Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Qibin Hou"'
Publikováno v:
Computational Visual Media, Vol 6, Iss 2, Pp 191-204 (2020)
Abstract In this paper, we consider salient instance segmentation. As well as producing bounding boxes, our network also outputs high-quality instance-level segments as initial selections to indicate the regions of interest. Taking into account the c
Externí odkaz:
https://doaj.org/article/b1011967c56d43f18e65eed0940c3a70
Publikováno v:
Computational Visual Media, Vol 5, Iss 4, Pp 417-428 (2020)
Abstract In this paper, we propose a simple but effective framework for lane boundary detection, called SpinNet. Considering that cars or pedestrians often occlude lane boundaries and that the local features of lane boundaries are not distinctive, th
Externí odkaz:
https://doaj.org/article/4787f70ecadf4d1c9498172b8a8632cc
Publikováno v:
Computational Visual Media, Vol 5, Iss 2, Pp 117-150 (2019)
Abstract Detecting and segmenting salient objects from natural scenes, often referred to as salient object detection, has attracted great interest in computer vision. While many models have been proposed and several applications have emerged, a deep
Externí odkaz:
https://doaj.org/article/44f9080fc64541e2afbfec5662119756
Publikováno v:
Computational Visual Media, Vol 4, Iss 4, Pp 333-348 (2018)
Abstract In this paper, we reconsider the clustering problem for image over-segmentation from a new perspective. We propose a novel search algorithm called “active search” which explicitly considers neighbor continuity. Based on this search metho
Externí odkaz:
https://doaj.org/article/e85281e7202e4c2dabc528e3220071b5
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 45:887-904
We explore the potential of pooling techniques on the task of salient object detection by expanding its role in convolutional neural networks. In general, two pooling-based modules are proposed. A global guidance module (GGM) is first built based on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::94a00ca4c9923b27dc63ad1df3fcb293
https://doi.org/10.1109/tpami.2021.3140168
https://doi.org/10.1109/tpami.2021.3140168
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 32:8128-8141
Attention mechanisms have been proven highly effective for salient object detection. Most previous works utilize attention as a self-gated module to reweigh the feature maps at different levels independently. However, they are limited to certain-leve
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::47f1b2607d651dee00d6a6e945e7185e
https://doi.org/10.1109/tcsvt.2021.3102944
https://doi.org/10.1109/tcsvt.2021.3102944
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. :1-9
Vision transformers have recently attained state-of-the-art results in visual recognition tasks. Their success is largely attributed to the self-attention component, which models the global dependencies among the image patches (tokens) and aggregates
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8a16ae9f9fd5ce56ed11ebd5b451e456
https://doi.org/10.1109/tpami.2022.3208922
https://doi.org/10.1109/tpami.2022.3208922
Publikováno v:
Sixth International Conference on Traffic Engineering and Transportation System (ICTETS 2022).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a0aafd21988fee54b9aaad50195227db
https://doi.org/10.1117/12.2668663
https://doi.org/10.1117/12.2668663
Publikováno v:
Proceedings of the 30th ACM International Conference on Multimedia.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b155cfd53477c15dc1c65b87b339da86
https://doi.org/10.1145/3503161.3548016
https://doi.org/10.1145/3503161.3548016
Publikováno v:
IEEE Transactions on Image Processing. 29:8652-8667
Salient object segmentation, edge detection, and skeleton extraction are three contrasting low-level pixel-wise vision problems, where existing works mostly focused on designing tailored methods for each individual task. However, it is inconvenient a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::39eb43f5b76c8bcb687d1460a2dc363b
https://doi.org/10.1109/tip.2020.3017352
https://doi.org/10.1109/tip.2020.3017352