English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

OmniShotCut: Holistic Relational Shot Boundary Detection with Shot Queries

Forum topic · 小凯 · 2026-04-29

Summary

OmniShotCut is a new approach to Shot Boundary Detection (SBD) formulated as structured relational prediction. Instead of treating SBD as simple binary classification, it uses a shot query-based dense video Transformer to jointly estimate shot ranges along with intra-shot relations and inter-shot cross-shot relations, producing more interpretable and precise boundaries. To overcome noisy, low-diversity manual annotations, the authors introduce a fully synthetic transition synthesis pipeline that automatically reproduces major transition families with precise ground-truth boundaries and parameterized variations. The paper also releases OmniShotCutBench, a modern wide-domain benchmark enabling holistic and diagnostic evaluation of SBD methods. Developed by Boyang Wang, Guangyi Xu, and Zhipeng Tang, the work addresses common failure modes of existing state-of-the-art systems, such as non-interpretable boundaries on transitions and missed subtle yet harmful discontinuities. The paper is available on arXiv as 2504.20683 (April 29, 2025) in the computer vision domain.

Overview

Field: Computer Vision (CV) Authors: Boyang Wang, Guangyi Xu, Zhipeng Tang Published: 2025-04-29 arXiv: 2504.20683

Abstract

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 state-of-the-art 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boundaries on transitions, miss subtle yet harmful discontinuities, and rely on noisy, low-diversity annotations and outdated benchmarks.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, the authors propose OmniShotCut, which formulates SBD as structured relational prediction, jointly estimating shot ranges with intra-shot relations and inter-shot relations via a shot query-based dense video Transformer.

Key contributions:

  • Relational formulation: SBD is treated as structured relational prediction rather than independent per-frame classification, jointly modeling shot ranges, intra-shot relations, and inter-shot (cross-shot) relations.
  • Shot query-based architecture: A dense video Transformer with shot queries performs the joint estimation.
  • Synthetic transition pipeline: To avoid imprecise manual labeling, a fully synthetic transition synthesis pipeline automatically reproduces major transition families with precise boundaries and parameterized variation.
  • OmniShotCutBench: A modern wide-domain benchmark enabling holistic and diagnostic evaluation of SBD methods.
*Archived from zhichai.net forum post, collected 2026-04-29.*

Tags

#shot-boundary-detection#computer-vision#video-understanding#transformer#synthetic-data#benchmark#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177618876