• Journal of Broadcast Engineering
• /
• v.12 no.4
• /
• pp.303-310
• /
• 2007

Motion Estimation (ME) is a core part of most Video compression systems since it affects directly the output video quality and the encoding time. The most basic method of ME, Full Search (FS) gives the highest visual quality but also has the problem of significant computational load. To solve this problem, many fast algorithm has been proposed. Among them, MVFAST and PMVFAST show impressive results in video quality and the computational load by using the correlation between motion vectors of adjacent blocks. In particular, PMVFAST reduces search points dramatically and also gives very high video quality by using the median predictor. In this paper, we propose a new algorithm that uses the redefined median predictor which reduces the number of search points and yields a high visual quality by reducing the number of thresholds and early termination conditions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3976-3990
• /
• 2022

Currently, cross-attention is widely used in Siamese trackers to replace traditional correlation operations for feature fusion between template and search region. The former can establish a similar relationship between the target and the search region better than the latter for robust visual object tracking. But existing trackers using cross-attention only focus on rich semantic information of high-level features, while ignoring the appearance information contained in low-level features, which makes trackers vulnerable to interference from similar objects. In this paper, we propose a Multi-level Cross-attention Siamese network(MCSiam) to aggregate the semantic information and appearance information at the same time. Specifically, a multi-level cross-attention module is designed to fuse the multi-layer features extracted from the backbone, which integrate different levels of the template and search region features, so that the rich appearance information and semantic information can be used to carry out the tracking task simultaneously. In addition, before cross-attention, a target-aware module is introduced to enhance the target feature and alleviate interference, which makes the multi-level cross-attention module more efficient to fuse the information of the target and the search region. We test the MCSiam on four tracking benchmarks and the result show that the proposed tracker achieves comparable performance to the state-of-the-art trackers.

• Korean Journal of Cognitive Science
• /
• v.34 no.3
• /
• pp.153-180
• /
• 2023

Previous research on the action effect had shown how simple action towards a stimulus can enhance the processing of that stimulus in subsequent visual search task (Buttaccio & Hahn, 2011; Weidler & Abrams, 2014). In four experiments, we investigated whether semantic representation of action word can induce the same attentional boost towards that stimulus and whether the type of action performed can modulate the action effect. In experiment 1, we replicated the same experimental paradigm displayed in previous studies. Participants were first shown an action word cue - "go" or "no". When the action cue was "go", participants were to press a designated key, but not to when the action cue was "no". Next, participants performed a visual search task, in which they reported the orientation of a tilted bar. The target could appear on top of the previously shown prime object (valid), or not (invalid). Reaction times (RTs) to the search task were measure for analysis and comparison, and the action effect had been replicated. In experiment 2, participants were instructed to respond with the keyboard for the action task, and to respond with the joystick for the visual search task. In experiment 3, participants were instructed not to press any key on the onset of prime, and then perform the visual search task to isolate the effect of semantic representation. Lastly, in experiment 4, participants were instructed to press separate keys for "go" and "no" on the onset of prime, and then perform the visual search task. Results indicate that semantic representation alone did not modulate the action effect, regardless of type of action and medium of action.

• Journal of KIISE:Databases
• /
• v.36 no.5
• /
• pp.366-373
• /
• 2009

In this paper, we propose a similarity search algorithm for image databases. One of the central problems regarding content-based image retrieval (CBIR) is the semantic gap between the low-level features computed automatically from images and the human interpretation of image content. Many search algorithms used in CBIR have used the Minkowski metric (or $L_p$-norm) to measure similarity between image pairs. However those functions cannot adequately capture the aspects of the characteristics of the human visual system as well as the nonlinear relationships in contextual information. Our new search algorithm tackles this problem by employing new similarity measures and ranking strategies that reflect the nonlinearity of human perception and contextual information. Our search algorithm yields superior experimental results on a real handwritten digit image database and demonstrates its effectiveness.

