Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Jiaxu, Leng"'
Few-shot object detection, learning to adapt to the novel classes with a few labeled data, is an imperative and long-lasting problem due to the inherent long-tail distribution of real-world data and the urgent demands to cut costs of data collection
Externí odkaz:
http://arxiv.org/abs/2111.00201
Publikováno v:
Frontiers in Physics, Vol 10 (2023)
Prohibited item detection in X-ray images is an effective measure to maintain public safety. Recent prohibited item detection methods based on deep learning has achieved impressive performance. Some methods improve prohibited item detection performan
Externí odkaz:
https://doaj.org/article/c0fefe4634cc4d8f973285dc6afb4ab3
Publikováno v:
Neurocomputing. 536:137-151
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::03c1876fc25dfa729ebeb9c31553513e
https://doi.org/10.1016/j.neucom.2023.03.003
https://doi.org/10.1016/j.neucom.2023.03.003
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 33:1320-1334
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::328c4afb65c823173ddfb37938289374
https://doi.org/10.1109/tcsvt.2022.3210207
https://doi.org/10.1109/tcsvt.2022.3210207
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 33:118-131
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5f9c52ee603772d6978e3ed704f3904c
https://doi.org/10.1109/tcsvt.2022.3199325
https://doi.org/10.1109/tcsvt.2022.3199325
Autor:
Jiaxu Leng, Ying Liu
Publikováno v:
IEEE Access, Vol 6, Pp 24256-24263 (2018)
Robust scale estimation and occlusion handling are two challenging problems in visual target tracking. Most existing methods do not perform well with complex image sequences, especially those with scale changes and partial occlusion. In this paper, a
Externí odkaz:
https://doaj.org/article/1b6cecc2b6da4a19afeed575decd93ec
Publikováno v:
Neurocomputing. 511:54-66
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5d8899d9ad9157910c7bb44683b9cedf
https://doi.org/10.1016/j.neucom.2022.09.040
https://doi.org/10.1016/j.neucom.2022.09.040
Publikováno v:
ACM Transactions on Graphics. 42:1-17
Humans remain far better than machines at learning, where humans require fewer examples to learn new concepts and can use those concepts in richer ways. Take handwriting as an example, after learning from very limited handwriting scripts, a person ca
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d963ab75b7dcf0e7417be1add20a7679
https://doi.org/10.1145/3550070
https://doi.org/10.1145/3550070
Publikováno v:
Pattern Recognition Letters. 159:9-15
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dda5a3e2b8572c7df12511a7d2d199e2
https://doi.org/10.1016/j.patrec.2022.04.029
https://doi.org/10.1016/j.patrec.2022.04.029
Publikováno v:
Applied Intelligence. 53:4431-4447
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::794b7f74876af29669a3796d39146671
https://doi.org/10.1007/s10489-022-03636-8
https://doi.org/10.1007/s10489-022-03636-8