Popular repositories

1. mcan-vqa mcan-vqa Public

   Deep Modular Co-Attention Networks for Visual Question Answering

   Python 432 88

2. openvqa openvqa Public

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

   Python 308 64

3. bottom-up-attention.pytorch bottom-up-attention.pytorch Public

   A PyTorch reimplementation of bottom-up-attention models

   Jupyter Notebook 287 74

4. prophet prophet Public

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

   Python 260 27

5. imp imp Public

   a family of multimodal small language models

   Python 115 13

6. activitynet-qa activitynet-qa Public

   An VideoQA dataset based on the videos from ActivityNet

   Python 55 9