PARSE-Ego4D: Personal Action Recommendation Suggestions for Egocentric Videos
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913444500865024 |
|---|---|
| author | Abreu, Steven Do, Tiffany D. Ahuja, Karan Gonzalez, Eric J. Payne, Lee McDuff, Daniel Gonzalez-Franco, Mar |
| author_facet | Abreu, Steven Do, Tiffany D. Ahuja, Karan Gonzalez, Eric J. Payne, Lee McDuff, Daniel Gonzalez-Franco, Mar |
| contents | Intelligent assistance involves not only understanding but also action. Existing ego-centric video datasets contain rich annotations of the videos, but not of actions that an intelligent assistant could perform in the moment. To address this gap, we release PARSE-Ego4D, a new set of personal action recommendation annotations for the Ego4D dataset. We take a multi-stage approach to generating and evaluating these annotations. First, we used a prompt-engineered large language model (LLM) to generate context-aware action suggestions and identified over 18,000 action suggestions. While these synthetic action suggestions are valuable, the inherent limitations of LLMs necessitate human evaluation. To ensure high-quality and user-centered recommendations, we conducted a large-scale human annotation study that provides grounding in human preferences for all of PARSE-Ego4D. We analyze the inter-rater agreement and evaluate subjective preferences of participants. Based on our synthetic dataset and complete human annotations, we propose several new tasks for action suggestions based on ego-centric videos. We encourage novel solutions that improve latency and energy requirements. The annotations in PARSE-Ego4D will support researchers and developers who are working on building action recommendation systems for augmented and virtual reality systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_09503 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PARSE-Ego4D: Personal Action Recommendation Suggestions for Egocentric Videos Abreu, Steven Do, Tiffany D. Ahuja, Karan Gonzalez, Eric J. Payne, Lee McDuff, Daniel Gonzalez-Franco, Mar Computer Vision and Pattern Recognition Human-Computer Interaction Neural and Evolutionary Computing Intelligent assistance involves not only understanding but also action. Existing ego-centric video datasets contain rich annotations of the videos, but not of actions that an intelligent assistant could perform in the moment. To address this gap, we release PARSE-Ego4D, a new set of personal action recommendation annotations for the Ego4D dataset. We take a multi-stage approach to generating and evaluating these annotations. First, we used a prompt-engineered large language model (LLM) to generate context-aware action suggestions and identified over 18,000 action suggestions. While these synthetic action suggestions are valuable, the inherent limitations of LLMs necessitate human evaluation. To ensure high-quality and user-centered recommendations, we conducted a large-scale human annotation study that provides grounding in human preferences for all of PARSE-Ego4D. We analyze the inter-rater agreement and evaluate subjective preferences of participants. Based on our synthetic dataset and complete human annotations, we propose several new tasks for action suggestions based on ego-centric videos. We encourage novel solutions that improve latency and energy requirements. The annotations in PARSE-Ego4D will support researchers and developers who are working on building action recommendation systems for augmented and virtual reality systems. |
| title | PARSE-Ego4D: Personal Action Recommendation Suggestions for Egocentric Videos |
| topic | Computer Vision and Pattern Recognition Human-Computer Interaction Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2407.09503 |