Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Boyang, Xu, Guangyi, Zhang, Jiahui, Tang, Zhipeng, Cheng, Zezhou
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.24762
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918516054032384
author Wang, Boyang
Xu, Guangyi
Zhang, Jiahui
Tang, Zhipeng
Cheng, Zezhou
author_facet Wang, Boyang
Xu, Guangyi
Zhang, Jiahui
Tang, Zhipeng
Cheng, Zezhou
contents Shot Boundary Detection (SBD) aims to automatically identify shot changes and divide a video into coherent shots. While SBD was widely studied in the literature, existing methods often produce non-interpretable boundaries on transitions, miss subtle yet harmful discontinuities, and rely on noisy, low-diversity annotations and outdated benchmarks. To alleviate these limitations, we propose OmniShotCut to formulate SBD as structured relational prediction, jointly estimating shot ranges with intra-shot relations and inter-shot relations, by a shot query-based dense video Transformer. To avoid imprecise manual labeling, we adopt a fully synthetic transition synthesis pipeline that automatically reproduces major transition families with precise boundaries and parameterized variants. We also introduce OmniShotCutBench, a modern wide-domain benchmark enabling holistic and diagnostic evaluation. Experiments on the benchmarks demonstrate the effectiveness and generality of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2604_24762
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer
Wang, Boyang
Xu, Guangyi
Zhang, Jiahui
Tang, Zhipeng
Cheng, Zezhou
Computer Vision and Pattern Recognition
Shot Boundary Detection (SBD) aims to automatically identify shot changes and divide a video into coherent shots. While SBD was widely studied in the literature, existing methods often produce non-interpretable boundaries on transitions, miss subtle yet harmful discontinuities, and rely on noisy, low-diversity annotations and outdated benchmarks. To alleviate these limitations, we propose OmniShotCut to formulate SBD as structured relational prediction, jointly estimating shot ranges with intra-shot relations and inter-shot relations, by a shot query-based dense video Transformer. To avoid imprecise manual labeling, we adopt a fully synthetic transition synthesis pipeline that automatically reproduces major transition families with precise boundaries and parameterized variants. We also introduce OmniShotCutBench, a modern wide-domain benchmark enabling holistic and diagnostic evaluation. Experiments on the benchmarks demonstrate the effectiveness and generality of our method.
title OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.24762