EUVIMEDEUVIMED entdecken
Crossref

Learning When and How to Update Memory for Video Object Segmentation

Shengye Qiao, Changqun Xia, Yanjie Liang, Xiaowu Chen, Jia Li

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-09 · 48 (9) · 10266-10283

DOI: 10.1109/tpami.2026.3684742 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-09. Verfasst von Shengye Qiao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 104 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Major Key Project of PCL, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent progress in semi-supervised video object segmentation has largely hinged on memory-based methods. However, when faced with increasingly tough challenges emerging in complex scenarios, such as fundamental semantic transformations and severe spatial deformations, the fixed-interval memory update mechanism usually adopted in these memory-based methods is insufficient to align with the pivotal moments of object changes. This inflexible mechanism motivates us to design an adaptive memory update mechanism in response to the semantic-spatial changes of target objects. To this end, we propose a novel Change-Sensitive Network (CSNet) to learn when and how to update memory to effectively address intricate challenges in complex scenarios. Specifically, we first design an Adaptive Perception-Capture module with a hierarchical contrastive learning loss to determine when to update memory moments by measuring the extent of object changes, thus dividing entire videos into different object-change clips. To further extract and highlight object changes to assist in the segmentation of frames after changes occur, we construct Dynamic Memory Update modules to redefine how to update memory by smoothly retaining the object prototypes within clips and dynamically amplifying the object variations across clips. Extensive experiments demonstrate that our proposed CSNet exhibits clear superiority when evaluated on eight datasets covering three kinds: common, complex and long-video datasets.

Förderung

  • National Natural Science Foundation of China
  • Major Key Project of PCL
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Qiao, S., Xia, C., Liang, Y., Chen, X., & Li, J. (2026). Learning When and How to Update Memory for Video Object Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(9), 10266-10283. https://doi.org/10.1109/tpami.2026.3684742

Vancouver

Qiao S, Xia C, Liang Y, Chen X, Li J. Learning When and How to Update Memory for Video Object Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(9):10266-10283. doi:10.1109/tpami.2026.3684742

BibTeX
@article{Qiao2026,
  author = {Qiao, Shengye and Xia, Changqun and Liang, Yanjie and Chen, Xiaowu and Li, Jia},
  title = {Learning When and How to Update Memory for Video Object Segmentation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {9},
  pages = {10266--10283},
  doi = {10.1109/tpami.2026.3684742}
}
Kostenlos starten →