HIPPO-Video: Simulating Watch Histories with Large Language Models for Personalized Video Highlighting
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_ | 1866916858230210560 |
|---|---|
| author | Lee, Jeongeun Yu, Youngjae Lee, Dongha |
| author_facet | Lee, Jeongeun Yu, Youngjae Lee, Dongha |
| contents | The exponential growth of video content has made personalized video highlighting an essential task, as user preferences are highly variable and complex. Existing video datasets, however, often lack personalization, relying on isolated videos or simple text queries that fail to capture the intricacies of user behavior. In this work, we introduce HIPPO-Video, a novel dataset for personalized video highlighting, created using an LLM-based user simulator to generate realistic watch histories reflecting diverse user preferences. The dataset includes 2,040 (watch history, saliency score) pairs, covering 20,400 videos across 170 semantic categories. To validate our dataset, we propose HiPHer, a method that leverages these personalized watch histories to predict preference-conditioned segment-wise saliency scores. Through extensive experiments, we demonstrate that our method outperforms existing generic and query-based approaches, showcasing its potential for highly user-centric video highlighting in real-world scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16873 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HIPPO-Video: Simulating Watch Histories with Large Language Models for Personalized Video Highlighting Lee, Jeongeun Yu, Youngjae Lee, Dongha Computer Vision and Pattern Recognition Artificial Intelligence The exponential growth of video content has made personalized video highlighting an essential task, as user preferences are highly variable and complex. Existing video datasets, however, often lack personalization, relying on isolated videos or simple text queries that fail to capture the intricacies of user behavior. In this work, we introduce HIPPO-Video, a novel dataset for personalized video highlighting, created using an LLM-based user simulator to generate realistic watch histories reflecting diverse user preferences. The dataset includes 2,040 (watch history, saliency score) pairs, covering 20,400 videos across 170 semantic categories. To validate our dataset, we propose HiPHer, a method that leverages these personalized watch histories to predict preference-conditioned segment-wise saliency scores. Through extensive experiments, we demonstrate that our method outperforms existing generic and query-based approaches, showcasing its potential for highly user-centric video highlighting in real-world scenarios. |
| title | HIPPO-Video: Simulating Watch Histories with Large Language Models for Personalized Video Highlighting |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2507.16873 |