CNN architectures for geometric transformation-invariant feature representation in computer vision: a review

A Mumuni, F Mumuni - SN Computer Science, 2021 - Springer
One of the main challenges in machine vision relates to the problem of obtaining robust
representation of visual features that remain unaffected by geometric transformations. This …

[HTML][HTML] Bone metastasis classification using whole body images from prostate cancer patients based on convolutional neural networks application

N Papandrianos, E Papageorgiou, A Anagnostis… - PloS one, 2020 - journals.plos.org
Bone metastasis is one of the most frequent diseases in prostate cancer; scintigraphy
imaging is particularly important for the clinical diagnosis of bone metastasis. Up to date …

[HTML][HTML] A deep-learning approach for diagnosis of metastatic breast cancer in bones from whole-body scans

N Papandrianos, E Papageorgiou, A Anagnostis… - Applied Sciences, 2020 - mdpi.com
(1) Background: Bone metastasis is one of the most frequent diseases in breast, lung and
prostate cancer; bone scintigraphy is the primary imaging method of screening that offers the …

Robust appearance modeling for object detection and tracking: a survey of deep learning approaches

A Mumuni, F Mumuni - Progress in Artificial Intelligence, 2022 - Springer
The task of object detection and tracking is one of the most complex and challenging
problems in artificial intelligence (AI) systems that model perception. Object tracking has …

Deep feature fusion through adaptive discriminative metric learning for scene recognition

C Wang, G Peng, B De Baets - Information Fusion, 2020 - Elsevier
With the development of deep learning techniques, fusion of deep features has
demonstrated the powerful capability to improve recognition performance. However, most …

[HTML][HTML] Human-centered deep compositional model for handling occlusions

G Koporec, J Perš - Pattern Recognition, 2023 - Elsevier
Despite their powerful discriminative abilities, Convolutional Neural Networks (CNNs) lack
the properties of generative models. This leads to a decreased performance in environments …

[HTML][HTML] Industrial Machinery Components Classification: A Case of DS Pooling

A Batool, Y Dai, H Ma, S Yin - Symmetry, 2023 - mdpi.com
Industries are increasingly shifting towards unmanned and intelligent systems that require
efficient processing and monitoring of structures across various applications, ranging from …

[引用][C] Discriminative metric learning for scene recognition based on deep features

C Wang - 2022 - biblio.ugent.be
With the popularization of the Internet and mobile smart devices, imaging technology has
been well developed, and the spatial resolution of images has been greatly improved …