检索结果-内蒙古大学图书馆

Multimedia Benchmark workshop, MediaEval 2015

作者： Vlastelica, Marin P. Hayrapetyan, Sergey Tapaswi, Makarand Stiefelhagen, Rainer Computer Vision for Human Computer Interaction Karlsruhe Institute of Technology Germany

We present the approach and results of our system on the MediaEval Affective Impact of Movies Task. The challenge involves two primary tasks: affect classification and violence detection. We test the performance of multiple visual features followed by linear SVM classifiers. Inspired by successes in different vision fields, we use (i) GIST features used in scene modeling, (ii) features extracted from a deep convolutional neural network trained on object recognition, and (iii) improved dense trajectory features encoded using Fisher vectors commonly used in action recognition.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Appearance-based indoor localization: A comparison of patch descriptor performance

引用

PATTERN RECOGNITION LETTERS 2015年 66卷 109-117页

作者： Rivera-Rubio, Jose Alexiou, Ioannis Bharath, Anil A. Univ London Imperial Coll Sci Technol & Med London SW7 2AZ England

vision is one of the most important of the senses, and humans use it extensively during navigation. We evaluated different types of image and video frame descriptors that could be used to determine distinctive visual landmarks for localizing a person based on what is seen by a camera that they carry. To do this, we created a database containing over 3 km of video-sequences with ground-truth in the form of distance travelled along different corridors. Using this database, the accuracy of localization-both in terms of knowing which route a user is on-and in terms of position along a certain route, can be evaluated. For each type of descriptor, we also tested different techniques to encode visual structure and to search between journeys to estimate a user's position. The techniques include single-frame descriptors, those using sequences of frames, and both color and achromatic descriptors. We found that single-frame indexing worked better within this particular dataset. This might be because the motion of the person holding the camera makes the video too dependent on individual steps and motions of one particular journey. Our results suggest that appearance-based information could be an additional source of navigational data indoors, augmenting that provided by, say, radio signal strength indicators (RSSIs). Such visual information could be collected by crowdsourcing low-resolution video feeds, allowing journeys made by different users to be associated with each other, and location to be inferred without requiring explicit mapping. This offers a complementary approach to methods based on simultaneous localization and mapping (SLAM) algorithms. (C) 2015 The Authors. Published by Elsevier B.V.

关键词： Visual localization Descriptors human-computer interaction Assistive devices

来源：评论

学校读者我要写书评

暂无评论

2nd workshop on designing with older adults: Towards a complete methodology 15

2nd Workshop on designing with older adults: Towards a compl...

引用

17th International Conference on human-computer interaction with Mobile Devices and Services, MobileHCI 2015

作者： Nicol, Emma Dunlop, Mark Komninos, Andreas McGee-Lennon, Marilyn Baillie, Lynne Eslambolchilar, Parisa Foong, Pin Sym Gault, Paul Hakobyan, Lilit Lumsden, Jo Velàsquez, Fáber Danilo Giraldo Horcher, Ann-Marie Univ. Strathclyde Glasgow United Kingdom Glasgow Caledonian University United Kingdom Swansea University Swansea United Kingdom NUS Grad School of Integrative Sciences and Engineering Singapore Singapore University of Aberdeen United Kingdom Aston University Birmingham United Kingdom University of Quindío Colombia Nova South Eastern University United States

ISBN: (纸本)9781450336536

The ageing process can interfere considerably with the use of mobile devices, e.g. due to changes in vision, attention, and motor control. Designing mobile technology with older adults poses its own challenges. In the absence of a complete methodology for working with older users, researchers and designers are often left to improvise their own methods. This can result in co-design relationships being compromised and weak design insights emerging. How can we best adapt or modify existing methods for working with this group?

