Zobrazeno 1 - 10
of 52
pro vyhledávání: '"Jinqing Qi"'
Publikováno v:
Neurocomputing. 506:300-310
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::63350dabea1dc7915a8319533112fb4e
https://doi.org/10.1016/j.neucom.2022.07.086
https://doi.org/10.1016/j.neucom.2022.07.086
Autor:
Dezhuang Li, Ruoqi Li, Lijun Wang, Yifan Wang, Jinqing Qi, Lu Zhang, Ting Liu, Qingquan Xu, Huchuan Lu
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:1297-1305
We present YOFO (You Only inFer Once), a new paradigm for referring video object segmentation (RVOS) that operates in an one-stage manner. Our key insight is that the language descriptor should serve as target-specific guidance to identify the target
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::45b7b534a0bba6b2fdfa6a57ce2314b1
https://doi.org/10.1609/aaai.v36i2.20017
https://doi.org/10.1609/aaai.v36i2.20017
Publikováno v:
Proceedings of the 30th ACM International Conference on Multimedia.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f41ccb2da87cc7b5ca577099f79d3abd
https://doi.org/10.1145/3503161.3548037
https://doi.org/10.1145/3503161.3548037
Publikováno v:
Neurocomputing. 411:416-427
Though with the rapid development of deep learning, salient object detection methods have achieved increasingly better performance, how to get effective feature representation to predict more accurate saliency maps is still a burning problem we need
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::19b557384146a4a2a8e9b9086c4b101c
https://doi.org/10.1016/j.neucom.2020.06.021
https://doi.org/10.1016/j.neucom.2020.06.021
Publikováno v:
Pattern Recognition and Computer Vision ISBN: 9783031189159
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fe7636670219380e51608f811d4da351
https://doi.org/10.1007/978-3-031-18916-6_24
https://doi.org/10.1007/978-3-031-18916-6_24
Publikováno v:
IEEE Signal Processing Letters. 26:114-118
Salient object detection has received great amount of attention in recent years. In this letter, we propose a novel salient object detection algorithm, which combines the global contextual information along with the low-level edge features. First, we
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::23ffcc5aa1c9300499450f93ed828b3c
https://doi.org/10.1109/lsp.2018.2881835
https://doi.org/10.1109/lsp.2018.2881835
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 44(7)
High-cost pixel-level annotations makes it appealing to train saliency detection models with weak supervision. However, a single weak supervision source hardly contain enough information to train a well-performing model. To this end, we introduce a u
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::325786b3175a66a8664e4354f0a098d0
https://pubmed.ncbi.nlm.nih.gov/33591912
https://pubmed.ncbi.nlm.nih.gov/33591912
Publikováno v:
ACM Multimedia
Recently, with the advance of deep Convolutional Neural Networks (CNNs), person Re-Identification (Re-ID) has witnessed great success in various applications. However, with limited receptive fields of CNNs, it is still challenging to extract discrimi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::51278d295038be98ed0a83a84db49f19
Publikováno v:
Signal Processing. 147:92-100
Eye fixation models, which try to quantitatively predict human eye attended areas in visual fields, have received increasing interest in recent years. In this paper, a novel framework is proposed for the detection of eye fixations. First, a multi-cha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::643ff73567b4a1233a4f733e0c9f3705
https://doi.org/10.1016/j.sigpro.2018.01.003
https://doi.org/10.1016/j.sigpro.2018.01.003
Publikováno v:
International Journal of Computer Vision, 129(9). Springer Netherlands
This paper proposes a new visual tracking algorithm, which leverages the merits of both template matching approaches and classification models for long-term object detection and tracking. To this end, a regression network is learned offline to detect
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::393e223370f4268201e5aded28c054be
https://dare.uva.nl/personal/pure/en/publications/learning-regression-and-verification-networks-for-robust-longterm-tracking(48360e74-75c6-4565-ad81-983de738df04).html
https://dare.uva.nl/personal/pure/en/publications/learning-regression-and-verification-networks-for-robust-longterm-tracking(48360e74-75c6-4565-ad81-983de738df04).html