A frozen SAM2 backbone with adaptive token selection and symmetric KL clustering achieves competitive self-supervised video object segmentation by aligning soft part assignments across time.
In: Proceedings of the IEEE/CVF International Conference on Computer Vision (2019)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
`Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation
A frozen SAM2 backbone with adaptive token selection and symmetric KL clustering achieves competitive self-supervised video object segmentation by aligning soft part assignments across time.