Region Aware Video Object Segmentation With Deep Motion Modeling

Current semi-supervised video object segmentation (VOS) methods often employ the entire features of one frame to predict object masks and update memory. This introduces significant redundant computations. To reduce redundancy, we introduce a Region Aware Video Object Segmentation (RAVOS) approach, w...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 33(2024) vom: 29., Seite 2639-2651
1. Verfasser: Miao, Bo (VerfasserIn)
Weitere Verfasser: Bennamoun, Mohammed, Gao, Yongsheng, Mian, Ajmal
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2024
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000caa a22002652 4500
001 NLM370413539
003 DE-627
005 20240404235224.0
007 cr uuu---uuuuu
008 240331s2024 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2024.3381445  |2 doi 
028 5 2 |a pubmed24n1364.xml 
035 |a (DE-627)NLM370413539 
035 |a (NLM)38551827 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Miao, Bo  |e verfasserin  |4 aut 
245 1 0 |a Region Aware Video Object Segmentation With Deep Motion Modeling 
264 1 |c 2024 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 03.04.2024 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Current semi-supervised video object segmentation (VOS) methods often employ the entire features of one frame to predict object masks and update memory. This introduces significant redundant computations. To reduce redundancy, we introduce a Region Aware Video Object Segmentation (RAVOS) approach, which predicts regions of interest (ROIs) for efficient object segmentation and memory storage. RAVOS includes a fast object motion tracker to predict object ROIs in the next frame. For efficient segmentation, object features are extracted based on the ROIs, and an object decoder is designed for object-level segmentation. For efficient memory storage, we propose motion path memory to filter out redundant context by memorizing the features within the motion path of objects. In addition to RAVOS, we also propose a large-scale occluded VOS dataset, dubbed OVOS, to benchmark the performance of VOS models under occlusions. Evaluation on DAVIS and YouTube-VOS benchmarks and our new OVOS dataset show that our method achieves state-of-the-art performance with significantly faster inference time, e.g., 86.1 J & F at 42 FPS on DAVIS and 84.4 J & F at 23 FPS on YouTube-VOS. Project page: ravos.netlify.app 
650 4 |a Journal Article 
700 1 |a Bennamoun, Mohammed  |e verfasserin  |4 aut 
700 1 |a Gao, Yongsheng  |e verfasserin  |4 aut 
700 1 |a Mian, Ajmal  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 33(2024) vom: 29., Seite 2639-2651  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:33  |g year:2024  |g day:29  |g pages:2639-2651 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2024.3381445  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 33  |j 2024  |b 29  |h 2639-2651