scholarly journals Human Attribute Recognition— A Comprehensive Survey

2020 ◽  
Vol 10 (16) ◽  
pp. 5608
Author(s):  
Ehsan Yaghoubi ◽  
Farhad Khezeli ◽  
Diana Borza ◽  
SV Aruna Kumar ◽  
João Neves ◽  
...  
Keyword(s):  
Pattern Recognition ◽  
Deep Learning ◽  
Algorithm Design ◽  
Research Field ◽  
Highly Active ◽  
Depth Analysis ◽  
Comprehensive Survey ◽  
Attribute Recognition ◽  
Active Research ◽  
Comprehensive Discussion

Human Attribute Recognition (HAR) is a highly active research field in computer vision and pattern recognition domains with various applications such as surveillance or fashion. Several approaches have been proposed to tackle the particular challenges in HAR. However, these approaches have dramatically changed over the last decade, mainly due to the improvements brought by deep learning solutions. To provide insights for future algorithm design and dataset collections, in this survey, (1) we provide an in-depth analysis of existing HAR techniques, concerning the advances proposed to address the HAR’s main challenges; (2) we provide a comprehensive discussion over the publicly available datasets for the development and evaluation of novel HAR approaches; (3) we outline the applications and typical evaluation metrics used in the HAR context.

scholarly journals A Green Prospective for Learned Post-processing in Sparse-view Tomographic Reconstruction

2021 ◽  
Author(s):  
Elena Morotti ◽  
Davide Evangelista ◽  
Elena Loli Piccolomini
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Tomographic Reconstruction ◽  
Research Field ◽  
Filtered Backprojection ◽  
Post Processing ◽  
Training Set ◽  
Imaging Reconstruction ◽  
Active Research

Deep Learning is developing interesting tools which are of great interest for inverse imaging applications. In this work, we consider a medical imaging reconstruction task from subsampled measurements, which is an active research field where Convolutional Neural Networks have already revealed their great potential. However, the commonly used architectures are very deep and, hence, prone to overfitting and unfeasible for clinical usages. Inspired by the ideas of the green-AI literature, we here propose a shallow neural network to perform an efficient Learned Post-Processing on images roughly reconstructed by the filtered backprojection algorithm. The results obtained on images from the training set and on unseen images, using both the non-expensive network and the widely used very deep ResUNet show that the proposed network computes images of comparable or higher quality in about one fourth of time.

Mining Hidden Association Rules from Real-Life Data

2010 ◽  
pp. 168-184
Author(s):  
Marco-Antonio Balderas Cepeda
Keyword(s):  
Association Rules ◽  
Real Life ◽  
Research Field ◽  
Good Reliability ◽  
Highly Active ◽  
Network Intrusion ◽  
Real Life Data ◽  
Alternative Approach ◽  
Rule Sets ◽  
Active Research

Association rule mining has been a highly active research field over the past decade. Extraction of frequency-related patterns has been applied to several domains. However, the way association rules are defined has limited people’s ability to obtain all the patterns of interest. In this chapter, the authors present an alternative approach that allows us to obtain new kinds of association rules that represent deviations from common behaviors. These new rules are called anomalous rules. To obtain such rules requires that we extract all the most frequent patterns together with certain extension patterns that may occur very infrequently. An approach that relies on anomalous rules has possible application in the areas of counterterrorism, fraud detection, pharmaceutical data analysis and network intrusion detection. They provide an adaption of measures of interest to our anomalous rule sets, and we propose an algorithm that can extract anomalous rules as well. Their experiments with benchmark and real-life datasets suggest that the set of anomalous rules is smaller than the set of association rules. Their work also provides evidence that our proposed approach can discover hidden patterns with good reliability.

scholarly journals Neural Machine Reading Comprehension: Methods and Trends

2019 ◽  
Vol 9 (18) ◽  
pp. 3698 ◽  
Author(s):  
Shanshan Liu ◽  
Xin Zhang ◽  
Sheng Zhang ◽  
Hui Wang ◽  
Weiming Zhang
Keyword(s):  
Reading Comprehension ◽  
Deep Learning ◽  
Research Field ◽  
The Past ◽  
Learning Techniques ◽  
Comprehensive Survey ◽  
Recent Trends ◽  
General Architecture ◽  
Machine Reading ◽  
Open Issues

