Zobrazeno 1 - 10
of 77
pro vyhledávání: '"Computer science and engineering::Computing methodologies::Artificial intelligence [Engineering]"'
Publikováno v:
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 42:781-794
Convolutional Neural Networks (CNNs) demonstrate excellent performance in various applications but have high computational complexity. Quantization is applied to reduce the latency and storage cost of CNNs. Among the quantization methods, Binary and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c6142b7f7cc7abdf1d50095b0b143c0
https://doi.org/10.1109/tcad.2022.3184276
https://doi.org/10.1109/tcad.2022.3184276
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 32:8078-8093
Deep Neural Networks (DNN) are gaining higher commercial values in computer vision applications, e.g., image classification, video analytics, etc. This calls for urgent demands of the intellectual property (IP) protection of DNN models. In this paper
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::33e23a706d00c09e679569dbd161ab3d
https://doi.org/10.1109/tcsvt.2022.3184644
https://doi.org/10.1109/tcsvt.2022.3184644
Autor:
Qiao, Zhongzheng, Hu, Minghui, Jiang, Xudong, Suganthan, Ponnuthurai Nagaratnam, Savitha, Ramasamy
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Class-incremental learning (CIL) on multivariate time series (MTS) is an important yet understudied problem. Based on practical privacy-sensitive circumstances, we propose a novel distillation-based strategy using a single-headed classifier without s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4ae4c704b9851cad1d4a7a7b4904ddd1
https://doi.org/10.1109/icassp49357.2023.10094960
https://doi.org/10.1109/icassp49357.2023.10094960
Through advancement of the Vehicle-to-Everything (V2X) network, road safety, energy consumption, and traffic efficiency can be significantly improved. An accurate vehicle trajectory prediction benefits communication traffic management and network res
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::112aafc9676880d8bd7dc4cf4ee3dca5
http://arxiv.org/abs/2303.02880
http://arxiv.org/abs/2303.02880
Publikováno v:
IEEE Design & Test, 39, 4, pp. 7-14
IEEE Design & Test, 39(4)
IEEE Design & Test, 39, 7-14
IEEE Design & Test, 39(4)
IEEE Design & Test, 39, 7-14
Our previous work selected for Top Picks in Hardware and Embedded Security 2020 demonstrates that it is possible to reverse engineer neural networks by using side-channel attacks. We developed a framework that considers each part of the neural networ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f2116810200728847530fafcdd812b4a
https://hdl.handle.net/2066/253563
https://hdl.handle.net/2066/253563
Publikováno v:
IEEE Access, Vol 10, Pp 17881-17896 (2022)
Aircraft trajectory prediction is a challenging problem in air traffic control, especially for conflict detection. Traditional trajectory predictors require a variety of inputs such as flight-plans, aircraft performance models, meteorological forecas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eb1da11206ae5ddfb118c1bbbe964eab
https://doi.org/10.1109/access.2022.3149231
https://doi.org/10.1109/access.2022.3149231
Publikováno v:
SN Computer Science. 4
Personalized dialogue agents are capable of generating responses consistent with a specific persona. Typically, personalized dialogue agents generate responses based on both the dialogue history and a representation of the agent’s desired persona.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e5c5314602d9da5e1223bc6ea323c6df
https://doi.org/10.1007/s42979-022-01548-5
https://doi.org/10.1007/s42979-022-01548-5
Autor:
Nicolas M. Charpentier, Ange A. Maurice, Dong Xia, Wen-Jie Li, Chang-Sian Chua, Andrea Brambilla, Jean-Christophe P. Gabriel
Publikováno v:
Resources, Conservation and Recycling
Resources, Conservation and Recycling, 2023, 196, pp.107033. ⟨10.1016/j.resconrec.2023.107033⟩
Resources, Conservation and Recycling, 2023, 196, pp.107033. ⟨10.1016/j.resconrec.2023.107033⟩
The growing number of electronic devices has led to a surge in e-waste, making efficient recycling essential to reduce environmental impact and recover valuable metals. However, traditional recycling methods struggle to extract them due to their low
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::90eab166663037cc43d7add447af5f21
https://hdl.handle.net/10356/167421
https://hdl.handle.net/10356/167421
Autor:
Wang, Sijie, Kang, Qiyu, She, Rui, Tay, Wee Peng, Hartmannsgruber, Andreas, Navarro, Diego Navarro
Camera relocalization has various applications in autonomous driving. Previous camera pose regression models consider only ideal scenarios where there is little environmental perturbation. To deal with challenging driving environments that may have c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::198ad3f798cee8bd5323dfea74824e0a
https://aaai.org/aaai-publications/aaai-conference-proceedings/
https://aaai.org/aaai-publications/aaai-conference-proceedings/
Publikováno v:
2022 17th International Conference on Control, Automation, Robotics and Vision (ICARCV).
In an Internet of Vehicles (IoV) network, vehicles periodically broadcast Basic Safety Messages (BSMs) that contain the vehicle's current position, speed, and acceleration. Safety-critical applications like blind-spot warning and lane change warning
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::59ffaeac824d93a675eb64e83c3767a7
https://doi.org/10.1109/icarcv57592.2022.10004369
https://doi.org/10.1109/icarcv57592.2022.10004369