AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding

Alessandro Suglia, Claudio Greco, Katie Baker, Jose Part, Ioannis Papaioannou, Arash Eshghi, Ioannis Konstas, Oliver Lemon


Abstract
AI personal assistants deployed via robots or wearables require embodied understanding to collaborate with humans effectively. However, current Vision-Language Models (VLMs) primarily focus on third-person view videos, neglecting the richness of egocentric perceptual experience. To address this gap, we propose three key contributions. First, we introduce the Egocentric Video Understanding Dataset (EVUD) for training VLMs on video captioning and question answering tasks specific to egocentric videos. Second, we present , a 7B parameter VLM trained using parameter-efficient methods on EVUD. Finally, we evaluate ‘s capabilities on OpenEQA, a challenging benchmark for embodied video question answering. Our model achieves state-of-the-art performance, outperforming open-source models including strong Socratic models using GPT-4 as a planner by 3.6%.Additionally, we outperform Claude 3 and Gemini Pro Vision 1.0 and showcase competitive results compared to Gemini Pro 1.5 and GPT-4V, even surpassing the latter in spatial reasoning. This research paves the way for building efficient VLMs that can be deployed in robots or wearables, leveraging embodied video understanding to collaborate seamlessly with humans in everyday tasks, contributing to the advancement of next-generation Embodied AI.
Anthology ID:
2024.findings-emnlp.649
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11101–11122
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.649
DOI:
Bibkey:
Cite (ACL):
Alessandro Suglia, Claudio Greco, Katie Baker, Jose Part, Ioannis Papaioannou, Arash Eshghi, Ioannis Konstas, and Oliver Lemon. 2024. AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11101–11122, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding (Suglia et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.649.pdf