Recent advances in convolutional neural networks

J Gu, Z Wang, J Kuen, L Ma, A Shahroudy, B Shuai… - Pattern recognition, 2018 - Elsevier
In the last few years, deep learning has led to very good performance on a variety of
problems, such as visual recognition, speech recognition and natural language processing …

Automated plant species identification—Trends and future directions

J Wäldchen, M Rzanny, M Seeland… - PLoS computational …, 2018 - journals.plos.org
Current rates of species loss triggered numerous attempts to protect and conserve
biodiversity. Species conservation, however, requires species identification skills, a …

Attentive region embedding network for zero-shot learning

GS **e, L Liu, X **, F Zhu, Z Zhang… - Proceedings of the …, 2019 - openaccess.thecvf.com
Zero-shot learning (ZSL) aims to classify images from unseen categories, by merely utilizing
seen class images as the training data. Existing works on ZSL mainly leverage the global …

Mask-CNN: Localizing parts and selecting descriptors for fine-grained bird species categorization

XS Wei, CW **e, J Wu, C Shen - Pattern Recognition, 2018 - Elsevier
Fine-grained image recognition is a challenging computer vision problem, due to the small
inter-class variations caused by highly similar subordinate categories, and the large intra …

Region graph embedding network for zero-shot learning

GS **e, L Liu, F Zhu, F Zhao, Z Zhang, Y Yao… - Computer Vision–ECCV …, 2020 - Springer
Most of the existing Zero-Shot Learning (ZSL) approaches learn direct embeddings from
global features or image parts (regions) to the semantic space, which, however, fail to …

Semantic-aware scene recognition

A López-Cifuentes, M Escudero-Vinolo, J Bescós… - Pattern Recognition, 2020 - Elsevier
Scene recognition is currently one of the top-challenging research fields in computer vision.
This may be due to the ambiguity between classes: images of several scene classes may …

Automatic classification of pavement distress using 3D ground-penetrating radar and deep convolutional neural network

X Liang, X Yu, C Chen, Y **… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
The realization of nondestructive detection and classification of pavement distress is of great
significance for putting forward a reasonable maintenance scheme and prolonging the …

Flower classification using deep convolutional neural networks

H Hiary, H Saadeh, M Saadeh, M Yaqub - IET computer vision, 2018 - Wiley Online Library
Flower classification is a challenging task due to the wide range of flower species, which
have a similar shape, appearance or surrounding objects such as leaves and grass. In this …

Multifaceted fused-CNN based scoring of breast cancer whole-slide histopathology images

N Wahab, A Khan - Applied Soft Computing, 2020 - Elsevier
Automating the scoring of Whole-Slide Images (WSIs) is a challenging task because the
search space for selecting region of interest (ROI) is huge due to the very large sizes of …

TA-CNN: Two-way attention models in deep convolutional neural network for plant recognition

Y Zhu, W Sun, X Cao, C Wang, D Wu, Y Yang, N Ye - Neurocomputing, 2019 - Elsevier
Automatic plant recognition using AI is a challenging problem. In addition to the recognition
of the plant specimen, we also want to recognize the plant type in its actual living …