SIFT meets CNN: A decade survey of instance retrieval

L Zheng, Y Yang, Q Tian - IEEE transactions on pattern …, 2017 - ieeexplore.ieee.org
In the early days, content-based image retrieval (CBIR) was studied with global features.
Since 2003, image retrieval based on local descriptors (de facto SIFT) has been extensively …

A review on human activity recognition using vision‐based method

S Zhang, Z Wei, J Nie, L Huang… - Journal of healthcare …, 2017 - Wiley Online Library
Human activity recognition (HAR) aims to recognize activities from a series of observations
on the actions of subjects and the environmental conditions. The vision‐based HAR …

Momentum contrast for unsupervised visual representation learning

K He, H Fan, Y Wu, S Xie… - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
Abstract We present Momentum Contrast (MoCo) for unsupervised visual representation
learning. From a perspective on contrastive learning as dictionary look-up, we build a …

Unmasking Clever Hans predictors and assessing what machines really learn

S Lapuschkin, S Wäldchen, A Binder… - Nature …, 2019 - nature.com
Current learning machines have successfully solved hard application problems, reaching
high accuracy and displaying seemingly intelligent behavior. Here we apply recent …

Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning

HC Shin, HR Roth, M Gao, L Lu, Z Xu… - IEEE transactions on …, 2016 - ieeexplore.ieee.org
Remarkable progress has been made in image recognition, primarily due to the availability
of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs …

Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery

F Hu, GS Xia, J Hu, L Zhang - Remote Sensing, 2015 - mdpi.com
Learning efficient image representations is at the core of the scene classification task of
remote sensing imagery. The existing methods for solving the scene classification task …

Design principles for industrie 4.0 scenarios

M Hermann, T Pentek, B Otto - 2016 49th Hawaii international …, 2016 - ieeexplore.ieee.org
The increasing integration of the Internet of Everything into the industrial value chain has
built the foundation for the next industrial revolution called Industrie 4.0. Although Industrie …

Cost-sensitive learning of deep feature representations from imbalanced data

SH Khan, M Hayat, M Bennamoun… - IEEE transactions on …, 2017 - ieeexplore.ieee.org
Class imbalance is a common problem in the case of real-world object detection and
classification tasks. Data of some classes are abundant, making them an overrepresented …

Convolutional neural networks for speech recognition

O Abdel-Hamid, A Mohamed, H Jiang… - … on audio, speech …, 2014 - ieeexplore.ieee.org
Recently, the hybrid deep neural network (DNN)-hidden Markov model (HMM) has been
shown to significantly improve speech recognition performance over the conventional …

Spatial pyramid pooling in deep convolutional networks for visual recognition

K He, X Zhang, S Ren, J Sun - IEEE transactions on pattern …, 2015 - ieeexplore.ieee.org
Existing deep convolutional neural networks (CNNs) require a fixed-size (eg, 224 224) input
image. This requirement is “artificial” and may reduce the recognition accuracy for the …