Motion and Spatiotemporal Aggregation Network for Occlusion Edge Detection From Videos
IEEE Transactions on Circuits and Systems for Video Technology · 2026-07 · 36 (7) · 10618-10631
DOI: 10.1109/tcsvt.2026.3673936 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-07. Verfasst von Liangyu Chen und 6 weiteren Autor:innen. Die Arbeit nennt 87 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Detecting occlusion edges from videos is a critical yet under-explored task, with recent works focusing on single-image occlusion edge detection while ignoring dynamic patterns in videos. In videos, occlusion edges typically occur when a moving object occludes either the background or another object, resulting in two types of occlusion edges: object-background (OB) edges that are characterized by appearance contrast and motion, and object-object (OO) edges that face ambiguity. Inspired by these observations, we propose a novel Motion and Spatio-Temporal Aggregated Network (MaSTAN) and treat the two edge types differently for more effectively detecting occlusion edges in videos. Specifically, we first extract spatial semantics and motion patterns from the videos and propose a novel Temporal Feature Propagation module (TFP) for temporal cue aggregation. Next, we put forward a Dual-branch Gated-attention Decoder (DG-Decoder) to generate edge-specific features for predicting the final occlusion edge maps. Extensive experiments on the OVIS-OE benchmark, the first large benchmark dedicated to video occlusion edge detection, demonstrate that MaSTAN achieves state-of-the-art performance, significantly advancing the capability of occlusion edge detection in video. The source code and benchmark will be made publicly available.
Förderung
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Chen, L., Pu, M., Liu, Z., Hou, X., Huang, Y., Zhou, R., & Ling, H. (2026). Motion and Spatiotemporal Aggregation Network for Occlusion Edge Detection From Videos. IEEE Transactions on Circuits and Systems for Video Technology, 36(7), 10618-10631. https://doi.org/10.1109/tcsvt.2026.3673936
Vancouver
Chen L, Pu M, Liu Z, Hou X, Huang Y, Zhou R, et al. Motion and Spatiotemporal Aggregation Network for Occlusion Edge Detection From Videos. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(7):10618-10631. doi:10.1109/tcsvt.2026.3673936
BibTeX
@article{Chen2026,
author = {Chen, Liangyu and Pu, Mengyang and Liu, Zhihao and Hou, Xiaohui and Huang, Yaping and Zhou, Rong and Ling, Haibin},
title = {Motion and Spatiotemporal Aggregation Network for Occlusion Edge Detection From Videos},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2026},
volume = {36},
number = {7},
pages = {10618--10631},
doi = {10.1109/tcsvt.2026.3673936}
}
EUVIMED