HiSum: A Hierarchical Framework for Long Video Summarization with Temporal Enhancement

View at publisher Summarise with VIRAT
Authors: Jiaojiao Lin, Cong Zhang, Wenjian Shao, Lingyun Zhu, Yi Qian, Jokul Li
Cited by: 0
References: 20

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

We propose HiSum, a novel Hierarchical and temporally-enhanced framework for the task of long video Summarization. A significant challenge in this domain is generating concise yet informative summaries for long videos, which requires a nuanced understanding of both spatial and temporal information. Existing methods are often limited, struggling with temporally complex summaries and supporting videos typically shorter than one hour. To address these limitations, we propose HiSum, a training-free framework for long video summarization that is hierarchical, scene-aware, and temporally enhanced. HiSum will segment a video based on scene boundaries and then construct a summary hierarchically, effectively overcoming context length constraints. A dedicated temporal enhancement component is employed to mitigate information loss between chunks. Experimental results demonstrate that HiSum outperforms not only in resource consumption, but also in summary generation quality. Evaluated on the InfiniBench dataset, HiSum attained a GPT-5 score of 7.51 (on a 0-10 scale), significantly outperforming prevailing methods like Qwen2.5-VL, which scored 3.47.1

Fields of Study & Subjects

Video Analysis and Summarization Multimodal Machine Learning Applications Generative Adversarial Networks and Image Synthesis

Publication details

Journal / source
International Conference on Consumer Electronics
Pages
1–6
Publication date
3 February 2026
Language
EN