Prompt Tuning with Soft Context Sharing for Vision-Language Models

This is the repository for paper UniQA

Repository for Multilingual-VQA task created during HuggingFace JAX/Flax community week.

ECCV2016 - fine-grained photo aesthetics rating with interpretability

An expert benchmark aiming to comprehensively evaluate the aesthetic perception capacities of MLLMs.

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Must-read Papers on pre-trained language models.

Must-read papers on prompt-based tuning for pre-trained language models.

👁️ 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...

🔥[ICCV 2023, Official Code] for paper "Thinking Image Color Aesthetics Assessment: Models, Datasets and Benchmarks". Official Weights and Demos provided. 首个面向图像色彩主观美学评估的数据集、算法和benchmark.

Understanding Deep Learning - Simon J.D. Prince

Aesthetically-Relevant-Image-Captioning

Image Caption metrics: Bleu、Cider、Meteor、Rouge、Spice

Large Scale Image Aesthetics Evaluation

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

Research code for ECCV 2020 paper "UNITER: UNiversal Image-TExt Representation Learning"

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

⏬ Download AVA dataset (A Large-Scale Database for Aesthetic Visual Analysis)

A Scalable Incremental Learning Framework for Blind Image Quality Assessment

Code for Remember and Reuse: Cross-Task Blind Image Quality Assessment via Relevance-aware Incremental Learning (ACM Multimedia 2021)

Code for the paper "Understanding Aesthetics with Language: A Photo Critique Dataset for Aesthetic Assessment"

Datasets, Transforms and Models specific to Computer Vision

Measures and metrics for image2image tasks. PyTorch.

[CVPRW 2022] Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network

视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.