Zobrazeno 1 - 10
of 113
pro vyhledávání: '"Song, Andy"'
Self-attention mechanism is the key of the Transformer but often criticized for its computation demands. Previous token pruning works motivate their methods from the view of computation redundancy but still need to load the full network and require s
Externí odkaz:
http://arxiv.org/abs/2404.05657
Training-free metrics (a.k.a. zero-cost proxies) are widely used to avoid resource-intensive neural network training, especially in Neural Architecture Search (NAS). Recent studies show that existing training-free metrics have several limitations, su
Externí odkaz:
http://arxiv.org/abs/2403.04161
Learning the underlying Bayesian Networks (BNs), represented by directed acyclic graphs (DAGs), of the concerned events from purely-observational data is a crucial part of evidential reasoning. This task remains challenging due to the large and discr
Externí odkaz:
http://arxiv.org/abs/2209.02946
Neural architecture search (NAS) aims to automate architecture engineering in neural networks. This often requires a high computational overhead to evaluate a number of candidate networks from the set of all possible networks in the search space duri
Externí odkaz:
http://arxiv.org/abs/2204.12726
Person re-identification (Re-ID) has been a significant research topic in the past decade due to its real-world applications and research significance. While supervised person Re-ID methods achieve superior performance over unsupervised counterparts,
Externí odkaz:
http://arxiv.org/abs/2109.06057
Autor:
Rahaman, Mohammad Saiedur, Shao, Wei, Salim, Flora D., Turky, Ayad, Song, Andy, Chan, Jeffrey, Jiang, Junliang, Bradbrook, Doug
Existing parking recommendation solutions mainly focus on finding and suggesting parking spaces based on the unoccupied options only. However, there are other factors associated with parking spaces that can influence someone's choice of parking such
Externí odkaz:
http://arxiv.org/abs/2106.07384
Autor:
Shao, Wei, Zhang, Yu, Xiao, Pengfei, Qin, Kyle Kai, Rahaman, Mohammad Saiedur, Chan, Jeffrey, Guo, Bin, Song, Andy, Salim, Flora D.
Publikováno v:
In Pervasive and Mobile Computing January 2024 97
Autor:
Shao, Wei, Zhao, Sichen, Zhang, Zhen, Wang, Shiyu, Rahaman, Mohammad Saiedur, Song, Andy, Salim, Flora Dilys
Existing research on parking availability sensing mainly relies on extensive contextual and historical information. In practice, the availability of such information is a challenge as it requires continuous collection of sensory signals. In this stud
Externí odkaz:
http://arxiv.org/abs/2007.08551
Publikováno v:
Sensors (14248220). Dec2023, Vol. 23 Issue 23, p9598. 19p.
Typical person re-identification (re-ID) methods train a deep CNN to extract deep features and combine them with a distance metric for the final evaluation. In this work, we focus on exploiting the full information encoded in the deep feature to boos
Externí odkaz:
http://arxiv.org/abs/1811.08561