Results 41 to 50 of about 69,407 (212)
Cv-CapsNet: Complex-Valued Capsule Network
IEEE Access, 2019 Capsule network (CapsNet) can recognize the objects by encoding the part-whole relationships in a way similar to our human perceptual system and has already shown its great potential in image classification tasks.
Xinming Cheng +3 more
doaj +1 more source
A Parameter Efficient Multi-Scale Capsule Network
, 2021 Capsule networks consider spatial relationships in an input image. The relationship-based feature propagation in capsule networks shows promising results. However, a large number of trainable parameters limit their widespread use.
Changick Kim +3 more
core +1 more source
Decomposing word embedding with the capsule network [PDF]
Knowledge-Based Systems, 2021 Word sense disambiguation tries to learn the appropriate sense of an ambiguous word in a given context. The existing pre-trained language methods and the methods based on multi-embeddings of word did not explore the power of the unsupervised word embedding sufficiently.
Xin Liu 0054 +6 more
openaire +2 more sources
Offline Signature Identification and Verification Based on Capsule Representations
Cybernetics and Information Technologies, 2020 Offline signature is one of the frequently used biometric traits in daily life and yet skilled forgeries are posing a great challenge for offline signature verification. To differentiate forgeries, a variety of research has been conducted on hand-crafted
Gumusbas Dilara, Yildirim Tulay
doaj +1 more source
Machines, 2022 As scalar neurons of traditional neural networks promote dimension reduction caused by pooling, it is a difficult task to extract the high-dimensional spatial features and long-term correlation of pure signals from the noisy vibration signal.
Youming Wang, Gongqing Cao, Jiali Han
doaj +1 more source
Computer-assisted diagnosis of wireless-capsule endoscopic images using neural network based techniques [PDF]
, 2005 Computerised processing of medical images can ease the search of the representative features in the images. The endoscopic images possess rich information expressed by texture.
M. Boulougoura +5 more
core +1 more source
A Bottom-Up Capsule Network for Hierarchical Image Classification
, 2023 Hierarchical image classification is an arduous task in deep learning and computer vision. It requires classifying multiple image classes following a taxonomy or data hierarchy. This paper introduces a bottom-up hierarchical capsule network (BUH-CapsNet)
Noor, KT +3 more
core +1 more source
CoRR, 2019 Capsule Networks attempt to represent patterns in images in a way that preserves hierarchical spatial relationships. Additionally, research has demonstrated that these techniques may be robust against adversarial perturbations. We present an improvement to training capsule networks with added robustness via non-parametric kernel methods.
Taylor W. Killian +3 more
openaire +2 more sources
Multi-Kernel Capsule Network for Schizophrenia Identification [PDF]
, 2020 Schizophrenia seriously affects the quality of life. To date, both simple (e.g., linear discriminant analysis) and complex (e.g., deep neural network) machine learning methods have been utilized to identify schizophrenia based on functional connectivity ...
Li, Junhua +3 more
core +1 more source
Malware Detection Based on the Feature Selection of a Correlation Information Decision Matrix
Mathematics, 2023 Smartphone apps are closely integrated with our daily lives, and mobile malware has brought about serious security issues. However, the features used in existing traffic-based malware detection techniques have a large amount of redundancy and useless ...
Kai Lu, Jieren Cheng, Anli Yan
doaj +1 more source