scholarly journals Graph Convolutional Networks for Cross-Modal Information Retrieval

2022 ◽  
Vol 2022 ◽  
pp. 1-8
Author(s):  
Xianben Yang ◽  
Wei Zhang
Keyword(s):  
Computer Vision ◽  
Information Retrieval ◽  
Deep Learning ◽  
Retrieval System ◽  
Retrieval Model ◽  
Language Understanding ◽  
Convolutional Networks ◽  
Image Retrieval System ◽  
High Level ◽  
Research Hotspots

In recent years, due to the wide application of deep learning and more modal research, the corresponding image retrieval system has gradually extended from traditional text retrieval to visual retrieval combined with images and has become the field of computer vision and natural language understanding and one of the important cross-research hotspots. This paper focuses on the research of graph convolutional networks for cross-modal information retrieval and has a general understanding of cross-modal information retrieval and the related theories of convolutional networks on the basis of literature data. Modal information retrieval is designed to combine high-level semantics with low-level visual capabilities in cross-modal information retrieval to improve the accuracy of information retrieval and then use experiments to verify the designed network model, and the result is that the model designed in this paper is more accurate than the traditional retrieval model, which is up to 90%.

scholarly journals Natural Language Understanding for Multi-Level Distributed Intelligent Virtual Sensors

IoT ◽  
2020 ◽  
Vol 1 (2) ◽  
pp. 494-505
Author(s):  
Radu-Casian Mihailescu ◽  
Georgios Kyriakou ◽  
Angelos Papangelis
Keyword(s):  
Deep Learning ◽  
User Interface ◽  
Natural Language ◽  
Learning Approach ◽  
Language Understanding ◽  
Virtual Sensor ◽  
Virtual Sensors ◽  
Multi Level ◽  
High Level ◽  
User Friendly

In this paper we address the problem of automatic sensor composition for servicing human-interpretable high-level tasks. To this end, we introduce multi-level distributed intelligent virtual sensors (multi-level DIVS) as an overlay framework for a given mesh of physical and/or virtual sensors already deployed in the environment. The goal for multi-level DIVS is two-fold: (i) to provide a convenient way for the user to specify high-level sensing tasks; (ii) to construct the computational graph that provides the correct output given a specific sensing task. For (i) we resort to a conversational user interface, which is an intuitive and user-friendly manner in which the user can express the sensing problem, i.e., natural language queries, while for (ii) we propose a deep learning approach that establishes the correspondence between the natural language queries and their virtual sensor representation. Finally, we evaluate and demonstrate the feasibility of our approach in the context of a smart city setup.

Downsizing the Semantic Gap in Contextual Image Retrieval System Using Superintend Gross Silhouette Descriptor

2020 ◽  
Vol 8 (4) ◽  
pp. 1-20
Author(s):  
Girija G. Chiddarwar ◽  
S.Phani Kumar
Keyword(s):  
Image Retrieval ◽  
Correlation Coefficient ◽  
Retrieval System ◽  
Shape Descriptor ◽  
Query Image ◽  
Relationship Strength ◽  
Image Retrieval System ◽  
High Level ◽  
Straight Lines ◽  
The Relationship

Since shape is the most important feature for recognizing objects, it has to be extracted accurately in order to enhance the content based image retrieval system, but challenges prevailed in extracting shape features of an object in an image due to inability of shape descriptor which extracts a limited number of different shapes that are not invariant, alongside the inability to extracting features of overlapping objects, and the shape connotation gap problem between low level and high level features. In order to overcome these problems, this work proposes a Superintend Gross Silhouette Descriptor which uses pixel coordinates on spatial domain of the image for finding the real shape of the object by means of straight lines so it has the ability to detect the overlapped objects as well as the polygonal shapes. After being extracted, features would be trained using a random woodland classifier which classifies the features into a group of classes at maximum convergence for mitigating the shape connotation problem. At the time of retrieval, the features of the query image would be tested with trained features for measuring the similarity by the dynamite correlation coefficient method, which is a measure of the linear correlation so it would render the absolute value of the correlation coefficient which maintains the relationship strength among features.

scholarly journals EFEKTIVITAS OPAC SEBAGAI SARANA TEMU KEMBALI INFORMASI DI UPT PERPUSTAKAAN UNIVERSITAS MUHAMMADIYAH MAGELANG (UNIMMA)

2021 ◽  
Vol 16 (1) ◽  
pp. 80
Author(s):  
Rizki Shofak Isnaini ◽  
Jamzanah Wahyu Widayati
Keyword(s):  
Information Retrieval ◽  
Data Collection ◽  
Class Number ◽  
Quantitative Research ◽  
Retrieval System ◽  
Information Retrieval System ◽  
Class Numbers ◽  
Value Range ◽  
High Level

Evaluation of information retrieval tool is very important to find out how far the retrieval system has worked. This study evaluates the OPAC of Muhammadiyah University of Magelang (UNIMMA) by determining the effectiveness of the information retrieval system seen from the relevance of the data displayed with the data requested by the user. This is descriptive quantitative research that calculates the value of recall and precision, while the data collection is conducted through literature studies and documentation. Based on the data collected, it can be concluded that OPAC UNIMMA is in the effective category with a high level of precision, and in the value range of 0.68 - 1.00 with recall and precision values respectively 0.77 or 77% and 0.84 or 84%. However, from the observations on each class number, it is found that the class number has a higher recall value than the precision, ie: the class numbers of 200, 800, and 900.

