Traditional Text-based Search Research Articles

Suitable and Style-Consistent Multi-Texture Recommendation for Cartoon Illustrations

Texture plays an important role in cartoon illustrations to display object materials and enrich visual experiences. Unfortunately, manually designing and drawing an appropriate texture is not easy even for proficient artists, let alone novice or amateur people. While there exist tons of textures on the Internet, it is not easy to pick an appropriate one using traditional text-based search engines. Although several texture pickers have been proposed, they still require the users to browse the textures by themselves, which is still labor-intensive and time-consuming. In this article, an automatic texture recommendation system is proposed for recommending multiple textures to replace a set of user-specified regions in a cartoon illustration with visually pleasant look. Two measurements, the suitability measurement and the style-consistency measurement, are proposed to make sure that the recommended textures are suitable for cartoon illustration and at the same time mutually consistent in style. The suitability is measured based on the synthesizability, cartoonity, and region fitness of textures. The style-consistency is predicted using a learning-based solution since it is subjective to judge whether two textures are consistent in style. An optimization problem is formulated and solved via the genetic algorithm. Our method is validated on various cartoon illustrations, and convincing results are obtained.

Revolutionizing digital marketing: unveiling the impact of influencer marketing, AI-driven customer support, and voice search optimization on engagement and efficiency on the example of the semiconductor manufacturing industry

In the rapidly evolving landscape of semiconductor manufacturing, this research paper explores the application of pivotal digital marketing trends and strategic innovations to reshape contemporary business strategies within the industry. Recognizing the significance of staying at the forefront of these transformations, our study aims to provide a nuanced understanding of three prominent digital marketing innovations: Influencer Marketing, Artificial Intelligence (AI)-driven Customer Support, and Voice Search Optimization. Through a rigorous methodology integrating literature review and case study analysis specific to semiconductor manufacturing in India, we unveil the successful implementation and tangible impact of these innovations on user engagement, brand perception, and overall marketing efficacy within the semiconductor sector of India. The research was done in 2022-2023 over the semiconductor companies working in India (HCL Technologies, Bharat Electronics Limited, ABB India Limited, Vedanta, CG Power and Industrial Solutions Limited, and Havells India Limited). Comparative analyses against traditional methods reveal significant improvements tailored to this industry: Influencer Marketing campaigns demonstrated a 25% increase in reach and engagement compared to conventional advertising. The integration of AI-driven Customer Support resulted in a 30% reduction in response time, enhancing customer satisfaction scores by 15%. Furthermore, Voice Search Optimization strategies yielded a 20% improvement in search accuracy, outperforming traditional text-based Search Engine Optimization (SEO) approaches within the semiconductor manufacturing context. Delving into challenges and opportunities associated with each innovation within the semiconductor industry, we provide evidence-based recommendations for businesses seeking to navigate the dynamic digital marketing landscape in this specialized domain. As semiconductor manufacturing continues to redefine its business ecosystem, embracing these innovations emerges as a cornerstone for sustained success in the digital era within this unique sector.

Development of a Visual Search Service Effectiveness Scale for Assessing Image Search Effectiveness: A Behavioral and Technological Perspective

Despite the potential of visual search services (VSSs) to increase the size of the global visual search market, there is no VSS effectiveness measurement scale in the literature. Prior studies of traditional text-based search services have aimed to establish a method for assessing the performance of web search services. Our primary objective is to integrate state-of-the-art research in the fields of information-seeking behavior, visual search performance, and human–computer interaction pertaining to evaluating VSS effectiveness. The key dimensions of VSS effectiveness were identified by adopting the Delphi method, and the associated measures were developed. Then, survey data were collected from 426 VSS users, and the developed measures of VSS effectiveness were validated using the exploratory factor analysis technique. Finally, the scale developed includes 19 measures belonging to three key dimensions: user dependency on VSSs, the perceived ability to use VSSs, and VSS retrieval performance. The nomological validity of the developed scale’s three dimensions was also ensured and was evident from the positive correlations between them and VSS user continuance intention. Overall, we find that the better the functionality of a VSS is, the more users with a high perceived ability can acquire better information. This study also contributes to the theory development in the literature on search service effectiveness measures in terms of highlighting the VSS feature to be considered when providing a VSS that is suitable for the user’s preference.

