DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Kwanyong | ko |
dc.contributor.author | Woo, Sanghyun | ko |
dc.contributor.author | Oh, Seoung Wug | ko |
dc.contributor.author | Kweon, In So | ko |
dc.contributor.author | Lee, Joon-Young | ko |
dc.date.accessioned | 2022-11-29T03:01:18Z | - |
dc.date.available | 2022-11-29T03:01:18Z | - |
dc.date.created | 2022-11-25 | - |
dc.date.created | 2022-11-25 | - |
dc.date.issued | 2022-06-24 | - |
dc.identifier.citation | 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, pp.1342 - 1351 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10203/301209 | - |
dc.description.abstract | Recently, memory-based approaches show promising results on semi-supervised video object segmentation. These methods predict object masks frame-by-frame with the help of frequently updated memory of the previous mask. Different from this per-frame inference, we investigate an alternative perspective by treating video object segmentation as clip-wise mask propagation. In this per-clip inference scheme, we update the memory with an interval and simul-taneously process a set of consecutive frames (i.e. clip) between the memory updates. The scheme provides two potential benefits: accuracy gain by clip-level optimization and efficiency gain by parallel computation of multiple frames. To this end, we propose a new method tailored for the perclip inference. Specifically, we first introduce a clip-wise operation to refine the features based on intra-clip correlation. In addition, we employ a progressive matching mechanism for efficient information-passing within a clip. With the synergy of two modules and a newly proposed perclip based training, our network achieves state-of-the-art performance on Youtube-VOS 2018/2019 val (84.6% and 84.6%) and DAVIS 2016/2017 val (91.9% and 86.1%). Fur-thermore, our model shows a great speed-accuracy trade-off with varying memory update intervals, which leads to huge flexibility. | - |
dc.language | English | - |
dc.publisher | Computer Vision Foundation, IEEE Computer Society | - |
dc.title | Per-Clip Video Object Segmentation | - |
dc.type | Conference | - |
dc.identifier.wosid | 000867754201058 | - |
dc.identifier.scopusid | 2-s2.0-85139670221 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 1342 | - |
dc.citation.endingpage | 1351 | - |
dc.citation.publicationname | 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | New Orleans | - |
dc.identifier.doi | 10.1109/CVPR52688.2022.00141 | - |
dc.contributor.localauthor | Kweon, In So | - |
dc.contributor.nonIdAuthor | Park, Kwanyong | - |
dc.contributor.nonIdAuthor | Woo, Sanghyun | - |
dc.contributor.nonIdAuthor | Oh, Seoung Wug | - |
dc.contributor.nonIdAuthor | Lee, Joon-Young | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.