Weakly-Supervised RGBD Video Object Segmentation

Depth information opens up new opportunities for video object segmentation (VOS) to be more accurate and robust in complex scenes. However, the RGBD VOS task is largely unexplored due to the expensive collection of RGBD data and time-consuming annotation of segmentation. In this work, we first intro...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 33(2024) vom: 18., Seite 2158-2170
1. Verfasser: Yang, Jinyu (VerfasserIn)
Weitere Verfasser: Gao, Mingqi, Zheng, Feng, Zhen, Xiantong, Ji, Rongrong, Shao, Ling, Leonardis, Ales
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 NLM369603028
003 DE-627
005 20240319233009.0
007 cr uuu---uuuuu
008 240313s2024 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2024.3374130  |2 doi 
028 5 2 |a pubmed24n1336.xml 
035 |a (DE-627)NLM369603028 
035 |a (NLM)38470575 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Yang, Jinyu  |e verfasserin  |4 aut 
245 1 0 |a Weakly-Supervised RGBD Video Object Segmentation 
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 18.03.2024 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Depth information opens up new opportunities for video object segmentation (VOS) to be more accurate and robust in complex scenes. However, the RGBD VOS task is largely unexplored due to the expensive collection of RGBD data and time-consuming annotation of segmentation. In this work, we first introduce a new benchmark for RGBD VOS, named DepthVOS, which contains 350 videos (over 55k frames in total) annotated with masks and bounding boxes. We futher propose a novel, strong baseline model - Fused Color-Depth Network (FusedCDNet), which can be trained solely under the supervision of bounding boxes, while being used to generate masks with a bounding box guideline only in the first frame. Thereby, the model possesses three major advantages: a weakly-supervised training strategy to overcome the high-cost annotation, a cross-modal fusion module to handle complex scenes, and weakly-supervised inference to promote ease of use. Extensive experiments demonstrate that our proposed method performs on par with top fully-supervised algorithms. We will open-source our project on https://github.com/yjybuaa/depthvos/ to facilitate the development of RGBD VOS 
650 4 |a Journal Article 
700 1 |a Gao, Mingqi  |e verfasserin  |4 aut 
700 1 |a Zheng, Feng  |e verfasserin  |4 aut 
700 1 |a Zhen, Xiantong  |e verfasserin  |4 aut 
700 1 |a Ji, Rongrong  |e verfasserin  |4 aut 
700 1 |a Shao, Ling  |e verfasserin  |4 aut 
700 1 |a Leonardis, Ales  |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: 18., Seite 2158-2170  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:33  |g year:2024  |g day:18  |g pages:2158-2170 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2024.3374130  |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 18  |h 2158-2170