Development of an Effective Bootleg Videos Retrieval System as a Part of Content-Based Video Search Engine

Many research studies in content-based video search engines are concerned with content-based video queries retrieval where a query by example is sent to retrieve a list of visually similar videos. However, minor research is concerned with indexing and searching public video streaming services such as YouTube, where there is a dilemma for misusing copyrighted video materials and detecting bootleg manipulated videos before being uploaded. In this paper, a novel and effective technique for a content-based video search engine with effective detection of bootleg videos is evaluated on a large-scale video index dataset of 1088 video records. A novel feature vector is introduced using video shots temporal and key-object/concept features applying combinational-based matching algorithms, using various similarity metrics for evaluation. The retrieval system was evaluated using more than 200 non-semantic-based video queries evaluating both normal and bootleg videos, with retrieval precision for normal videos of 97.9% and retrieval recall of 100% combined by the F1 measure to be 98.3%. Bootleg videos retrieval precision scored 99.2% and retrieval recall was of 96.7% combined by the F1 measure to be 97.9%. This allows making a conclusion that this technique can help in enhancing both traditional text-based search engines and commonly used bootleg detection techniques.

Model-based information navigation for engineering documents

Engineering and the manner in which engineers think is largely visual and functional, and yet engineers are typically provided with search engines that are text-based. While software based on a visual and functional ethos exist (CAD for example), when searching for information engineers are still required to enter a text query into a search box. This process holds potential incompatibilities both with the nature of the data (i.e. 3D models) and with the way in which engineers think and work. Consequentially, the proposition tested in this paper is that a model-based approach to information access, i.e. a representation of an organisations information around a model of an artefact i.e. CAD model, can improve engineering information retrieval.In an A-B test with a traditional text-based search engine, and using study questions derived from real-world information seeking scenarios based on the activities of a world-leading aircraft manufacturer, the results presented in this paper suggest that there is merit to such an approach. Specifically, this paper shows that there is no significant difference in time to complete a search between a model-based and text-based interfaces in spite of the addition of a new stage in the search process (navigating a 3D model); that the system structure of the model-based interface allows for non-text based documents to be indexed, making up for the inherent limitations in traditional text-based search; and that participants enjoy using the model-based interface and find it intuitive, easy and simple to use. Further, this paper also finds that those with more experience/familiar with the product structure and those in managerial positions are more likely to find information using a model-based interface that those who are not, who perform better using a text-based interface.

What Can Pictures Tell Us About Web Pages? Improving Document Search Using Images.

Traditional Web search engines do not use the images in the HTML pages to find relevant documents for a given query. Instead, they typically operate by computing a measure of agreement between the keywords provided by the user and only the text portion of each page. In this paper we study whether the content of the pictures appearing in a Web page can be used to enrich the semantic description of an HTML document and consequently boost the performance of a keyword-based search engine. We present a Web-scalable system that exploits a pure text-based search engine to find an initial set of candidate documents for a given query. Then, the candidate set is reranked using visual information extracted from the images contained in the pages. The resulting system retains the computational efficiency of traditional text-based search engines with only a small additional storage cost needed to encode the visual information. We test our approach on one of the TREC Million Query Track benchmarks where we show that the exploitation of visual content yields improvement in accuracies for two distinct text-based search engines, including the system with the best reported performance on this benchmark. We further validate our approach by collecting document relevance judgements on our search results using Amazon Mechanical Turk. The results of this experiment confirm the improvement in accuracy produced by our image-based reranker over a pure text-based system.

Evaluating implicit judgments from image search clickthrough data

The interactions of users with search engines can be seen as implicit relevance feedback by the user on the results offered to them. In particular, the selection of results by users can be interpreted as a confirmation of the relevance of those results, and used to reorder or prioritize subsequent search results. This collection of search/result pairings is called clickthrough data, and many uses for it have been proposed. However, the reliability of clickthrough data has been challenged and it has been suggested that clickthrough data are not a completely accurate measure of relevance between search term and results. This paper reports on an experiment evaluating the reliability of clickthrough data as a measure of the mutual relevance of search term and result. The experiment comprised a user study involving over 67 participants and determines the reliability of image search clickthrough data, using factors identified in previous similar studies. A major difference in this work to previous work is that the source of clickthrough data comes from image searches, rather than the traditional text page searches. Image search clickthrough data were rarely examined in prior works but has differences that impact the accuracy of clickthrough data. These differences include a more complete representation of the results in image search, allowing users to scrutinize the results more closely before selecting them, as well as presenting the results in a less obviously ordered way. The experiment reported here demonstrates that image clickthrough data can be more reliable as a relevance feedback measure than has been the case with traditional text-based search. There is also evidence that the precision of the search system influences the accuracy of click data when users make searches in an information-seeking capacity. © 2012 Wiley Periodicals, Inc.

