Search by Image. New Search Engine Service Model

Smelyakov, Kirill; Sandrkin, Denys; Рубан, Ігор; Martovytskyi, Vitalii; Romanenkov, Yuri

doi:10.1109/infocommst.2018.8632117

Cited by 19 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They proposed a re-ranking solution classifying the visual features into three categories based on relevance feedback with genetic algorithm. Smelyakov et al [34] suggested a model of service for searching using the image. They used colour content comparison, texture component comparison, object shape comparison, SIFT signature, perceptive hash, Haar features, and artificial neural networks to achieve a sufficient reliability of image search.…”

Section: Image Searchmentioning

confidence: 99%

An Exploratory Study on a Reinforcement Learning Prototype for Multimodal Image Retrieval Using a Conversational Search Interface

2022

View full text Add to dashboard Cite

In the realm of information, conversational search is a relatively new trend. In this study, we have developed, implemented, and evaluated a multiview conversational image search system to investigate user search behaviour. We have also explored the potential for reinforcement learning to learn from user search behaviour and support the user in the complex information seeking process. A conversational image search system may mimic a natural language discussion with a user via text or speech, and then assist the user in locating the required picture via a dialogue-based search. We modified and improved a dual-view search interface that displays discussions on one side and photos on the other. Based on the states, incentives, and dialogues in the initial run, we developed a reinforcement learning model and a customized search algorithm in the back end that predicts which reply and images would be provided to the user among a restricted set of fixed responses. Usability of the system was validated using methodologies such as Chatbot Usability Questionnaire, System Usability Scale, and User Experience Questionnaire, and the values were tabulated. The result of this usability experiment proved that most of the users found the system to be very usable and helpful for their image search.

show abstract

Section: Image Searchmentioning

confidence: 99%

An Exploratory Study on a Reinforcement Learning Prototype for Multimodal Image Retrieval Using a Conversational Search Interface

2022

View full text Add to dashboard Cite

show abstract

“…In the articles [8][9][10][11][12][13][14][15][16][17][18] are presented the different approaches to the analytical assessments of the parameters of distributed computer systems and of the information spaces.…”

Section: Literature Surveymentioning

confidence: 99%

Method of Parallel Information Object Search in Unified Information Spaces

Dodonov¹,

Mukhin²,

Zavgorodnii³

et al. 2021

IJCNIS

View full text Add to dashboard Cite

The article describes the concept of a unified information space and an algorithm of its formation using a special information and computer system. The process of incoming object search in a unified information space is considered, which makes it possible to uniquely identify it by corresponding features. One of the main tasks of a unified information space is that each information object in it is uniquely identified. For this, the identification method was used, which is based on a step-by-step analysis of object characteristics. The method of parallel information object search in unified information spaces is proposed, when information object search will be conducted independently in all unified information spaces in parallel. Experimental studies of the method of parallel information object search in unified information spaces were conducted, on the basis of which the analysis of efficiency and incoming objects search time in unified information spaces was carried out. There was experimentally approved that the more parameters that describe the information object, the less the time of object identification depends on the length of the interval. Also, there was experimentally approved that the efficiency of the searching of the incoming objects in unified information spaces tends to a directly proportional relationship with a decrease in the length of the interval and an increase in the number of parameters, and vice versa.

show abstract

“…Text analytics tools enable automatic choice, systematization and analysis of alphanumeric data due to the application of linguistic rules, statistical machine learning methods within various areas of application [3,9,10,11]. TBS is a particular case of text analytics tasks, i.e.…”

Section: Task Fulfillmentmentioning

confidence: 99%

“…One of the dominant paradigms (not the only one [5]) in this field is the research and reproduction of the structure and functions of the human intellect [9]. At every certain moment of their practical activity, an individual operates effectively with a limited small number of notions [10,11]. Excess LDA is a stress situation, in which effective work may demand specific training [3,10] or may be supported, at the best, during a limited time period.…”

Section: Introductionmentioning

confidence: 99%

Local Concurrency in Text Block Search Tasks

Barkovska¹

2020

IJETER

View full text Add to dashboard Cite

The relevant problem of text analytics tools development is real-time mode establishment via data processing operations parallelizing. The use of the local parallel (LP) approach is advantageous. The classification of search algorithms for text blocks, which are candidate for local parallel (LP) approach implementation, was presented. The advantages of LP approach implementation were regarded. The variants of bit and segmental word-patterns processing in text block search tasks were proposed and exemplified. Perspectives and certain threats to its implementation were studied in terms of Boyer-Moore algorithm.

show abstract

Search by Image. New Search Engine Service Model

Cited by 19 publications

References 12 publications

An Exploratory Study on a Reinforcement Learning Prototype for Multimodal Image Retrieval Using a Conversational Search Interface

An Exploratory Study on a Reinforcement Learning Prototype for Multimodal Image Retrieval Using a Conversational Search Interface

Method of Parallel Information Object Search in Unified Information Spaces

Local Concurrency in Text Block Search Tasks

Contact Info

Product

Resources

About