EgoLife: Towards Egocentric Life Assistant
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918328186961920 |
|---|---|
| author | Yang, Jingkang Liu, Shuai Guo, Hongming Dong, Yuhao Zhang, Xiamengwei Zhang, Sicheng Wang, Pengyun Zhou, Zitang Xie, Binzhu Wang, Ziyue Ouyang, Bei Lin, Zhengyu Cominelli, Marco Cai, Zhongang Zhang, Yuanhan Zhang, Peiyuan Hong, Fangzhou Widmer, Joerg Gringoli, Francesco Yang, Lei Li, Bo Liu, Ziwei |
| author_facet | Yang, Jingkang Liu, Shuai Guo, Hongming Dong, Yuhao Zhang, Xiamengwei Zhang, Sicheng Wang, Pengyun Zhou, Zitang Xie, Binzhu Wang, Ziyue Ouyang, Bei Lin, Zhengyu Cominelli, Marco Cai, Zhongang Zhang, Yuanhan Zhang, Peiyuan Hong, Fangzhou Widmer, Joerg Gringoli, Francesco Yang, Lei Li, Bo Liu, Ziwei |
| contents | We introduce EgoLife, a project to develop an egocentric life assistant that accompanies and enhances personal efficiency through AI-powered wearable glasses. To lay the foundation for this assistant, we conducted a comprehensive data collection study where six participants lived together for one week, continuously recording their daily activities - including discussions, shopping, cooking, socializing, and entertainment - using AI glasses for multimodal egocentric video capture, along with synchronized third-person-view video references. This effort resulted in the EgoLife Dataset, a comprehensive 300-hour egocentric, interpersonal, multiview, and multimodal daily life dataset with intensive annotation. Leveraging this dataset, we introduce EgoLifeQA, a suite of long-context, life-oriented question-answering tasks designed to provide meaningful assistance in daily life by addressing practical questions such as recalling past relevant events, monitoring health habits, and offering personalized recommendations. To address the key technical challenges of (1) developing robust visual-audio models for egocentric data, (2) enabling identity recognition, and (3) facilitating long-context question answering over extensive temporal information, we introduce EgoButler, an integrated system comprising EgoGPT and EgoRAG. EgoGPT is an omni-modal model trained on egocentric datasets, achieving state-of-the-art performance on egocentric video understanding. EgoRAG is a retrieval-based component that supports answering ultra-long-context questions. Our experimental studies verify their working mechanisms and reveal critical factors and bottlenecks, guiding future improvements. By releasing our datasets, models, and benchmarks, we aim to stimulate further research in egocentric AI assistants. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_03803 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EgoLife: Towards Egocentric Life Assistant Yang, Jingkang Liu, Shuai Guo, Hongming Dong, Yuhao Zhang, Xiamengwei Zhang, Sicheng Wang, Pengyun Zhou, Zitang Xie, Binzhu Wang, Ziyue Ouyang, Bei Lin, Zhengyu Cominelli, Marco Cai, Zhongang Zhang, Yuanhan Zhang, Peiyuan Hong, Fangzhou Widmer, Joerg Gringoli, Francesco Yang, Lei Li, Bo Liu, Ziwei Computer Vision and Pattern Recognition We introduce EgoLife, a project to develop an egocentric life assistant that accompanies and enhances personal efficiency through AI-powered wearable glasses. To lay the foundation for this assistant, we conducted a comprehensive data collection study where six participants lived together for one week, continuously recording their daily activities - including discussions, shopping, cooking, socializing, and entertainment - using AI glasses for multimodal egocentric video capture, along with synchronized third-person-view video references. This effort resulted in the EgoLife Dataset, a comprehensive 300-hour egocentric, interpersonal, multiview, and multimodal daily life dataset with intensive annotation. Leveraging this dataset, we introduce EgoLifeQA, a suite of long-context, life-oriented question-answering tasks designed to provide meaningful assistance in daily life by addressing practical questions such as recalling past relevant events, monitoring health habits, and offering personalized recommendations. To address the key technical challenges of (1) developing robust visual-audio models for egocentric data, (2) enabling identity recognition, and (3) facilitating long-context question answering over extensive temporal information, we introduce EgoButler, an integrated system comprising EgoGPT and EgoRAG. EgoGPT is an omni-modal model trained on egocentric datasets, achieving state-of-the-art performance on egocentric video understanding. EgoRAG is a retrieval-based component that supports answering ultra-long-context questions. Our experimental studies verify their working mechanisms and reveal critical factors and bottlenecks, guiding future improvements. By releasing our datasets, models, and benchmarks, we aim to stimulate further research in egocentric AI assistants. |
| title | EgoLife: Towards Egocentric Life Assistant |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.03803 |