关键词： human computer interaction

来源：评论

学校读者我要写书评

暂无评论

How mobile devices are revolutionizing user interaction 33

How mobile devices are revolutionizing user interaction

引用

33rd Annual CHI Conference on human Factors in Computing Systems, CHI EA 2015

作者： Lee, Hwanyong Trevett, Neil Olson, Tom Erukhimov, Victor Oh-Bach, Alon Kyungpook National University Korea Republic of Khronos Group Department of OpenCL WG NVIDIA Korea Republic of Department of OpenGL Common WG ARM Korea Republic of Department of OpenVX WG Itsees Inc. Korea Republic of Department of EGL WG and TAP Samsung Korea Republic of

ISBN: (纸本)9781450331463

In the mobile device ecosystem, standardization is a key component of user interface, user interaction, and user experience development. Application Programming Interface (API) standards play an especially important role in connecting software to silicon, creating consistent development environments and accelerating media. The Khronos Group is a non-profit industry consortium creating open standards for the authoring and acceleration of parallel computing, graphics, dynamic media, computer vision, and sensor processing on a wide variety of platforms and devices. OpenGL, the graphics standard API from Khronos Group, is widely used for the foundation layer in GUI development in many types of projects: from personal devices including PC, iOS, and Android;to safetycritical applications such as avionics. OpenCL, the cross-platform parallel programming interface, is widely used for massive computation in fields such as machine intelligence and computer vision. Mobile devices require powerful new user interaction capabilities. Khronos open standard APIs enable applications to access capabilities such as the use of sensors to collect user and environment information, and processing power to manipulate and understand the sensor data. Recently, Khronos Group announced the release of new API standard, which can be used as the foundation layer for innovative user experience applications in the near future. This workshop is organized to discuss these new Khronos Group technologies, and to share the features and the UI/UX innovations that mobile devices may realize in the future. Copyright is held by the author/owner(s).

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Computational analysis of human-robot interactions through first-person vision: Personality and interaction experience

Computational analysis of human-robot interactions through f...

引用

IEEE International workshop on Robot and human Communication (ROMAN)

作者： Oya Celiktutan Hatice Gunes School of Electrical Engineering and Computer Science Queen Mary University of London London UK

In this paper, we analyse interactions with Nao, a small humanoid robot, from the viewpoint of human participants through an ego-centric camera placed on their forehead. We focus on human participants' and robot's personalities and their impact on the human-robot interactions. We automatically extract nonverbal cues (e.g., head movement) from first-person perspective and explore the relationship of nonverbal cues with participants' self-reported personality and their interaction experience. We generate two types of behaviours for the robot (i.e., extroverted vs. introverted) and examine how robot's personality and behaviour affect the findings. Significant correlations are obtained between the extroversion and agreeable-ness traits of the participants and the perceived enjoyment with the extroverted robot. Plausible relationships are also found between the measures of interaction experience and personality and the first-person vision features. We then use computational models to automatically predict the participants' personality traits from these features. Promising results are achieved for the traits of agreeableness, conscientiousness and extroversion.

关键词： Feature extraction Cameras human-robot interaction Robot vision systems Forehead Videos

来源：评论

学校读者我要写书评

暂无评论

A novel vision-based human-machine interface for a robotic walker framework

A novel vision-based human-machine interface for a robotic w...

引用

IEEE International workshop on Robot and human Communication (ROMAN)

作者： João Paulo Paulo Peixoto Urbano Nunes Department of Electrical and Computer Engineering University of Coimbra Portugal

This paper presents an innovative human-Machine Interface (HMI) for a robotic walker. Robotic walkers offer their users an aid for sustaining mobility and the potential to rehabilitate their lower limbs. Mobility is a crucial function for a human being and these aids are paramount for improving the independence and quality of life of those who suffer from some form of mobility impairment. However, important factors like cost and safety make them either frequently inaccessible to the public or discarded due to a lack of confidence in their operation. The approach adopted in this work offers an intuitive human-machine interface combined with innovative safety measures. This result was possible due to the resourceful use of the low-cost Leap Motion sensor. Experimental evaluation was divided into two stages. First the system was tested using a simulated environment which served to validate the principle of operation of the HMI. In the second stage the proposed HMI was tested on board a robotic platform to evaluate its performance in a real-world scenario. Experiments performed with healthy volunteers revealed an intuitive user interaction and accurate user intention determination.

关键词： Safety Robot sensing systems Legged locomotion Force Man machine systems Tracking

来源：评论

学校读者我要写书评

暂无评论

LVRA: Low vision reading algorithm 14

LVRA: Low vision reading algorithm

引用

workshop on REHAB 2014

作者： Mashat, Mohamed A. Fardoun, Habib M. Gonzaléz, Lorenzo Carretero King Abdulaziz University Jeddah Saudi Arabia

ISBN: (纸本)9781631900112

This paper presents the Low vision Reading Algorithm for people with low vision problems;Low vision Algorithm is used to reveal the hidden information under the zones in which the user cannot see correctly. This algorithm improves the obtained result when the device is used to read some type of document or web page. Thus, if it is connected with a ocular movement detection application, it aids people to use the devices in a more comfortable way. Copyright © 2014 ICST.

