Beyond Visual Similarity: ProtoSAM2 for Long-Term VOS via Adaptive Motion and Prototype Refinement
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 845-854
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62473201)
- National Natural Science Foundation of China (62477026)
- National Natural Science Foundation of China (92470202)
- National Natural Science Foundation of China (62272468)
- National Natural Science Foundation of China (62332015)
- Basic research program of Jiangsu (BK20250043)
- Frontier Technologies R&D Program of Jiangsu (BF2024070)
This publication has 29 references indexed in Scilit:
- Segment anything in medical imagesNature Communications, 2024
- XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model2022
- Learning What to Learn for Video Object Segmentation2020
- RAFT: Recurrent All-Pairs Field Transforms for Optical Flow2020
- Collaborative Video Object Segmentation by Foreground-Background Integration2020
- RVOS: End-To-End Recurrent Network for Video Object Segmentation2019
- YouTube-VOS: Sequence-to-Sequence Video Object Segmentation2018
- Fast Video Object Segmentation by Reference-Guided Mask Propagation2018
- One-Shot Video Object Segmentation2017
- A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation2016