A comprehensive survey on applications of transformers for deep learning tasks

S Islam, H Elmekki, A Elsebai, J Bentahar… - Expert Systems with …, 2024‏ - Elsevier
Abstract Transformers are Deep Neural Networks (DNN) that utilize a self-attention
mechanism to capture contextual relationships within sequential data. Unlike traditional …

A review on automatic image annotation techniques

D Zhang, MM Islam, G Lu - Pattern Recognition, 2012‏ - Elsevier
Nowadays, more and more images are available. However, to find a required image for an
ordinary user is a challenging task. Large amount of researches on image retrieval have …

Precise no-reference image quality evaluation based on distortion identification

C Yan, T Teng, Y Liu, Y Zhang, H Wang… - ACM Transactions on …, 2021‏ - dl.acm.org
The difficulty of no-reference image quality assessment (NR IQA) often lies in the lack of
knowledge about the distortion in the image, which makes quality assessment blind and …

Multiple feature reweight densenet for image classification

K Zhang, Y Guo, X Wang, J Yuan, Q Ding - IEEE access, 2019‏ - ieeexplore.ieee.org
Recent network research has demonstrated that the performance of convolutional neural
networks can be improved by introducing a learning block that captures spatial correlations …

Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories

S Lazebnik, C Schmid, J Ponce - 2006 IEEE computer society …, 2006‏ - ieeexplore.ieee.org
This paper presents a method for recognizing scene categories based on approximate
global geometric correspondence. This technique works by partitioning the image into …

Modeling the shape of the scene: A holistic representation of the spatial envelope

A Oliva, A Torralba - International journal of computer vision, 2001‏ - Springer
In this paper, we propose a computational model of the recognition of real world scenes that
bypasses the segmentation and the processing of individual objects or regions. The …

Recognizing indoor scenes

A Quattoni, A Torralba - 2009 IEEE conference on computer …, 2009‏ - ieeexplore.ieee.org
Indoor scene recognition is a challenging open problem in high level vision. Most scene
recognition models that work well for outdoor scenes perform poorly in the indoor domain …

Learning multi-label scene classification

MR Boutell, J Luo, X Shen, CM Brown - Pattern recognition, 2004‏ - Elsevier
In classic pattern recognition problems, classes are mutually exclusive by definition.
Classification errors occur when the classes overlap in the feature space. We examine a …

A bayesian hierarchical model for learning natural scene categories

L Fei-Fei, P Perona - … vision and pattern recognition (CVPR'05), 2005‏ - ieeexplore.ieee.org
We propose a novel approach to learn and recognize natural scene categories. Unlike
previous work, it does not require experts to annotate the training set. We represent the …

SIMPLIcity: Semantics-sensitive integrated matching for picture libraries

JZ Wang, J Li, G Wiederhold - IEEE Transactions on pattern …, 2001‏ - ieeexplore.ieee.org
We present here SIMPLIcity (semantics-sensitive integrated matching for picture libraries),
an image retrieval system, which uses semantics classification methods, a wavelet-based …