Machine reading comprehension (MRC), which requires a machine to answer questions based on a given context, has attracted increasing attention with the incorporation of various deep-learning techniques over the past few years. Although research on MRC based on deep learning is flourishing, there remains a lack of a comprehensive survey summarizing existing approaches and recent trends, which motivated the work presented in this article. Specifically, we give a thorough review of this research field, covering different aspects including (1) typical MRC tasks: their definitions, differences, and representative datasets; (2) the general architecture of neural MRC: the main modules and prevalent approaches to each; and (3) new trends: some emerging areas in neural MRC as well as the corresponding challenges. Finally, considering what has been achieved so far, the survey also envisages what the future may hold by discussing the open issues left to be addressed.

scholarly journals RECORDING AND MODELLING OF MONUMENTS' INTERIOR SPACE USING RANGE AND OPTICAL SENSORS

2016 ◽  
Vol XLI-B5 ◽  
pp. 939-944
Author(s):  
Charalampos Georgiadis ◽  
Petros Patias ◽  
Vasilios Tsioukas
Keyword(s):  
Optical Sensors ◽  
Laser Scanning ◽  
Three Dimensional ◽  
Point Clouds ◽  
Research Field ◽  
Interior Space ◽  
Range Camera ◽  
Highly Active ◽  
Fixed Base ◽  
Active Research

Three dimensional modelling of artefacts and building interiors is a highly active research field in our days. Several techniques are being utilized to perform such a task, spanning from traditional surveying techniques and photogrammetry to structured light scanners, laser scanners and so on. New technological advancements in both hardware and software create new recording techniques, tools and approaches. In this paper we present a new recording and modelling approach based on the SwissRanger SR4000 range camera coupled with a Canon 400D dSLR camera. The hardware component of our approach consists of a fixed base, which encloses the range and SLR cameras. The two sensors are fully calibrated and registered to each other thus we were able to produce colorized point clouds acquired from the range camera. In this paper we present the initial design and calibration of the system along with experimental data regarding the accuracy of the proposed approach. We are also providing results regarding the modelling of interior spaces and artefacts accompanied with accuracy tests from other modelling approaches based on photogrammetry and laser scanning.

scholarly journals You can Try without Visiting: A Comprehensive Survey on Virtually Try-on Outfits

2021 ◽  
Author(s):  
Hajer Ghodhbani ◽  
Adel Alimi ◽  
Mohamed Neji ◽  
Imran Razzak
Keyword(s):  
Deep Learning ◽  
Literature Review ◽  
Research Field ◽  
Future Research ◽  
Fashion Industry ◽  
Research Directions ◽  
Comprehensive Literature Review ◽  
Benchmark Datasets ◽  
Comprehensive Survey ◽  
Future Research Directions

<p>Our work aims to conduct a comprehensive literature review of deep learning methods applied in the fashion industry and, especially, the image-based virtual fitting task by citing research works published in the last years. We have summarized their challenges, their main frameworks, the popular benchmark datasets, and the different evaluation metrics. Also, some promising future research directions are discussed to propose improvements in this research field.</p>

A Review of Deep Machine Learning

2016 ◽  
Vol 24 ◽  
pp. 124-136 ◽  
Author(s):  
Ben Bright Benuwa ◽  
Yong Zhao Zhan ◽  
Benjamin Ghansah ◽  
Dickson Keddy Wornyo ◽  
Frank Banaseka Kataka
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Paradigm Shift ◽  
State Of The Art ◽  
Learning Algorithms ◽  
Algorithm Design ◽  
Prior State ◽  
Art Techniques

The rapid increase of information and accessibility in recent years has activated a paradigm shift in algorithm design for artificial intelligence. Recently, deep learning (a surrogate of Machine Learning) have won several contests in pattern recognition and machine learning. This review comprehensively summarises relevant studies, much of it from prior state-of-the-art techniques. This paper also discusses the motivations and principles regarding learning algorithms for deep architectures.

scholarly journals Human Attribute Recognition: A Comprehensive Survey

2020 ◽  
Author(s):  
Ehsan Yaghoubi ◽  
Farhad Khezeli ◽  
Diana Borza ◽  
SV Aruna Kumar ◽  
João Neves ◽  
...  
Keyword(s):  
Deep Learning ◽  
Evaluation Metrics ◽  
Learning Approaches ◽  
Comprehensive Review ◽  
Comprehensive Survey ◽  
Attribute Recognition

Over the last decade, the field of Human Attribute Recognition (HAR) has dramatically changed, mainly due to the improvements brought by deep learning solutions. This survey reviews the progress obtained in HAR, considering the transition from the traditional hand-crafted to deep-learning approaches. The most relevant works on the field are analyzed concerning the advances proposed to address the HAR's typical challenges. Furthermore, we outline the applications and typical evaluation metrics used in the HAR context. Finally, we provide a comprehensive review of the publicly available datasets for the development and evaluation of novel HAR approaches.

