shehanmunasinghe / AI701-Project-G02

Extending Video-based Large Multimodal Models

Shehan Munasinghe, Rusiru Thushara, Mohamed Insaf Ismithdeen

Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE

{shehan.munasinghe, rusiru.achchige, mohamed.ismithdeen}@mbzuai.ac.ae

AI701 Project : Group ID = G-02

---

1 - Setup and Demo

See here for instrunctions on insallation and running the CLI demo.

2 - Training

See here for more details.

3 - Quantitative Evaluation Framework for Video-based Conversational Models

See here for more details.

4 - Quantitative Evaluation of Conversation-based Video Spatial Grounding

See here for more details.