Search results

The purpose of this paper is to utilize document expansion techniques for improving image representation and retrieval. This paper proposes a concise framework for tag-based image retrieval (TBIR).

The proposed approach includes three core components: a strategy of selecting expansion (similar) images from the whole corpus (e.g. cluster-based or nearest neighbor-based); a technique for assessing image similarity, which is adopted for selecting expansion images (text, image, or mixed); and a model for matching the expanded image representation with the search query (merging or separate).

The results show that applying the proposed method yields significant improvements in effectiveness, and the method obtains better performance on the top of the rank and makes a great improvement on some topics with zero score in baseline. Moreover, nearest neighbor-based expansion strategy outperforms the cluster-based expansion strategy, and using image features for selecting expansion images is better than using text features in most cases, and the separate method for calculating the augmented probability P(q|R_D) is able to erase the negative influences of error images in R_D.

Despite these methods only outperform on the top of the rank instead of the entire rank list, TBIR on mobile platforms still can benefit from this approach.

Unlike former studies addressing the sparsity, vocabulary mismatch, and tag relatedness in TBIR individually, the approach proposed by this paper addresses all these issues with a single document expansion framework. It is a comprehensive investigation of document expansion techniques in TBIR.

The purpose of this study was to compare the ease of use and the effectiveness of several interfaces for retrieving tagged images.

A number of participants were randomly assigned to one of four retrieval interfaces: tag search in a search box; faceted tag search in a search box; selecting terms from the tag cloud of all the tags in the database; and selecting concepts from an ontology created from the tags assigned to the images. Each interface was tested by 21 users.

The results show that the highest recall on average was achieved by users of the ontology interface, for seven out of the ten tasks, however, users were more satisfied with the textbox‐based search than the cloud or the ontology.

The experiment was rather specific, and more studies are needed in order to generalize the findings.

With the widespread use of tagging on the web it is of importance to examine whether tagging enables resource discovery. This study shows that in addition to the tags, the retrieval interface also influences user satisfaction and retrieval success.

Visual Distinctive Language (VDL)-based iconic tags are structured visual information annotation. They explicate the content and organization of tagged information by graphical and symbolic features in order to improve the vocabulary problems of textual tags. The purpose of this paper is to investigate how these special icons help in tagged-based user information searching.

A two-stage experiment was designed and conducted so as to follow and quantify the searching process in specific searching target case and no specific searching target case when using VDL-based iconic tags.

The experimental results manifested that VDL-based iconic tags enhanced the role of tag in information searching. They could make user better understand tag clusters, which, in turn, provide global structure of involved topics. Also, VDL-based iconic tags helped user to find out searching target more quickly with higher accuracy by taking advantages of visual representation of tag categories and symbolic signification of tag content.

This study is one of the first to verify how structured icons work in information searching and how user’s graphical cognition impacts on tag-based information searching process. The research findings are dedicated to the theory of VDL-based iconic tags, as well as to a new visualization method for search user interface design.

Image annotation plays an important role in image retrieval process, especially when it comes to content-based image retrieval. In order to compensate the intrinsic weakness of machines in performing cognitive task of (human-like) image annotation, leveraging humans’ knowledge and abilities in the form of crowdsourcing-based annotation have gained momentum. Among various approaches for this purpose, an innovative one is integrating the annotation process into the CAPTCHA workflow. In this paper, the current state of the research works in the field and experimental efficiency analysis of this approach are investigated.

At first, and with the aim of presenting a current state report of research studies in the field, a comprehensive literature review is provided. Then, several experiments and statistical analyses are conducted to investigate how CAPTCHA-based image annotation is reliable, accurate and efficient.

In addition to study of current trends and best practices for CAPTCHA-based image annotation, the experimental results demonstrated that despite some intrinsic limitations on leveraging the CAPTCHA as a crowdsourcing platform, when the challenge, i.e. annotation task, is selected and designed appropriately, the efficiency of CAPTCHA-based image annotation can outperform traditional approaches. Nonetheless, there are several design considerations that should be taken into account when the CAPTCHA is used as an image annotation platform.

To the best of the authors’ knowledge, this is the first study to analyze different aspects of the titular topic through exploration of the literature and experimental investigation. Therefore, it is anticipated that the outcomes of this study can draw a roadmap for not only CAPTCHA-based image annotation but also CAPTCHA-mediated crowdsourcing and even image annotation.

The purpose of this paper is to analyse users’ attitudes towards online information retrieval and processing. The aim is to identify the characteristics of information that better capture the attention of the users and to provide evidence for the information retrieval behaviour of the users by studying online photo archives as information units.

The paper analyses a unique quasi-experimental data of photo archive access counts collected by the author from an online newspaper. In addition to access counts of each photo in 500 randomly chosen photo galleries, characteristics of the photo galleries are also recorded. Survival (duration) analysis is used in order to analyse the factors affecting the share of the photo gallery viewed by a certain proportion of the initial number of viewers.

The results of the survival analysis indicate that users are impatient in case of longer photo galleries; they lose attention faster and stop viewing earlier when gallery length is uncertain; they are attracted by keywords and initial presentation and they give more credit to specific rather than general information categories.

Results of the study offer applicable implications for information providers, especially on the online domain. In order to attract more attention, entities can engage in targeted information provision by taking into account people’s attitude towards information retrieval and processing as presented in this paper.

This paper uses a unique data set in a quasi-experimental setting in order to identify the characteristics of online information that users are attracted to.

The aim is to determine, in a business context, if tagging is a more effective method of discovering relevant information when compared to traditional hierarchical filing systems.

