Temporally Consistent Referring Video Object Segmentation with Hybrid Memory

Bo Miao, Mohammed Bennamoun, Yongsheng Gao, Mubarak Shah, Ajmal Mian

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)
98 Downloads (Pure)

Abstract

Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining consistent object segmentation due to temporal context variability and the presence of other visually similar objects. We propose an end-to-end R-VOS paradigm that explicitly models temporal instance consistency alongside the referring segmentation. Specifically, we introduce a novel hybrid memory that facilitates inter-frame collaboration for robust spatio-temporal matching and propagation. Features of frames with automatically generated high-quality reference masks are propagated to segment the remaining frames based on multi-granularity association to achieve temporally consistent R-VOS. Furthermore, we propose a new Mask Consistency Score (MCS) metric to evaluate the temporal consistency of video segmentation. Extensive experiments demonstrate that our approach enhances temporal consistency by a significant margin, leading to top-ranked performance on popular R-VOS benchmarks, i.e., Ref-YouTube-VOS (67.1%) and Ref-DAVIS17 (65.6%). The code is available at https://github.com/bo-miao/HTR.
Original languageEnglish
Article number10572009
Pages (from-to)11373-11385
Number of pages13
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume34
Issue number11
Early online date26 Jun 2024
DOIs
Publication statusPublished - 2024

Fingerprint

Dive into the research topics of 'Temporally Consistent Referring Video Object Segmentation with Hybrid Memory'. Together they form a unique fingerprint.

Cite this