LVOS: A Benchmark for Large-Scale Long-Term Video Object Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-01 · 48 (1) · 946-961
DOI: 10.1109/tpami.2025.3611020 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-01. Verfasst von Lingyi Hong und 11 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 124 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Video object segmentation (VOS) aims to distinguish and track target objects in a video. Despite the excellent performance achieved by off-the-shelf VOS models, part of the existing VOS benchmarks mainly focuses on short-term videos, where objects remain visible most of the time. However, these benchmarks may not fully capture challenges encountered in practical applications, and the absence of long-term datasets restricts further investigation of VOS in realistic scenarios. Thus, we propose a novel benchmark named LVOS, comprising 720 videos with 296,401 frames and 407,945 high-quality annotations. Videos in LVOS last 1.14 minutes on average. Each video includes various attributes, especially challenges encountered in the wild, such as long-term reappearing and cross-temporal similar objects. Compared to previous benchmarks, our LVOS better reflects VOS models' performance in real scenarios. Based on LVOS, we evaluate 15 existing VOS models under 3 different settings and conduct a comprehensive analysis. On LVOS, these models suffer a large performance drop, highlighting the challenge of achieving precise tracking and segmentation in real-world scenarios. Attribute-based analysis indicates that one of the significant factors contributing to accuracy decline is the increased video length, interacting with complex challenges such as long-term reappearance, cross-temporal confusion, and occlusion, which emphasize LVOS's crucial role. We hope our LVOS can advance development of VOS in real scenes.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Hong, L., Liu, Z., Chen, W., Tan, C., Feng, Y., Zhou, X., Guo, P., Li, J., Chen, Z., Gao, S., Zhang, W., & Zhang, W. (2026). LVOS: A Benchmark for Large-Scale Long-Term Video Object Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(1), 946-961. https://doi.org/10.1109/tpami.2025.3611020
Vancouver
Hong L, Liu Z, Chen W, Tan C, Feng Y, Zhou X, et al. LVOS: A Benchmark for Large-Scale Long-Term Video Object Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(1):946-961. doi:10.1109/tpami.2025.3611020
BibTeX
@article{Hong2026,
author = {Hong, Lingyi and Liu, Zhongying and Chen, Wenchao and Tan, Chenzhi and Feng, Yuang and Zhou, Xinyu and Guo, Pinxue and Li, Jinglun and Chen, Zhaoyu and Gao, Shuyong and Zhang, Wei and Zhang, Wenqiang},
title = {LVOS: A Benchmark for Large-Scale Long-Term Video Object Segmentation},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {1},
pages = {946--961},
doi = {10.1109/tpami.2025.3611020}
}
EUVIMED