Train Scene Graph Generation for Visual Genome and GQA in PyTorch >= 1.2 with improved zero and few-shot generalization.

PyTorch DataLoader for many VQA datasets

Predicting a subgraph alongside the answer in a graph based VQA model

Vision-Language, Solve GQA(Visual Reasoning in the Real World) dataset.

[GCPR 2023] Zero-shot Translation of Attention Patterns in VQA Models to Natural Language

A RAG-based question-answering system that processes user queries using local documents. It extracts relevant information to answer questions, falling back to a large language model when local sources are insufficient, ensuring accurate and contextual responses.

This is a multimodal model design for the Vision Question Answering (VQA) task. It integrates the Llama2 13B, OWL-ViT, and YOLOv8 models.

LaTeX files for my honours thesis: "Graph Attention Networks for Compositional Visual Question Answering"

Source code for my honours thesis: "Graph Attention Networks for Compositional Visual Question Answering"

A toolkit for vision-language processing to support the increasing popularity of mulit-modal transformer-based models

Case study of multi-layer perceptron and random forest techniques as applied to a subset of the GQA dataset.

Simple Llama architecture LLM in pytorch