YUV20K: a complexity-driven benchmark and trajectory-aware alignment model for video camouflaged object detection
Visual Intelligence · 2026-12 · 4 (1)
DOI: 10.1007/s44267-026-00132-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Visual Intelligence, online erschienen am 10.11.2026. Verfasst von Yiyu Liu und 3 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
The development of video camouflaged object detection (VCOD) is currently constrained by the scarcity of challenging benchmarks and the lack of robustness of models in the face of erratic motion dynamics. Existing methods frequently encounter challenges related to motion-induced appearance instability and temporal feature misalignment, particularly in complex motion scenarios. To address the issue of data bottleneck, we present YUV20K, a pixel-level annotated, complexity-driven VCOD benchmark. It is composed of 24,295 annotated frames, which are organized into 91 scenes and 47 species. It focuses on challenging scenarios, including large displacement motion, camera motion, and four additional complex-motion scenarios. In terms of methodology, a novel framework is proposed, comprising two key modules: motion feature stabilization (MFS) and trajectory-aware alignment (TAA). The MFS module utilizes frame-agnostic semantic basis primitives to stabilize features, while the TAA module leverages trajectory-guided deformable sampling to ensure precise temporal alignment. Extensive experiments demonstrate that our method achieves strong performance on existing datasets and establishes a competitive baseline on the challenging YUV20K.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Liu, Y., Ye, S., Hao, C., & Yu, Z. (2026). YUV20K: a complexity-driven benchmark and trajectory-aware alignment model for video camouflaged object detection. Visual Intelligence, 4(1). https://doi.org/10.1007/s44267-026-00132-2
Vancouver
Liu Y, Ye S, Hao C, Yu Z. YUV20K: a complexity-driven benchmark and trajectory-aware alignment model for video camouflaged object detection. Visual Intelligence. 2026;4(1). doi:10.1007/s44267-026-00132-2
BibTeX
@article{Liu2026,
author = {Liu, Yiyu and Ye, Shuo and Hao, Chao and Yu, Zitong},
title = {YUV20K: a complexity-driven benchmark and trajectory-aware alignment model for video camouflaged object detection},
journal = {Visual Intelligence},
year = {2026},
volume = {4},
number = {1},
doi = {10.1007/s44267-026-00132-2}
}
EUVIMED