visual-understanding

There are 3 repositories under visual-understanding topic.

  • bcmi/Causal-VidQA

    [CVPR 2022] A large-scale public benchmark dataset for video question-answering, especially about evidence and commonsense reasoning. The code used in our paper "From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering", CVPR2022.

    Language:Python5210124

  • jaleedkhan/neusire

    NeuSyRE: A Neuro-Symbolic Visual Understanding and Reasoning Framework based on Scene Graph Enrichment

    Language:Jupyter Notebook17104

  • AInnovateLab/ViRED

    [MSN'24] ViRED: Prediction of Visual Relations in Engineering Drawings

    1000