Zobrazeno 1 - 10
of 56
pro vyhledávání: '"Kuiyuan Yang"'
The gap between low-level visual signals and high-level semantics has been progressively bridged by continuous development of deep neural network (DNN). With recent progress of DNN, almost all image classification tasks have achieved new records of a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fd096ffcd88a2f4bf97792e8dc8b05a7
http://arxiv.org/abs/2302.13275
http://arxiv.org/abs/2302.13275
Autor:
Xiangtai Li, Hao He, Yibo Yang, Henghui Ding, Kuiyuan Yang, Guangliang Cheng, Yunhai Tong, Dacheng Tao
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. :1-8
Video Instance Segmentation (VIS) is a new and inherently multi-task problem, which aims to detect, segment, and track each instance in a video sequence. Existing approaches are mainly based on single-frame features or single-scale features of multip
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ba7c715ff9bce25da084eb3a77ac468f
https://doi.org/10.1109/tpami.2022.3211612
https://doi.org/10.1109/tpami.2022.3211612
Autor:
Yunhai Tong, Xia Li, Zhouchen Lin, Xiangtai Li, Guangliang Cheng, Ansheng You, Li Zhang, Kuiyuan Yang
Publikováno v:
IEEE Transactions on Image Processing. 30:7050-7063
Graph-based convolutional model such as non-local block has shown to be effective for strengthening the context modeling ability in convolutional neural networks (CNNs). However, its pixel-wise computational overhead is prohibitive which renders it u
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::59cddd570a9e550ae4615dd2bdf6e778
https://doi.org/10.1109/tip.2021.3099369
https://doi.org/10.1109/tip.2021.3099369
Publikováno v:
AAAI
Semantic segmentation generates comprehensive understanding of scenes through densely predicting the category for each pixel. High-level features from Deep Convolutional Neural Networks already demonstrate their effectiveness in semantic segmentation
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5d49286fb7fc9b31cd685235e259837f
https://doi.org/10.1609/aaai.v34i07.6805
https://doi.org/10.1609/aaai.v34i07.6805
Publikováno v:
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9c100658a5da9f5f0f1b7aa28c5251a5
https://doi.org/10.1109/iros51168.2021.9636227
https://doi.org/10.1109/iros51168.2021.9636227
Publikováno v:
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bd404e341222953e98005070ed8aed01
https://doi.org/10.1109/iros51168.2021.9636419
https://doi.org/10.1109/iros51168.2021.9636419
Publikováno v:
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6e2702f5ff173a02fc26f4fc4b03503a
https://doi.org/10.1109/iros51168.2021.9636746
https://doi.org/10.1109/iros51168.2021.9636746
Publikováno v:
Pattern Recognition. 91:391-403
Increasing the number of parameters seems to have improved convolutional neural networks, e.g. increasing the depth or width of the networks. In this paper, we propose a scheme to improve CNNs by deriving the six sub-filters from a filter, which shar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::01d901dea40d9d93c0036690f9386aee
https://doi.org/10.1016/j.patcog.2019.01.044
https://doi.org/10.1016/j.patcog.2019.01.044
Modelling long-range contextual relationships is critical for pixel-wise prediction tasks such as semantic segmentation. However, convolutional neural networks (CNNs) are inherently limited to model such dependencies due to the naive structure in its
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aef455697bcd65e231c6e04f0942f83d
Publikováno v:
ACM Transactions on Multimedia Computing, Communications, and Applications. 14:1-20
Large-scale image datasets and deep convolutional neural networks (DCNNs) are the two primary driving forces for the rapid progress in generic object recognition tasks in recent years. While lots of network architectures have been continuously design
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::49eb9e571808ede26dc43c2c0cc44dce
https://doi.org/10.1145/3204941
https://doi.org/10.1145/3204941