Cluster-based Video Summarization with Temporal Context Awareness

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huynh-Lam, Hai-Dang, Ho-Thi, Ngoc-Phuong, Tran, Minh-Triet, Le, Trung-Nghia
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917640784576512
author Huynh-Lam, Hai-Dang
Ho-Thi, Ngoc-Phuong
Tran, Minh-Triet
Le, Trung-Nghia
author_facet Huynh-Lam, Hai-Dang
Ho-Thi, Ngoc-Phuong
Tran, Minh-Triet
Le, Trung-Nghia
contents In this paper, we present TAC-SUM, a novel and efficient training-free approach for video summarization that addresses the limitations of existing cluster-based models by incorporating temporal context. Our method partitions the input video into temporally consecutive segments with clustering information, enabling the injection of temporal awareness into the clustering process, setting it apart from prior cluster-based summarization methods. The resulting temporal-aware clusters are then utilized to compute the final summary, using simple rules for keyframe selection and frame importance scoring. Experimental results on the SumMe dataset demonstrate the effectiveness of our proposed approach, outperforming existing unsupervised methods and achieving comparable performance to state-of-the-art supervised summarization techniques. Our source code is available for reference at \url{https://github.com/hcmus-thesis-gulu/TAC-SUM}.
format Preprint
id arxiv_https___arxiv_org_abs_2404_04511
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cluster-based Video Summarization with Temporal Context Awareness
Huynh-Lam, Hai-Dang
Ho-Thi, Ngoc-Phuong
Tran, Minh-Triet
Le, Trung-Nghia
Computer Vision and Pattern Recognition
Artificial Intelligence
In this paper, we present TAC-SUM, a novel and efficient training-free approach for video summarization that addresses the limitations of existing cluster-based models by incorporating temporal context. Our method partitions the input video into temporally consecutive segments with clustering information, enabling the injection of temporal awareness into the clustering process, setting it apart from prior cluster-based summarization methods. The resulting temporal-aware clusters are then utilized to compute the final summary, using simple rules for keyframe selection and frame importance scoring. Experimental results on the SumMe dataset demonstrate the effectiveness of our proposed approach, outperforming existing unsupervised methods and achieving comparable performance to state-of-the-art supervised summarization techniques. Our source code is available for reference at \url{https://github.com/hcmus-thesis-gulu/TAC-SUM}.
title Cluster-based Video Summarization with Temporal Context Awareness
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2404.04511