A five‐step interpretive hybrid approach of using both a focus group, questionnaires and SWOT analysis was used to test the proof of concept of tagging files compared to a traditional hierarchical filing system. The approach taken was chosen because of the difficulties and tradeoffs that had to be made between the number of champions and people available to take part in the research; the time that they could allow; and because transcription or recording of the participants was not permitted. The participants were encouraged to use the questionnaires and the SWOT analysis to record their thoughts anonymously whilst the focus groups allowed elaboration and discussion to help understand the true feelings and thoughts of the group collaboratively.

Traditional hierarchical filing systems can lead to the retrieval of irrelevant information, or to none at all, even though the information exists. The study shows that tagging could provide a cost‐effective solution by providing a better structured filing system that can help reduce duplication and the retrieval of irrelevant information.

One limitation of the study was the limited number of participants from just one organisation. Thus, generalisation of the results of this study to the wider population must be done with great care.

Organisations should evaluate the functionality of their chosen operating system and information store software in light of the potential benefits offered by tagging, and costly limitations of traditional file stores.

The paper contributes to the information retrieval and information overload literature by studying the effect tagging files has on an organisation. It provides an insight to the future of filing systems for management and triggers future empirical work into reducing information overload in the workplace.

Graphic-based tag clouds aim to visually represent tag content and tag structure, and then to better represent tagged information for later search. However, few studies have clarified the features among varied visualization approaches involved in graphic-based tag clouds and compared them for the purpose of information search.

After reviewing four kinds of graphic-based tag clouds, an experimental demonstration was conducted in our study to verify how user performs in information search for a general seeking task by using them. Precision ratio, recall ratio, clicks on search and time for search were four variables tested in the experiment. Also, two supplementary tests were respectively carried out to manifest how graphic-based tag clouds contributed to the identification of target tags and tag clusters.

The experimental results showed that compared to tag content visual tag structure was more important to find related tags from tag clouds for information search. In addition, tag clouds that visually represented the semantic relationships within tags could make user more confident about their search result and carry out a shorter learning process during searching, which signified a tag-based information search path when visual elements were applied.

This research is one of the first to illustrate systematically the graphic-based tag clouds and their impacts on information search. The research findings could suggest on how to build up more effective and interactive tag clouds and make proposition for the design of search user interface by using graphic-based tag clouds.

Image classification is becoming a supporting technology in several image-processing tasks. Due to rich semantic information contained in the images, it is very popular for an image to have several labels or tags. This paper aims to develop a novel multi-label classification approach with superior performance.

Many multi-label classification problems share two main characteristics: label correlations and label imbalance. However, most of current methods are devoted to either model label relationship or to only deal with unbalanced problem with traditional single-label methods. In this paper, multi-label classification problem is regarded as an unbalanced multi-task learning problem. Multi-task least-squares support vector machine (MTLS-SVM) is generalized for this problem, renamed as multi-label LS-SVM (ML²S-SVM).

Experimental results on the emotions, scene, yeast and bibtex data sets indicate that the ML²S-SVM is competitive with respect to the state-of-the-art methods in terms of Hamming loss and instance-based F1 score. The values of resulting parameters largely influence the performance of ML²S-SVM, so it is necessary for users to identify proper parameters in advance.

On the basis of MTLS-SVM, a novel multi-label classification approach, ML²S-SVM, is put forward. This method can overcome the unbalanced problem but also explicitly models arbitrary order correlations among labels by allowing multiple labels to share a subspace. In addition, the multi-label classification approach has a wider range of applications. That is to say, it is not limited to the field of image classification.

The purpose of this paper is to develop a general framework that incorporates collaborative social tagging with a novel ontology scheme conveying multiple perspectives.

This paper proposes a framework where multiple users tag the same object (an image in this case) and an ontology is extended based on these tags while being tolerant of different points of view. Both the tagging and the ontological models are intentionally designed to suit the multi‐perspective environment. The paper develops a method based on a set of rules that determine how to associate new concepts to predefined perspectives (in addition to determining relations to topics or other concepts as typically done in previous research) and how to insert and maintain multiple perspectives.

This case study experiment, with a set of selected annotated images, indicates the soundness of the proposed ontological model.

The proposed framework characterises the underlying processes for controlled collaborative development of a multi‐perspective ontology and its application to improve image annotation, searching and browsing. The significance of this research is that it focuses on exploring the impact of creating a constantly evolving ontology based on collaborative tagging. The paper is not aware of any other work that has attempted to devise such an environment and to study its dynamics.

Suggested tag was considered as one of the critical factors affecting a user’s tagging behaviour. However, compared to the findings on the suggested tags for the monolingual environment, it still lacks focused studies on the tag suggestions for cross-language information. Therefore, this paper aims to concern with annotation behaviour and psychological cognition in the cross-language environment when suggested tags are provided.

A cross-language tagging experiment was conducted to explore the impact of suggested tags on the tagging results and process. The descriptive statistics of tags, the sources and semantic relations of tags, as well as the user’s psychological cognition were all measured in the test.

The experimental results demonstrated that the multilingual suggested tags could bring some costs to a user’s tagging perception. Furthermore, the language factor of suggested tags led to different paths of tagging imitation (reflected by longer semantic mapping and imitation at the visual level) and different cognitive processes (topic extraction and inference process).

To the best of the authors’ knowledge, this study is one of the first to emphasize the effect of suggested tags during multilingual tagging. The findings will enrich the theories of user-information interaction in the cross-language environment and, in turn, provide practical implications for tag-based information system design.