The Internet Brain Volume Database: A Public Resource for Storage and Retrieval of Volumetric Data

Every month, numerous publications appear that include neuroanatomic volumetric observations. The current and past literature that includes volumetric measurements is vast, but variable with respect to specific species, structures, and subject characteristics (such as gender, age, pathology, etc.). In this report we introduce the Internet Brain Volume Database (IBVD), www.nitrc.org/projects/ibvd , a site devoted to facilitating access to and utilization of neuroanatomic volumetric observations as published in the literature. We review the design and functionality of the site. The IBVD is the first database dedicated to integrating, exposing and sharing brain volumetric observations across species and disease. It offers valuable functionality for quality assurance assessment of results as well as support for meta-analysis across large segments of the published literature that are obscured from traditional text-based search engines.

Building Multi-Modal Relational Graphs for Multimedia Retrieval

The abundance of Web 2.0 social media in various media formats calls for integration that takes into account tags associated with these resources. The authors present a new approach to multi-modal media search, based on novel related-tag graphs, in which a query is a resource in one modality, such as an image, and the results are semantically similar resources in various modalities, for instance text and video. Thus the use of resource tagging enables the use of multi-modal results and multi-modal queries, a marked departure from the traditional text-based search paradigm. Tag relation graphs are built based on multi-partite networks of existing Web 2.0 social media such as Flickr and Wikipedia. These multi-partite linkage networks (contributor-tag, tag-category, and tag-tag) are extracted from Wikipedia to construct relational tag graphs. In fusing these networks, the authors propose incorporating contributor-category networks to model contributor’s specialization; it is shown that this step significantly enhances the accuracy of the inferred relatedness of the term-semantic graphs. Experiments based on 200 TREC-5 ad-hoc topics show that the algorithms outperform existing approaches. In addition, user studies demonstrate the superiority of this visualization system and its usefulness in the real world.

Shape Distribution-Based 3D Shape Retrieval Methods: Review and Evaluation

AbstractThree-dimensional (3D) models are basis of modern digital manufacturing systems. It has attracted much attention in research and industrial applications to build 3D product models efficiently and cost-effectively. One of promising developments is product models reusing through sharing. The efficient retrieval of 3D product shapes can speed up 3D modeling for product design and manufacturing but it remains a technical challenge to search for similar 3D models or parts in a model set. Traditional text-based search engines fail in 3D model searching as the lack of detailed descriptions. This paper reviews current research and development in shape distribution-based 3D model retrieval methods. The methods are evaluated by the comparison of their efficiency and accuracy using examples. The further research is proposed based on solutions found.

A similarity-based method for retrieving documents from the SCI/SSCI database

As more and more documents become electronically available, finding documents in large databases that fit users' needs is becoming increasingly important. In the past, the document search problem was dealt with using the database query approach or the text-based search approach. In this paper, we investigate this problem, focusing on the SCI/SSCI databases from ISI. Specifically, we design our search methodology based on the four fields commonly seen in a scientific research document: abstract, title, keywords, and reference list. Of these four, only the abstract field can be viewed as a normal text, while the other three have their own characteristics to differentiate them from texts. Therefore, we first develop a method to compute the similarity value for each field. Our next problem is combining the four similarity values into a final value. One approach is to assign weights to each and compute the weighted sum. We have not adopted this simple weighting method, however, because it is difficult to determine appropriate weights. Instead, we use the back propagation neural network to combine them. Finally, extensive experiments have been carried out using real documents drawn from TKDE journal, and the results indicate that in all situations our method has a much higher accuracy than the traditional text-based search approach.

A search engine for 3D models

As the number of 3D models available on the Web grows, there is an increasing need for a search engine to help people find them. Unfortunately, traditional text-based search techniques are not always effective for 3D data. In this article, we investigate new shape-based search methods. The key challenges are to develop query methods simple enough for novice users and matching algorithms robust enough to work for arbitrary polygonal models. We present a Web-based search engine system that supports queries based on 3D sketches, 2D sketches, 3D models, and/or text keywords. For the shape-based queries, we have developed a new matching algorithm that uses spherical harmonics to compute discriminating similarity measures without requiring repair of model degeneracies or alignment of orientations. It provides 46 to 245% better performance than related shape-matching methods during precision--recall experiments, and it is fast enough to return query results from a repository of 20,000 models in under a second. The net result is a growing interactive index of 3D models available on the Web (i.e., a Google for 3D models).

What's the Story

What's the Story