AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding
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 \model, a 7B parameter VLM trained using parameter-efficient methods on EVUD. Finally, we evaluate \model'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.
Paper Type: Short
Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond
Research Area Keywords: video processing,multimodality,vision question answering
Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources, Data analysis
Languages Studied: English
Submission Number: 1339
Loading