HIPPO-Video: Simulating Watch Histories with Large Language Models for Personalized Video Highlighting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Jeongeun, Yu, Youngjae, Lee, Dongha
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