Open-source alternatives to TVQA

This is the official implementation of our ICLR 2018 paper Learning to Count Objects in Natural Images for Visual Question Answering0 in PyTorch1. In this paper, we introduce a counting component that allows VQA models to count objects from an attention map, achieving state-of-the-art…

This is the code for the paper

Pythia is a multimodal research framework and distributed training system designed for building, training, and evaluating large models that combine visual and linguistic data. It provides a modular environment for developing vision-language models, focusing on the integration of image and text inputs into shared feature representations. The framework utilizes a modular architecture that decouples model building blocks into interchangeable components, allowing for flexible configuration of vision and language modules. It includes a benchmark suite for executing reference models against standar

Code and Data for ManyModalQA: Modality Disambiguation and QA over Diverse Inputs

The code base for TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation Jun Wang, Mingfei Gao, Yuqian Hu, Ramprasaath R. Selvaraju, Chetan Ramaiah, Ran Xu, Joseph F. JaJa, Larry S. Davis

Probabilistic Neural-symbolic Models

Neural-symbolic visual question answering

This repository contains the code for the following paper:

A challenging Video Question Answering (VQA) Benchmark based on real-world traffic scenes.