Results 11 to 20 of about 2,079,458 (324)
Transfer Learning Based Data Feature Transfer for Fault Diagnosis [PDF]
IEEE Access, 2020 The development of sensor technology provides massive data for data-driven fault diagnosis. In recent years, more and more scholars are studying artificial intelligence technology to solve the bottleneck in fault diagnosis.
Wei Xu, Yi Wan, Tian-Yu Zuo, Xin-Mei Sha
doaj +2 more sources
Attention-based Wav2Text with Feature Transfer Learning [PDF]
2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2017 Conventional automatic speech recognition (ASR) typically performs multi-level pattern recognition tasks that map the acoustic speech waveform into a hierarchy of speech units.
Nakamura, Satoshi +2 more
core +2 more sources
Stimulus blanking reveals contrast-dependent transsaccadic feature transfer. [PDF]
Sci Rep, 2020 Abstract Across saccadic eye movements, the visual system receives two successive static images corresponding to the pre- and the postsaccadic projections of the visual field on the retina. The existence of a mechanism integrating the content of these images is today still a matter of debate.
Grzeczkowski L, Deubel H, Szinte M.
europepmc +5 more sources
Optimization of Feature Transfer Based on Biotriz
SSRN Electronic Journal, 2023 Pengfei Zhou +4 more
openalex +2 more sources
Feature-Supervised Action Modality Transfer [PDF]
2020 25th International Conference on Pattern Recognition (ICPR), 2021 This paper strives for action recognition and detection in video modalities like RGB, depth maps or 3D-skeleton sequences when only limited modality-specific labeled examples are available. For the RGB, and derived optical-flow, modality many large-scale labeled datasets have been made available.
Thoker, F.M., Snoek, C.G.M.
openaire +4 more sources
Using Decoupled Features for Photorealistic Style Transfer
SIAM Journal on Imaging Sciences, 2023 In this work we propose a photorealistic style transfer method for image and video that is based on vision science principles and on a recent mathematical formulation for the deterministic decoupling of sample statistics. The novel aspects of our approach include matching decoupled moments of higher order than in common style transfer approaches, and ...
Trevor Canham +3 more
openaire +3 more sources
Transferable Deep Features for Keyword Spotting [PDF]
International Workshop on Computational Intelligence for Multimedia Understanding (IWCIM), 2018 Publication in the conference proceedings of IWCIM, Kos island, Greece ...
Retsinas, George +2 more
openaire +1 more source
Understanding How Feature Structure Transfers in Transfer Learning [PDF]
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017 Transfer learning transfers knowledge across domains to improve the learning performance. Since feature structures generally represent the common knowledge across different domains, they can be transferred successfully even though the labeling functions across domains differ arbitrarily.
Tongliang Liu, Qiang Yang, Dacheng Tao
openaire +1 more source
IEEE Access, 2020 Machine learning methods have made great development in data-driven fault diagnosis of rolling bearings. But the intelligent fault diagnosis of intershaft bearing faces the following two dilemmas: 1) the fault vibration is extremely weak, and it is ...
Ya He +3 more
doaj +1 more source