Weapon and Object Detection Using Mobile-Net SSD Model in Deep Neural Network

2021 ◽  
Vol 9 (8) ◽  
pp. 1573-1582
Author(s):  
S Gopi Naik
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Deep Learning ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Optimization Algorithms ◽  
Object Identification ◽  
Integrated System ◽  
Raspberry Pi ◽  
High Level

Abstract: The plan is to establish an integrated system that can manage high-quality visual information and also detect weapons quickly and efficiently. It is obtained by integrating ARM-based computer vision and optimization algorithms with deep neural networks able to detect the presence of a threat. The whole system is connected to a Raspberry Pi module, which will capture live broadcasting and evaluate it using a deep convolutional neural network. Due to the intimate interaction between object identification and video and image analysis in real-time objects, By generating sophisticated ensembles that incorporate various low-level picture features with high-level information from object detection and scenario classifiers, their performance can quickly plateau. Deep learning models, which can learn semantic, high-level, deeper features, have been developed to overcome the issues that are present in optimization algorithms. It presents a review of deep learning based object detection frameworks that use Convolutional Neural Network layers for better understanding of object detection. The Mobile-Net SSD model behaves differently in network design, training methods, and optimization functions, among other things. The crime rate in suspicious areas has been reduced as a consequence of weapon detection. However, security is always a major concern in human life. The Raspberry Pi module, or computer vision, has been extensively used in the detection and monitoring of weapons. Due to the growing rate of human safety protection, privacy and the integration of live broadcasting systems which can detect and analyse images, suspicious areas are becoming indispensable in intelligence. This process uses a Mobile-Net SSD algorithm to achieve automatic weapons and object detection. Keywords: Computer Vision, Weapon and Object Detection, Raspberry Pi Camera, RTSP, SMTP, Mobile-Net SSD, CNN, Artificial Intelligence.

Design of Personalized Intelligent Information Retrieval Model Based on Agent

2012 ◽  
Vol 155-156 ◽  
pp. 1175-1179
Author(s):  
Zhong Biao Sheng ◽  
Hua Ping Jia ◽  
Xiao Rong Tong
Keyword(s):  
Information Retrieval ◽  
Domain Knowledge ◽  
Retrieval System ◽  
Retrieval Model ◽  
Retrieval Task ◽  
Dynamic Information ◽  
Model Based ◽  
Intelligent Information Retrieval ◽  
Intelligent Information ◽  
Personal Interests

The features of vast distributed dynamic information on Web caused the problem of “overload” and “mislead” while query. Intelligent agent is a way to solve it. After considering the problems of users’ personal interests during the information retrieve adequately, the paper proposes an intelligent information retrieval model based-on Agent. This system integrated domain knowledge and used many arithmetic of learning user’s interest. Each Agent co-operates to finish information retrieval task, manifest the characteristics of intellectualization and individuality of in information retrieval. It is a good way to realize the highly effective intelligent retrieval system research.

scholarly journals Computer Vision and Deep Learning for Environment-Adaptive Control of Robotic Lower-Limb Exoskeletons

2021 ◽  
Author(s):  
Brokoslaw Laschowski ◽  
William McNally ◽  
Alexander Wong ◽  
John McPhee
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Image Classification ◽  
Recognition System ◽  
Camera System ◽  
Human Control ◽  
Mode Recognition ◽  
Environment Recognition ◽  
Locomotion Mode ◽  
High Level

Robotic exoskeletons require human control and decision making to switch between different locomotion modes, which can be inconvenient and cognitively demanding. To support the development of automated locomotion mode recognition systems (i.e., high-level controllers), we designed an environment recognition system using computer vision and deep learning. We collected over 5.6 million images of indoor and outdoor real-world walking environments using a wearable camera system, of which ~923,000 images were annotated using a 12-class hierarchical labelling architecture (called the ExoNet database). We then trained and tested the EfficientNetB0 convolutional neural network, designed for efficiency using neural architecture search, to predict the different walking environments. Our environment recognition system achieved ~73% image classification accuracy. While these preliminary results benchmark EfficientNetB0 on the ExoNet database, further research is needed to compare different image classification algorithms to develop an accurate and real-time environment-adaptive locomotion mode recognition system for robotic exoskeleton control.

scholarly journals Integrating Extended Gaia Semantic Information Retrieval Model with Android based System using Native API

2019 ◽  
Vol 8 (3) ◽  
pp. 4835-4838
Keyword(s):  
Information Retrieval ◽  
Semantic Web ◽  
Semantic Information ◽  
Retrieval System ◽  
Software Agent ◽  
Information Retrieval System ◽  
Retrieval Model ◽  
Semantic Information Retrieval ◽  
Agile Software ◽  
Paper Author

In present scenario software industry becomes more advanced. We all know that for developing software system there are many latest technologies available like Agile Software development , Software Agent, Semantic Web ,IOT , Cloud Computing etc. In this paper author tries to provide implementation of Extended GAIA Semantic information Retrieval System. E.G.S.I.R. is basically combination of software agent and semantic web features

Sign in / Sign up

Export Citation Format

Share Document