Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Bohan Zhuang"'
Publikováno v:
Plant Methods, Vol 13, Iss 1, Pp 1-17 (2017)
Abstract Background Accurately counting maize tassels is important for monitoring the growth status of maize plants. This tedious task, however, is still mainly done by manual efforts. In the context of modern plant phenotyping, automating this task
Externí odkaz:
https://doaj.org/article/89ad99b0e1b14211b53f9f3497cea18c
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. :1-14
Network pruning and quantization are proven to be effective ways for deep model compression. To obtain a highly compact model, most methods first perform network pruning and then conduct network quantization based on the pruned model. However, this s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e7d117317fc52b1b37f093e40ea2d718
https://doi.org/10.1109/tpami.2023.3275159
https://doi.org/10.1109/tpami.2023.3275159
Autor:
Chunlei Liu, Wenrui Ding, Peng Chen, Bohan Zhuang, Yufeng Wang, Yang Zhao, Baochang Zhang, Yuqi Han
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 32:6414-6424
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0104cbc78c89610212afd58c67b3119d
https://doi.org/10.1109/tcsvt.2022.3166803
https://doi.org/10.1109/tcsvt.2022.3166803
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:2091-2099
Binary Neural Networks (BNNs) have received significant attention due to the memory and computation efficiency recently. However, the considerable accuracy gap between BNNs and their full-precision counterparts hinders BNNs to be deployed to resource
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1390dc7fc606d9b5e2a0896a4c88a10f
https://doi.org/10.1609/aaai.v35i3.16306
https://doi.org/10.1609/aaai.v35i3.16306
Recent advances in vision Transformers (ViTs) have come with a voracious appetite for computing power, high-lighting the urgent need to develop efficient training methods for ViTs. Progressive learning, a training scheme where the model capacity grow
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4a4a989caf4538dda74853ae8e82c9e4
http://arxiv.org/abs/2203.14509
http://arxiv.org/abs/2203.14509
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198298
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9bc4f5070119b3fabf9682d3fe21fdf9
https://doi.org/10.1007/978-3-031-19830-4_21
https://doi.org/10.1007/978-3-031-19830-4_21
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. :1-1
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1c02cc5ce5238856126f8c68e5203dd4
https://doi.org/10.1109/tcsvt.2023.3279281
https://doi.org/10.1109/tcsvt.2023.3279281
Study on Photocatalytic Desulfurization and Denitrification Performance of Cu- and Cr-Modified MWCNT
Publikováno v:
Processes, Vol 9, Iss 1823, p 1823 (2021)
Processes
Volume 9
Issue 10
Processes
Volume 9
Issue 10
Carbon nanotubes are a promising adsorbent for desulfurization and denitrification. In this paper, Cu- and Cr-doped TiO2 supported by multi-walled carbon nanotubes (MWCNTs/Cu-Cr-TiO2) were synthesized by the sol-gel method. Characterizations of the s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b5572b687e7768e02552315cd29d6f74
https://www.mdpi.com/2227-9717/9/10/1823
https://www.mdpi.com/2227-9717/9/10/1823
Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision. However, Transformer training and inference in previous works can be prohi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4024879a7339acc7675238ce80029b67
Publikováno v:
ACM Multimedia
With the rising popularity of intelligent mobile devices, it is of great practical significance to develop accurate, realtime and energy-efficient image Super-Resolution (SR) inference methods. A prevailing method for improving the inference efficien
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::014171186e68b4793c593c39995312be
http://arxiv.org/abs/2011.14265
http://arxiv.org/abs/2011.14265