Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Ge-Peng Ji"'
Publikováno v:
Computational Visual Media, Vol 9, Iss 1, Pp 155-175 (2022)
Abstract Previous video object segmentation approaches mainly focus on simplex solutions linking appearance and motion, limiting effective feature collaboration between these two cues. In this work, we study a novel and efficient full-duplex strategy
Externí odkaz:
https://doaj.org/article/f98fc5c8b9fd4421ae8956c77181129c
Publikováno v:
Machine Intelligence Research, 20 (3)
We present a masked vision-language transformer (MVLT) for fashion-specific multi-modal representation. Technically, we simply utilize the vision transformer architecture for replacing the bidirectional encoder representations from Transformers (BERT
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e306a08827b7c465dd657726484ad10
https://doi.org/10.1007/s11633-022-1394-4
https://doi.org/10.1007/s11633-022-1394-4
Publikováno v:
Machine Intelligence Research, 20 (1)
This paper introduces deep gradient network (DGNet), a novel deep framework that exploits object gradient supervision for camouflaged object detection (COD). It decouples the task into two connected branches, i.e., a context and a texture encoder. Th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eb8175f9c1ea3820280d9c4850d52297
http://arxiv.org/abs/2205.12853
http://arxiv.org/abs/2205.12853
Camouflaged object detection (COD) aims to identify the objects that conceal themselves in natural scenes. Accurate COD suffers from a number of challenges associated with low boundary contrast and the large variation of object appearances, e.g., obj
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d557b18cf5a0b31f556f70e1725fea20
Publikováno v:
Machine Intelligence Research, 19 (6)
We present the first comprehensive video polyp segmentation (VPS) study in the deep learning era. Over the years, developments in VPS are not moving forward with ease due to the lack of a large-scale dataset with fine-grained segmentation annotations
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1f66c23709ccbe06ee10b0b71971d0ec
Publikováno v:
Computational Visual Media, 9 (1)
Previous video object segmentation approaches mainly focus on simplex solutions linking appearance and motion, limiting effective feature collaboration between these two cues. In this work, we study a novel and efficient full-duplex strategy network
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4a527a1b7e973c4c136987bf2fd74a19
https://doi.org/10.1109/iccv48922.2021.00488
https://doi.org/10.1109/iccv48922.2021.00488
Publikováno v:
ACM Multimedia
RGB-D salient object detection (SOD) recently has attracted increasing research interest by benefiting conventional RGB SOD with extra depth information. However, existing RGB-D SOD models often fail to perform well in terms of both efficiency and ac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e5d0cb8d7dc5bc4f54b1268fbd96f7ae
http://arxiv.org/abs/2107.01779
http://arxiv.org/abs/2107.01779
Owing to the difficulties of mining spatial-temporal cues, the existing approaches for video salient object detection (VSOD) are limited in understanding complex and noisy scenarios, and often fail in inferring prominent objects. To alleviate such sh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a6954b4cc51cd62b8c0755b7714e4f3e
http://arxiv.org/abs/2105.10110
http://arxiv.org/abs/2105.10110
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence.
Existing RGB-D salient object detection (SOD) models usually treat RGB and depth as independent information and design separate networks for feature extraction from each. Such schemes can easily be constrained by a limited amount of training data or
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::59e0c9b46bf919eff85d01f47aa9add0
https://pubmed.ncbi.nlm.nih.gov/33861691
https://pubmed.ncbi.nlm.nih.gov/33861691
We present the first systematic study on concealed object detection (COD), which aims to identify objects that are "perfectly" embedded in their background. The high intrinsic similarities between the concealed objects and their background make COD f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5589c8fdf641cea22f45e8ca2c46b0f9
http://arxiv.org/abs/2102.10274
http://arxiv.org/abs/2102.10274