Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Seoung Wug Oh"'
Publikováno v:
Computer Graphics Forum. 41:165-175
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1f319a77755c95addca06b13aa99a5e3
https://doi.org/10.1111/cgf.14666
https://doi.org/10.1111/cgf.14666
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 44:442-455
We propose a novel and unified solution for user-guided video object segmentation tasks. In this work, we consider two scenarios of user-guided segmentation: semi-supervised and interactive segmentation. Due to the nature of the problem, available cu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d1ede30823f8e2054ddd28785d80c556
https://doi.org/10.1109/tpami.2020.3008917
https://doi.org/10.1109/tpami.2020.3008917
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 in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9d976637425e1cee1f325f4bbfc3702f
http://arxiv.org/abs/2208.01924
http://arxiv.org/abs/2208.01924
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1267da4cc713f4cfcbfe120cd1c052c7
https://doi.org/10.1109/cvprw56347.2022.00299
https://doi.org/10.1109/cvprw56347.2022.00299
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198052
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d1b71508ef27ae79e6576adbc8dfcdeb
https://doi.org/10.1007/978-3-031-19806-9_8
https://doi.org/10.1007/978-3-031-19806-9_8
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198175
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6f1c71add4d39ac5098fd0a0f2facb0e
https://doi.org/10.1007/978-3-031-19818-2_25
https://doi.org/10.1007/978-3-031-19818-2_25
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198052
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::85e8af8ad204f09e1a854854e1b8340e
https://doi.org/10.1007/978-3-031-19806-9_14
https://doi.org/10.1007/978-3-031-19806-9_14
Publikováno v:
CVPR
By the one-to-many nature of the super-resolution (SR) problem, a single low-resolution (LR) image can be mapped to many high-resolution (HR) images. However, learning based SR algorithms are trained to map an LR image to the corresponding ground tru
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d3a7e7588abe75b637ec53fd5bcc175e
https://doi.org/10.1109/cvpr46437.2021.01597
https://doi.org/10.1109/cvpr46437.2021.01597
Publikováno v:
CVPR
In this paper, we propose a novel learning-based polygonal point set tracking method. Compared to existing video object segmentation~(VOS) methods that propagate pixel-wise object mask information, we propagate a polygonal point set over frames. Spec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::41f52c5d71fdc9b6fd8c1ab53304947a
Publikováno v:
CVPR
We extend panoptic segmentation to the open-world and introduce an open-set panoptic segmentation (OPS) task. This task requires performing panoptic segmentation for not only known classes but also unknown ones that have not been acknowledged during
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::64ac6e9cdcd04c6600205b1e6a4a0a60