Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Hongje Seong"'
Publikováno v:
IEEE Access, Vol 8, Pp 82066-82077 (2020)
Scene recognition is a kind of image recognition problems which is aimed at predicting the category of the place at which the image is taken. In this paper, a new scene recognition method using the convolutional neural network (CNN) is proposed. The
Externí odkaz:
https://doaj.org/article/d664bb9c96194e6a8278c4de1f2dae45
Publikováno v:
Sensors, Vol 22, Iss 9, p 3494 (2022)
Construction signs alert drivers to the dangers of abnormally blocked roads. In the case of autonomous vehicles, construction signs should be detected automatically to prevent accidents. One might think that we can accomplish the goal easily using th
Externí odkaz:
https://doaj.org/article/aefdcf1cf56b4d749c559304c736c140
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 45:2595-2612
Semi-supervised video object segmentation (VOS) is to predict the segment of a target object in a video when a ground truth segmentation mask for the target is given in the first frame. Recently, space-time memory networks (STM) have received signifi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8f607dcf78d834be0bdd8c3545364415
https://doi.org/10.1109/tpami.2022.3163375
https://doi.org/10.1109/tpami.2022.3163375
Publikováno v:
IEEE Transactions on Systems, Man, and Cybernetics: Systems. 52:5877-5888
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9d5aae41cce5c2021a41a22deef0ed10
https://doi.org/10.1109/tsmc.2021.3132026
https://doi.org/10.1109/tsmc.2021.3132026
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:2053-2061
In this paper, a new deep learning network named as graph-based point tracker (GPT) is proposed for 3D object tracking in point clouds. GPT is not based on Siamese network applied to template and search area, but it is based on the transfer of target
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bfe151185f980b10a2dabc542f7db6c5
https://doi.org/10.1609/aaai.v36i2.20101
https://doi.org/10.1609/aaai.v36i2.20101
Publikováno v:
2022 International Joint Conference on Neural Networks (IJCNN).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3d3095ba3e33c92b8d2636f49cf63c75
https://doi.org/10.1109/ijcnn55064.2022.9891998
https://doi.org/10.1109/ijcnn55064.2022.9891998
Geometric verification is considered a de facto solution for the re-ranking task in image retrieval. In this study, we propose a novel image retrieval re-ranking network named Correlation Verification Networks (CVNet). Our proposed network, comprisin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f5db1a46bdb4a52821067122ab005b2a
http://arxiv.org/abs/2204.01458
http://arxiv.org/abs/2204.01458
Publikováno v:
IEEE Access, Vol 8, Pp 82066-82077 (2020)
Scene recognition is an image recognition problem aimed at predicting the category of the place at which the image is taken. In this paper, a new scene recognition method using the convolutional neural network (CNN) is proposed. The proposed method i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b24ad55d746d25391327714c66341c16
https://doi.org/10.1109/access.2020.2989863
https://doi.org/10.1109/access.2020.2989863
We present a new domain generalized semantic segmentation network named WildNet, which learns domain-generalized features by leveraging a variety of contents and styles from the wild. In domain generalization, the low generalization ability for unsee
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1538645b9a02ec7408ff70145980401c
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