Guardado en:
Detalles Bibliográficos
Autores principales: Tan, Kailong, Zhou, Yuxiang, Xia, Qianchen, Liu, Rui, Chen, Yong
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2401.04962
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929205979119616
author Tan, Kailong
Zhou, Yuxiang
Xia, Qianchen
Liu, Rui
Chen, Yong
author_facet Tan, Kailong
Zhou, Yuxiang
Xia, Qianchen
Liu, Rui
Chen, Yong
contents Keyframe extraction aims to sum up a video's semantics with the minimum number of its frames. This paper puts forward a Large Model based Sequential Keyframe Extraction for video summarization, dubbed LMSKE, which contains three stages as below. First, we use the large model "TransNetV21" to cut the video into consecutive shots, and employ the large model "CLIP2" to generate each frame's visual feature within each shot; Second, we develop an adaptive clustering algorithm to yield candidate keyframes for each shot, with each candidate keyframe locating nearest to a cluster center; Third, we further reduce the above candidate keyframes via redundancy elimination within each shot, and finally concatenate them in accordance with the sequence of shots as the final sequential keyframes. To evaluate LMSKE, we curate a benchmark dataset and conduct rich experiments, whose results exhibit that LMSKE performs much better than quite a few SOTA competitors with average F1 of 0.5311, average fidelity of 0.8141, and average compression ratio of 0.9922.
format Preprint
id arxiv_https___arxiv_org_abs_2401_04962
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Large Model based Sequential Keyframe Extraction for Video Summarization
Tan, Kailong
Zhou, Yuxiang
Xia, Qianchen
Liu, Rui
Chen, Yong
Computer Vision and Pattern Recognition
Keyframe extraction aims to sum up a video's semantics with the minimum number of its frames. This paper puts forward a Large Model based Sequential Keyframe Extraction for video summarization, dubbed LMSKE, which contains three stages as below. First, we use the large model "TransNetV21" to cut the video into consecutive shots, and employ the large model "CLIP2" to generate each frame's visual feature within each shot; Second, we develop an adaptive clustering algorithm to yield candidate keyframes for each shot, with each candidate keyframe locating nearest to a cluster center; Third, we further reduce the above candidate keyframes via redundancy elimination within each shot, and finally concatenate them in accordance with the sequence of shots as the final sequential keyframes. To evaluate LMSKE, we curate a benchmark dataset and conduct rich experiments, whose results exhibit that LMSKE performs much better than quite a few SOTA competitors with average F1 of 0.5311, average fidelity of 0.8141, and average compression ratio of 0.9922.
title Large Model based Sequential Keyframe Extraction for Video Summarization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.04962