الملخص
Video segmentation models maintain object identities by carrying instance information across frames. Under prolonged occlusion, reappearance, or interactions between similar instances, however, an unreliable update can overwrite a valid history and cause persistent identity drift. We introduce POSReasoner, a trainable, plug-and-play framework that explicitly decides when an observation should change an object's state. Each persistent state records identity, confidence, and absence history. A sparse state-observation graph supports Propose-Verify reasoning: provisional associations are revisited using object history, predicted presence, and competition among identities. The verified decisions determine whether to retain, update, reactivate, or suppress each state, while a learned gate controls the evidence written back to memory. Only verified transitions update the persistent state used in subsequent frames. POSReasoner uses standard video annotations and keeps the base model frozen, enabling integration with diverse VOS and VIS architectures. Experiments across long-term VOS and VIS benchmarks show consistent improvements over strong baselines, with the largest gains under occlusion and object reappearance.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Xu, Y., Yang, B., Liu, Z., Zhang, S., Qian, R., & Chen, H. (2026). Learning to Reason with Persistent Object States for Video Instance Segmentation. https://omanscience.com/ar/articles/learning-to-reason-with-persistent-object-states-for-video-instance-segmentation
MLA 9
Xu, Yongxue, et al. "Learning to Reason with Persistent Object States for Video Instance Segmentation." https://omanscience.com/ar/articles/learning-to-reason-with-persistent-object-states-for-video-instance-segmentation.
شيكاغو (المؤلف–التاريخ)
Xu, Yongxue, Boxue Yang, Ziqian Liu, Shaoqiu Zhang, Rui Qian, and Haopeng Chen. 2026. "Learning to Reason with Persistent Object States for Video Instance Segmentation." https://omanscience.com/ar/articles/learning-to-reason-with-persistent-object-states-for-video-instance-segmentation.
هارفارد
Xu, Y., Yang, B., Liu, Z., Zhang, S., Qian, R. and Chen, H. (2026) 'Learning to Reason with Persistent Object States for Video Instance Segmentation', Available at: https://omanscience.com/ar/articles/learning-to-reason-with-persistent-object-states-for-video-instance-segmentation.
فانكوفر
Xu Y, Yang B, Liu Z, Zhang S, Qian R, Chen H. Learning to Reason with Persistent Object States for Video Instance Segmentation. https://omanscience.com/ar/articles/learning-to-reason-with-persistent-object-states-for-video-instance-segmentation
IEEE
Y. Xu, B. Yang, Z. Liu, S. Zhang, R. Qian, and H. Chen, "Learning to Reason with Persistent Object States for Video Instance Segmentation," https://omanscience.com/ar/articles/learning-to-reason-with-persistent-object-states-for-video-instance-segmentation.