Zobrazeno 51 - 60
of 109
pro vyhledávání: '"Li, Shuai"'
Previous RGB-D salient object detection (SOD) methods have widely adopted deep learning tools to automatically strike a trade-off between RGB and D (depth), whose key rationale is to take full advantage of their complementary nature, aiming for a muc
Externí odkaz:
http://arxiv.org/abs/2008.04157
Existing RGB-D salient object detection methods treat depth information as an independent component to complement its RGB part, and widely follow the bi-stream parallel network architecture. To selectively fuse the CNNs features extracted from both R
Externí odkaz:
http://arxiv.org/abs/2009.05102
Compared with the conventional hand-crafted approaches, the deep learning based methods have achieved tremendous performance improvements by training exquisitely crafted fancy networks over large-scale training sets. However, do we really need large-
Externí odkaz:
http://arxiv.org/abs/2008.02938
With the rapid development of deep learning techniques, image saliency deep models trained solely by spatial information have occasionally achieved detection performance for video data comparable to that of the models trained by both spatial and temp
Externí odkaz:
http://arxiv.org/abs/2008.09103
In deep learning, it is usually assumed that the shape of the loss surface is fixed. Differently, a novel concept of deformation operator is first proposed in this paper to deform the loss surface, thereby improving the optimization. Deformation func
Externí odkaz:
http://arxiv.org/abs/2007.12515
Contextual bandit algorithms are commonly used in recommender systems, where content popularity can change rapidly. These algorithms continuously learn latent mappings between users and items, based on contexts associated with them both. Recent recom
Externí odkaz:
http://arxiv.org/abs/2007.08061
Recurrent neural networks (RNNs) are widely used as a memory model for sequence-related problems. Many variants of RNN have been proposed to solve the gradient problems of training RNNs and process long sequences. Although some classical models have
Externí odkaz:
http://arxiv.org/abs/2005.13867
Deep learning (DL) has been applied extensively in many computational imaging problems, often leading to superior performance over traditional iterative approaches. However, two important questions remain largely unanswered: first, how well can the t
Externí odkaz:
http://arxiv.org/abs/2004.06355
This paper proposes fractional order graph neural networks (FGNNs), optimized by the approximation strategy to address the challenges of local optimum of classic and fractional graph neural networks which are specialised at aggregating information fr
Externí odkaz:
http://arxiv.org/abs/2001.04026
We analyze the Gambler's problem, a simple reinforcement learning problem where the gambler has the chance to double or lose the bets until the target is reached. This is an early example introduced in the reinforcement learning textbook by Sutton an
Externí odkaz:
http://arxiv.org/abs/2001.00102