Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Wang, Dingheng"'
Publikováno v:
Mach. Intell. Res. (2022)
Visual recognition is currently one of the most important and active research areas in computer vision, pattern recognition, and even the general field of artificial intelligence. It has great fundamental importance and strong industrial needs. Deep
Externí odkaz:
http://arxiv.org/abs/2108.13055
How to effectively and efficiently deal with spatio-temporal event streams, where the events are generally sparse and non-uniform and have the microsecond temporal resolution, is of great value and has various real-life applications. Spiking neural n
Externí odkaz:
http://arxiv.org/abs/2107.11711
Publikováno v:
In Neurocomputing 14 January 2024 565
Autor:
Wang, Dingheng, Wu, Bijiao, Zhao, Guangshe, Yao, Man, Chen, Hengnu, Deng, Lei, Yan, Tianyi, Li, Guoqi
Recurrent neural networks (RNNs) are powerful in the tasks oriented to sequential data, such as natural language processing and video recognition. However, since the modern RNNs, including long-short term memory (LSTM) and gated recurrent unit (GRU)
Externí odkaz:
http://arxiv.org/abs/2008.09342
Deep neural networks (DNNs) have enabled impressive breakthroughs in various artificial intelligence (AI) applications recently due to its capability of learning high-level features from big data. However, the current demand of DNNs for computational
Externí odkaz:
http://arxiv.org/abs/2006.15938
Three dimensional convolutional neural networks (3DCNNs) have been applied in many tasks, e.g., video and 3D point cloud recognition. However, due to the higher dimension of convolutional kernels, the space complexity of 3DCNNs is generally larger th
Externí odkaz:
http://arxiv.org/abs/1912.03647
Publikováno v:
In Neural Networks September 2023 166:410-423
Publikováno v:
In Neurocomputing 1 November 2022 512:52-68
Publikováno v:
In Neural Networks December 2021 144:320-333
Publikováno v:
In Neural Networks September 2021 141:420-432