ConceptFusion

This is the repository that contains source code for the paper Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion.

Should you find our work useful, please cite

@article{rawal2024dissect,
  author    = {Rawal, {Ishaan Singh} and Matyasko, Alexander and Jaiswal, Shantanu and Fernando, Basura and Tan, Cheston},
  title     = {{Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion}},
  booktitle   = {International Conference on Machine Learning},
  year      = {2024},
  organization  = {PMLR}
}

An abridged version of our work was presented at NeurIPS 2023 XAI in Action Workshop. It can be found here.

@inproceedings{rawal2023videoqa,
  title={{Are VideoQA Models Truly Multimodal?}},
  author={Rawal, Ishaan and Jaiswal, Shantanu and Fernando, Basura and Tan, Cheston},
  booktitle={XAI in Action: Past, Present, and Future Applications},
  year={2023}
}

Website License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

If you use this, we ask that you link back to the original source, i.e., the Nerfies website template.