Fine-tuning InternVL-3.5-1B with different PEFT strategies: LoRA/QLoRA/full-tuning on MVBench dataset

[CVPR 2025] Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution

Parsing-free RAG supported by VLMs

CVPR25(Highlight)-Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Prior

Refine high-quality datasets and visual AI models

ECCV24 - Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance

ReID in Real Haze: Learning Robust Vehicle Re-identification in Real Hazy Scenes using Semi-supervised Learning --ECCV2022

Awesome Crowd Counting

AAAI22-SJDL-Vehicle: Semi-supervised Joint Defogging Learning for Foggy Vehicle Re-identification

Histology images query (unsupervised)

(Competition) 6th -- Scene-Text-Detection-and-Recognition.