From My View to Yours: Ego-to-Exo Transfer in VLMs for Understanding Activities of Daily Living
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_ | 1866909963507466240 |
|---|---|
| author | Reilly, Dominick Govind, Manish Kumar Xue, Le Das, Srijan |
| author_facet | Reilly, Dominick Govind, Manish Kumar Xue, Le Das, Srijan |
| contents | Vision Language Models (VLMs) have achieved strong performance across diverse video understanding tasks. However, their viewpoint invariant training limits their ability to understand egocentric properties (e.g., human object interactions) from exocentric video observations. This limitation is critical for many applications, such as Activities of Daily Living (ADL) monitoring, where the understanding of egocentric properties is essential, and egocentric cameras are impractical to deploy. To address this limitation, we propose Ego2ExoVLM, a VLM that learns to infer egocentric properties from exocentric videos by leveraging time-synchronized ego-exo videos during training. Ego2ExoVLM accomplishes this through the use of two components: Ego2Exo Sequence Distillation, which transfers knowledge from an egocentric teacher to an exocentric student, and Ego Adaptive Visual Tokens, designed to enhance the effectiveness of this knowledge transfer. To measure this capability, we introduce Ego-in-Exo Perception, a benchmark of 3.9K questions curated to explicitly measure the understanding of egocentric properties from exocentric videos. Ego2ExoVLM is evaluated on 10 tasks across Ego-in-Exo Perception and existing ADL benchmarks, achieving state-of-the-art results on the ADL-X benchmark suite and outperforming strong baselines on our proposed benchmark. All code, models, and data will be released at https://github.com/dominickrei/EgoExo4ADL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_05711 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From My View to Yours: Ego-to-Exo Transfer in VLMs for Understanding Activities of Daily Living Reilly, Dominick Govind, Manish Kumar Xue, Le Das, Srijan Computer Vision and Pattern Recognition Vision Language Models (VLMs) have achieved strong performance across diverse video understanding tasks. However, their viewpoint invariant training limits their ability to understand egocentric properties (e.g., human object interactions) from exocentric video observations. This limitation is critical for many applications, such as Activities of Daily Living (ADL) monitoring, where the understanding of egocentric properties is essential, and egocentric cameras are impractical to deploy. To address this limitation, we propose Ego2ExoVLM, a VLM that learns to infer egocentric properties from exocentric videos by leveraging time-synchronized ego-exo videos during training. Ego2ExoVLM accomplishes this through the use of two components: Ego2Exo Sequence Distillation, which transfers knowledge from an egocentric teacher to an exocentric student, and Ego Adaptive Visual Tokens, designed to enhance the effectiveness of this knowledge transfer. To measure this capability, we introduce Ego-in-Exo Perception, a benchmark of 3.9K questions curated to explicitly measure the understanding of egocentric properties from exocentric videos. Ego2ExoVLM is evaluated on 10 tasks across Ego-in-Exo Perception and existing ADL benchmarks, achieving state-of-the-art results on the ADL-X benchmark suite and outperforming strong baselines on our proposed benchmark. All code, models, and data will be released at https://github.com/dominickrei/EgoExo4ADL. |
| title | From My View to Yours: Ego-to-Exo Transfer in VLMs for Understanding Activities of Daily Living |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.05711 |