Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Patel, Nirav, Prajapati, Payal, Shah, Maitrik
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2410.14087
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916567817650176
author Patel, Nirav
Prajapati, Payal
Shah, Maitrik
author_facet Patel, Nirav
Prajapati, Payal
Shah, Maitrik
contents Generating a concise and informative video summary from a long video is important, yet subjective due to varying scene importance. Users' ability to specify scene importance through text queries enhances the relevance of such summaries. This paper introduces an approach for query-focused video summarization, aiming to align video summaries closely with user queries. To this end, we propose the Fully Convolutional Sequence Network with Attention (FCSNA-QFVS), a novel approach designed for this task. Leveraging temporal convolutional and attention mechanisms, our model effectively extracts and highlights relevant content based on user-specified queries. Experimental validation on a benchmark dataset for query-focused video summarization demonstrates the effectiveness of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2410_14087
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Your Interest, Your Summaries: Query-Focused Long Video Summarization
Patel, Nirav
Prajapati, Payal
Shah, Maitrik
Computer Vision and Pattern Recognition
Generating a concise and informative video summary from a long video is important, yet subjective due to varying scene importance. Users' ability to specify scene importance through text queries enhances the relevance of such summaries. This paper introduces an approach for query-focused video summarization, aiming to align video summaries closely with user queries. To this end, we propose the Fully Convolutional Sequence Network with Attention (FCSNA-QFVS), a novel approach designed for this task. Leveraging temporal convolutional and attention mechanisms, our model effectively extracts and highlights relevant content based on user-specified queries. Experimental validation on a benchmark dataset for query-focused video summarization demonstrates the effectiveness of our approach.
title Your Interest, Your Summaries: Query-Focused Long Video Summarization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.14087