A resource list and performance benchmark for blind video quality assessment (BVQA) models on user-generated content (UGC) datasets. [IEEE TIP'2021] "UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content", Zhengzhong Tu, Yilin Wang, Neil Birkbeck, Balu Adsumilli, Alan C. Bovik

SSG-VQA is a Visual Question Answering (VQA) dataset on laparoscopic videos providing diverse, geometrically grounded, unbiased and surgical action-oriented queries generated using scene graphs.

The Easy Visual Question Answering dataset.

Gamified Adversarial Prompting (GAP): Crowdsourcing AI-weakness-targeting data through gamification. Boost model performance with community-driven, strategic data collection

Counterfactual Reasoning VQA Dataset

VQA-Med 2021

CLEVR3D Dataset: Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulation

Multi-page document understanding and VQA using OCR-free method

B.Sc. Final Project: LXMERT Model Compression for Visual Question Answering.

This repo implements attention networks for visual question answering

How well do the GPT-4V, Gemini Pro Vision, and Claude 3 Opus models perform zero-shot vision tasks on data structures?

Investigation on VQA dataset. TensorFlow is utilized for the implementation of a solution based on CNN and RNN architectures plus some ideas such as Attention and Positional features.

Grid features extraction for ICCV 2021 paper "TRAR: Routing the Attention Spans in Transformers for Visual Question Answering"

VQA Challenge - hosted on Hasura using Flask

Medical Report Generation And VQA (Adapting XrayGPT to Any Modality)

An Automated Pipeline for Constructing a Vietnamese VQA-NLE Dataset (ICISN 2025)

Streamlit app for demonstrating multi-modal(vision+language) modelling in Pytorch.