关键词： human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Design for 'quality of use': Emotion and physical interface design

Design for 'quality of use': Emotion and physical interface ...

引用

International Conferences on Interfaces and human computer interaction 2014, Game and Entertainment Technologies 2014 and computer Graphics, Visualization, computer vision and Image Processing 2014

作者： Wodehouse, Andrew Sheridan, Marion Dept. of Design Manufacture and Engineering Management University of Strathclyde James Weir Building 75 Montrose Street GlasgowG1 1XJ United Kingdom Dept. of English Lord Hope Building University of Strathclyde 141 St James Road GlasgowG4 0LT United Kingdom

ISBN: (纸本)9789898533227

With recent technological developments in motion capture there is an opportunity to redefine the physical interactions we have with products, considering human needs in movement at the forefront rather than subservient to the machine. This paper reports on the exploration of emotional reaction to gestural interface design using Laban's Movement Analysis from the field of dance and drama. After outlining the current status of Gesture Controlled user Interfaces and why the use of Laban is appropriate to help understand the effects of movement, the results of a workshop on new interface design are presented. Teams were asked to re-imagine a number of product experiences that utilised appropriate Laban effort actions and to prototype and present these to the group. Several categories of devices, including direct manipulation, remote control and gesture recognition were identified. In aligning appropriate movements to device functionality, utilising culture and analogy and where necessary increasing complexity, the interfaces embody a number of concepts relating to gestural interface concepts. Copyright © 2014 IADIS Press All rights reserved.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

On being the right scale: Sizing large collections of 3D models 14

On being the right scale: Sizing large collections of 3D mod...

引用

SIGGRAPH Asia 2014 workshop on Indoor Scene Understanding Where Graphics Meets vision, SA 2014

作者： Savva, Manolis Chang, Angel X. Bernstein, Gilbert Manning, Christopher D. Hanrahan, Pat Computer Science Department Stanford University United States

ISBN: (纸本)9781450332422

We address the problem of recovering reliable sizes for a collection of models defined using scales with unknown correspondence to physical units. Our algorithmic approach provides absolute size estimates for 3D models by combining category-based size priors and size observations from 3D scenes. Our approach handles unobserved 3D models without any user intervention. It also scales to large public 3D model databases and is appropriate for handling the open-world problem of rapidly expanding collections of 3D models. We use two datasets from online 3D model repositories to evaluate against both human judgments of size and ground truth physical sizes of 3D models, and find that an algorithmic approach can predict sizes more accurately than people. Copyright © ACM.

关键词： 3D models

来源：评论

学校读者我要写书评

暂无评论

Alternate endings: Using fiction to explore design futures

Alternate endings: Using fiction to explore design futures

引用

32nd Annual ACM Conference on human Factors in Computing Systems, CHI EA 2014

作者： Linehan, Conor Kirman, Ben Wakkary, Ron Desjardins, Audrey Tanenbaum, Theresa Jean Blythe, Mark Reeves, Stuart Lincoln Social Computing Research Centre University of Lincoln United Kingdom School of Interactive Arts and Technology Simon Fraser University Canada School of Design Northumbria University Newcastle-Upon-Tyne United Kingdom Mixed Reality Lab. School of Computer Science University of Nottingham United Kingdom

ISBN: (纸本)9781450324748

Design research and practice within HCI is inherently oriented toward the future. However, the vision of the future described by HCI researchers and practitioners is typically utility-driven and focuses on the short term. It rarely acknowledges the potentially complex social and psychological long-term consequences of the technology artefacts produced. Thus, it has the potential to unintentionally cause real harm. Drawing on scholarship that investigates the link between fiction and design, this workshop will explore "alternate endings" to contemporary HCI papers. Attendees will use fictional narratives to envision long-term consequences of contemporary HCI projects, as a means for engaging the CHI community in a consideration of the values and implications of interactive technology.

关键词： human computer interaction

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：