• Journal of Fashion Business
• /
• v.21 no.4
• /
• pp.127-143
• /
• 2017

In this study, we examine a variety of influences in the field of design and analysis about the value of visual tactile design. In hair design, through study on visual tactility, creative design inspiration in the field of hair design enables development of quality research. Research methods use Internet publications such as local and foreign data, analysis, and related research and book forms, such as network searches. library goes for consideration by a literature search. Contents of this study used review of the case and by visual tactility design, for this study, expressive characteristics by color, texture and form of hair design, from 2014-2017 trend shown in the last three years the expressions of visual tactility being used through the analysis of design by date of the case. Result of this study is, visual tactile design appearing in the areas of hair design, that are not of the rules that are active, abstract form, texture, described as a visual feel the promotion of effective, and light and high brightness is sweet tactile impression, high saturation was cold, dark color was hard and heavy, red system is warm and the blue system is cold sense. In general, design trend in hair for three years from 2014-2017, visual tactility in 2014 is a high saturation and unstructured also soft and bright colors. 2015 is on the overall shape, color, texture, hybrid design configuration is more. As of 2016, 2017 is curved and straight texture, appearance of the hybrid mix to maximize the visual tactility.

• Journal of Korean Institute of Industrial Engineers
• /
• v.19 no.2
• /
• pp.53-64
• /
• 1993

Successful completion of a visual task in a predetermined time is very crucial to many operations such as piloting an aircraft. Although existing ergonomic interface models often provide a function of vision tests, it determines only the visibility at any given location. To complement this problem in existing models, the isoresponse time region considering the factors related to visual tasks is presented. Using a multiple regression model, equal response time regions were obtained within which mean response time is expected to be the same and is asymmetrical in shape. Among the factors considered, expectancy significantly decreased response time, and when cued, the effects of field heterogeneity, target uncertainty, density, size contrast and peripheral position on search time were less significant than those in unexpected cases. Response time and error rate, gender and visual acuity were not significantly correlated, and response time and age was positively correlated. These results are expected to be directly applicable to designing various visual tasks in real-life situations.

• Journal of Korea Multimedia Society
• /
• v.10 no.6
• /
• pp.707-715
• /
• 2007

The need for content-based retrieval from visual media, such as image and video data, is ever increasing rapidly in many applications, such as electronic art museums, internet shopping malls, internet search engines, and medical information systems. In our previous research, we proposed an architecture, called the HERMES, which is a Web Service-enabled visual media retrieval framework. In this paper, we propose the Web Service workflows that are employed in the HERMES. We describe how we designed the workflows for service registration and query processing in the framework. We especially explain how metadata and ontology can be utilized to realize more intelligent content-based retrieval on visual media data.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.27 no.2
• /
• pp.108-118
• /
• 1999

This study aims to apply World Wide Web(WWW) image files to visual material in lectures. Especially handles "Aesthetics of Landscape Architecture." Visual Materials of 800 web sites were searched and analyzed. It is found that web search needs a subject oriented web guide. It says now a need of application web material to lectures. Matching the web images with the subjects of lecture, above all, is the main approach of this study. Thus, a list up method is supposed, series of web image data to be inclusive in two tables. The data distribute on sub-subject, and applicant as materials in picturing objects of slide show, web guide, and single image. Two cases of lecture subjects were chosen in this study. A case that needs various visual materials and other case of advanced materials that needs a special web guide. Chance of results of this study is not yet fully clear in real lecture. It is sure, as an article of cyber lecture that provided result of increasingly participant's interest. By this study, it will be possible a fully made lecture material by further study.her study.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.44 no.5
• /
• pp.789-809
• /
• 2020

Growth in online channels has created fierce competition; consequently, retailers have to invest an increasing amount of effort into attracting consumers. In this study, eye-tracking technology examined consumers' visual behavior to gain an understanding of information searching behavior in exploring product information for fashion products. Product attribute information was classified into two image-based elements (model image information and detail image information) and two text-based elements (basic text information, detail text information), after which consumers' visual behavior for each information element was analyzed. Furthermore, whether involvement affects consumers' information search behavior was investigated. The results demonstrated that model image information attracted visual attention the quickest, while detail text information and model image information received the most visual attention. Additionally, high-involvement consumers tended to pay more attention to detailed information while low-involvement consumers tended to pay more attention to image-based and basic information. This study is expected to help broaden the understanding of consumer behavior and provide implications for establishing strategies on how to efficiently organize product information for online fashion stores.

• Journal of Information Processing Systems
• /
• v.7 no.3
• /
• pp.447-458
• /
• 2011

This study presents a comprehensive solution to the collection management, which is based on the model for Cultural Objects (CCO). The developed system manages and spreads the collections that are safeguarded in museums and galleries more easily by using IT. In particular, we present our approach for a non-structured search and recovery of the objects based on the annotation of artwork images. In this methodology, we have introduced a faceted search used as a framework for multi-classification and for exploring/browsing complex information bases in a guided, yet unconstrained way, through a visual interface.