Modal Tracking

The official implementation for the CVPR 2023 paper Joint Visual Grounding and Tracking with Natural Language Specification.

Paint by Example: Exemplar-based Image Editing with Diffusion Models

Diffusion Model-Based Image Editing: A Survey (arXiv)

A visual object tracking paper list, articles related to visual object tracking have been documented.

Diffusion-TTA improves pre-trained discriminative models such as image classifiers or segmentors using pre-trained generative models.

Diffusion Feedback Helps CLIP See Better

Code implementation of our NeurIPS 2023 paper: Vocabulary-free Image Classification

An open source implementation of CLIP.

This repository contains the official implementation of the research paper, "MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training" CVPR 2024

Code Release of F-LMM: Grounding Frozen Large Multimodal Models

[ECCV2024] This is an official implementation for "PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model"

[NeurIPS'24 Spotlight] EVE: Encoder-Free Vision-Language Models

[ICCV 2023] VPD is a framework that leverages the high-level and low-level knowledge of a pre-trained text-to-image diffusion model to downstream visual perception tasks.

[NeurIPS'23] Emergent Correspondence from Image Diffusion

Refine high-quality datasets and visual AI models

VisionLLM Series

TypeChat is a library that makes it easy to build natural language interfaces using types.

A personal investigative project to track the latest progress in the field of multi-modal object tracking.