Guardado en:
Detalles Bibliográficos
Autores principales: Hu, Hengrui, Ying, Kaining, Ding, Henghui
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2511.13715
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915623314915328
author Hu, Hengrui
Ying, Kaining
Ding, Henghui
author_facet Hu, Hengrui
Ying, Kaining
Ding, Henghui
contents This work focuses on multi-shot semi-supervised video object segmentation (MVOS), which aims at segmenting the target object indicated by an initial mask throughout a video with multiple shots. The existing VOS methods mainly focus on single-shot videos and struggle with shot discontinuities, thereby limiting their real-world applicability. We propose a transition mimicking data augmentation strategy (TMA) which enables cross-shot generalization with single-shot data to alleviate the severe annotated multi-shot data sparsity, and the Segment Anything Across Shots (SAAS) model, which can detect and comprehend shot transitions effectively. To support evaluation and future study in MVOS, we introduce Cut-VOS, a new MVOS benchmark with dense mask annotations, diverse object categories, and high-frequency transitions. Extensive experiments on YouMVOS and Cut-VOS demonstrate that the proposed SAAS achieves state-of-the-art performance by effectively mimicking, understanding, and segmenting across complex transitions. The code and datasets are released at https://henghuiding.com/SAAS/.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13715
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Segment Anything Across Shots: A Method and Benchmark
Hu, Hengrui
Ying, Kaining
Ding, Henghui
Computer Vision and Pattern Recognition
This work focuses on multi-shot semi-supervised video object segmentation (MVOS), which aims at segmenting the target object indicated by an initial mask throughout a video with multiple shots. The existing VOS methods mainly focus on single-shot videos and struggle with shot discontinuities, thereby limiting their real-world applicability. We propose a transition mimicking data augmentation strategy (TMA) which enables cross-shot generalization with single-shot data to alleviate the severe annotated multi-shot data sparsity, and the Segment Anything Across Shots (SAAS) model, which can detect and comprehend shot transitions effectively. To support evaluation and future study in MVOS, we introduce Cut-VOS, a new MVOS benchmark with dense mask annotations, diverse object categories, and high-frequency transitions. Extensive experiments on YouMVOS and Cut-VOS demonstrate that the proposed SAAS achieves state-of-the-art performance by effectively mimicking, understanding, and segmenting across complex transitions. The code and datasets are released at https://henghuiding.com/SAAS/.
title Segment Anything Across Shots: A Method and Benchmark
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.13715