Vision and Language Group@ MIL

Deep Modular Co-Attention Networks for Visual Question Answering

MILVLG

A lightweight, scalable, and general framework for visual question answering research

MILVLG

A PyTorch reimplementation of bottom-up-attention models

MILVLG

An VideoQA dataset based on the videos from ActivityNet

MILVLG

Deep Multimodal Neural Architecture Search

MILVLG

A PyTorch implementation of the paper Multimodal Transformer with Multiview Visual Representation for Image Captioning

MILVLG

ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration

MILVLG

Implementation of CVPR 2023 paper "Prompting Large Language Models with Answer Heuristics for Knowledge-based Visual Question Answering".

MILVLG

a family of multimodal small language models

MILVLG

MILVLG