Gene Subset Selection for Leukemia Classification Using Microarray Data

2019 ◽  
Vol 14 (4) ◽  
pp. 353-358 ◽  
Author(s):  
Mohamed Nisper Fathima Fajila
Keyword(s):  
Evolutionary Algorithm ◽  
Microarray Data ◽  
Gene Selection ◽  
Subset Selection ◽  
Research Field ◽  
Small Subset ◽  
Gene Subset ◽  
Highly Active ◽  
Selection Gene ◽  
Active Research

Background: Cancer subtype identification is an active research field which helps in the diagnosis of various cancers with proper treatments. Leukemia is one such cancer with various subtypes. High throughput technologies such as Deoxyribo Nucleic Acid (DNA) microarray are highly active in the field of cancer detection and classification alternatively. Objective: Yet, a precise analysis is important in microarray data applications as microarray experiments provide huge amount of data. Gene selection techniques promote microarray usage in the field of medicine. The objective of gene selection is to select a small subset of genes, which are the most informative in classification. associations while known disease-lncRNA associations are required only. Method: In this study, multi-objective evolutionary algorithm is used for gene subset selection in Leukemia classification. An initial redundant and irrelevant gene removal is followed by multiobjective evolutionary based gene subset selection. Gene subset selection highly influences the perfect classification. Thus, selecting the appropriate algorithm for subset selection is important. Results: The performance of the proposed method is compared against the standard genetic algorithm and evolutionary algorithm. Three Leukemia microarray datasets were used to evaluate the performance of the proposed method. Perfect classification was achieved for all the datasets only with few significant genes using the proposed approach. Conclusion: Thus, it is obvious that the proposed study perfectly classifies Leukemia with only few significant genes.</P>

scholarly journals Simulation and Experimental Evaluation of the EKF Simultaneous Localization and Mapping Algorithm on the Wifibot Mobile Robot

2018 ◽  
Vol 8 (2) ◽  
pp. 91-101 ◽  
Author(s):  
Noura Ayadi ◽  
Nabil Derbel ◽  
Nicolas Morette ◽  
Cyril Novales ◽  
Gérard Poisson
Keyword(s):  
Mobile Robot ◽  
Autonomous Navigation ◽  
Large Scale ◽  
Simultaneous Localization And Mapping ◽  
Research Field ◽  
Small Scale ◽  
Mapping Algorithm ◽  
Highly Active ◽  
Localization And Mapping ◽  
Active Research

Abstract In recent years, autonomous navigation for mobile robots has been considered a highly active research field. Within this context, we are interested to apply the Simultaneous Localization And Mapping (SLAM) approach for a wheeled mobile robot. The Extended Kalman Filter has been chosen to perform the SLAM algorithm. In this work, we explicit all steps of the approach. Performances of the developed algorithm have been assessed through simulation in the case of a small scale map. Then, we present several experiments on a real robot that are proceeded in order to exploit a programmed SLAM unit and to generate the navigation map. Based on experimental results, simulation of the SLAM method in the case of a large scale map is then realized. Obtained results are exploited in order to evaluate and compare the algorithm’s consistency and robustness for both cases.

scholarly journals 3D Point Cloud Semantic Augmentation: Instance Segmentation of 360° Panoramas by Deep Learning Techniques

2021 ◽  
Vol 13 (18) ◽  
pp. 3647
Author(s):  
Ghizlane Karara ◽  
Rafika Hajji ◽  
Florent Poux
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Point Cloud ◽  
Point Clouds ◽  
Research Field ◽  
Virtual Camera ◽  
3D Point Clouds ◽  
Active Research ◽  
2D Images ◽  
Instance Segmentation

Semantic augmentation of 3D point clouds is a challenging problem with numerous real-world applications. While deep learning has revolutionised image segmentation and classification, its impact on point cloud is an active research field. In this paper, we propose an instance segmentation and augmentation of 3D point clouds using deep learning architectures. We show the potential of an indirect approach using 2D images and a Mask R-CNN (Region-Based Convolution Neural Network). Our method consists of four core steps. We first project the point cloud onto panoramic 2D images using three types of projections: spherical, cylindrical, and cubic. Next, we homogenise the resulting images to correct the artefacts and the empty pixels to be comparable to images available in common training libraries. These images are then used as input to the Mask R-CNN neural network, designed for 2D instance segmentation. Finally, the obtained predictions are reprojected to the point cloud to obtain the segmentation results. We link the results to a context-aware neural network to augment the semantics. Several tests were performed on different datasets to test the adequacy of the method and its potential for generalisation. The developed algorithm uses only the attributes X, Y, Z, and a projection centre (virtual camera) position as inputs.

Sign in / Sign up

Export Citation Format

Share Document