Zobrazeno 1 - 10
of 47
pro vyhledávání: '"Minsi Wang"'
Publikováno v:
European Food Research and Technology. 248:85-94
A rapid and sensitive immunoassay for the simultaneous detection of thiabendazole (TBZ) and carbendazim (CBZ) was developed by using magnetic nanoparticles (MNPs) and two-color upconversion nanoparticles (UCNPs). The anti-thiabendazole and anti-carbe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8dc787cf32963cc6ae969428c4db7b75
https://doi.org/10.1007/s00217-021-03853-4
https://doi.org/10.1007/s00217-021-03853-4
Publikováno v:
IEEE Transactions on Multimedia. 22:215-228
Hashing has been widely used in large-scale image retrieval based on approximate nearest neighbor search. Most learning-to-hashing methods adopt a two-stage algorithm to generate binary codes. First, original images are mapped into continuous visual
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::478b5c235d519ba135d354bc1044ed1e
https://doi.org/10.1109/tmm.2019.2922130
https://doi.org/10.1109/tmm.2019.2922130
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f7bb62c3bb7ed9cc994e98962fee909d
https://doi.org/10.1109/iccv48922.2021.00850
https://doi.org/10.1109/iccv48922.2021.00850
Autor:
Shuo Cheng, Jiale Bai, Minsi Wang, Xiaokang Yang, Wen Gao, Chuanping Hu, Bingbing Ni, Zefan Li
Publikováno v:
IEEE Transactions on Multimedia. 21:3178-3193
Hashing is a widely adopted method based on an approximate nearest neighbor search and is used in large-scale image retrieval tasks. Conventional learning-based hashing algorithms employ end-to-end representation learning, which is a one-off techniqu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::19f1262f73100a468b72f84402f3d9b5
https://doi.org/10.1109/tmm.2019.2920601
https://doi.org/10.1109/tmm.2019.2920601
Publikováno v:
CVPR
In this work, we propose a Cross-view Contrastive Learning framework for unsupervised 3D skeleton-based action Representation (CrosSCLR), by leveraging multi-view complementary supervision signal. CrosSCLR consists of both single-view contrastive lea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3d4cd05e5adeb4d5daad2ec0c85ad3e1
http://arxiv.org/abs/2104.14466
http://arxiv.org/abs/2104.14466
Publikováno v:
CVPR
Most human activity analysis works (i.e., recognition or prediction) only focus on a single granularity, i.e., either modelling global motion based on the coarse level movement such as human trajectories or forecasting future detailed action based on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8218d06ae17a98a9cac586c97cccec7a
https://doi.org/10.1109/cvpr.2018.00239
https://doi.org/10.1109/cvpr.2018.00239
Publikováno v:
CVPR
Crowd counting or density estimation is a challenging task in computer vision due to large scale variations, perspective distortions and serious occlusions, etc. Existing methods generally suffer from two issues: 1) the model averaging effects in mul
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::58c6abcbdacec2d09ded2167e4a2d981
https://doi.org/10.1109/cvpr.2018.00550
https://doi.org/10.1109/cvpr.2018.00550
Publikováno v:
CVPR
Despite recent emergence of video caption methods, how to generate fine-grained video descriptions (i.e., long and detailed commentary about individual movements of multiple subjects as well as their frequent interactions) is far from being solved, w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e15e2e9a1a4ab7bb5ad28e081e6c6078
https://doi.org/10.1109/cvpr.2018.00629
https://doi.org/10.1109/cvpr.2018.00629
Autor:
Chen Yao, Hanjiang Lai, Chuanping Hu, Jiale Bai, Chongyang Zhang, Lin Mei, Yang Shen, Bingbing Ni, Minsi Wang
Publikováno v:
ACM Multimedia
This paper proposes a novel recursive hashing scheme, in contrast to conventional "one-off" based hashing algorithms. Inspired by human's "nonsalient-to-salient" perception path, the proposed hashing scheme generates a series of binary codes based on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d1af0a76e90e1ea1fb2d6b71daaf17c1
https://doi.org/10.1145/3123266.3123280
https://doi.org/10.1145/3123266.3123280
Publikováno v:
ICIP
The models based on deep convolutional networks and recurrent neural networks have dominated in recent image caption generation tasks. Performance and complexity are still eternal topic. Inspired by recent work, by combining the advantages of simple
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::20be4f4372905dcdc593743c14438368
https://doi.org/10.1109/icip.2016.7533201
https://doi.org/10.1109/icip.2016.7533201