HCI Bibliography Home | HCI Conferences | HCM Archive | Detailed Records | RefWorks | EndNote | Hide Abstracts
HCM Tables of Contents: 060708

Proceedings of the 2007 ACM International Workshop on Human-Centered Multimedia

Fullname:HCM'07: Proceedings of the 2nd ACM International Workshop on Human-Centered Multimedia
Editors:Alejandro Jaimes; Nicu Sebe
Location:Augsburg, Bavaria, Germany
Standard No:ISBN: 1-59593-781-1, 978-1-59593-781-0; ACM DL: Table of Contents hcibib: HCM07
  1. Overview
  2. Session 1
  3. Session 2
  4. Session 3


International workshop on human-centered multimedia: overview BIBAKFull-Text 1-2
  Alejandro Jaimes; Nicu Sebe
In this paper we describe the scope and goals of the International Workshop on Human-Centered Multimedia held in conjunction with ACM Multimedia 2007, and give an overview of some of the papers and ideas presented in the first version of the workshop held in conjunction with the same conference in 2006.
Keywords: human-centered computing, human-computer interfaces, multimedia, multimodal interaction

Session 1

Pillows as adaptive interfaces in ambient environments BIBAKFull-Text 3-12
  Frank Nack; Thecla Schiphorst; Zeljko Obrenovic; Michiel KauwATjoe; Simon de Bakker; Angel Perez Rosillio; Lora Aroyo
We have developed a set of small interactive throw pillows containing intelligent touch-sensing surfaces, in order to explore new ways to model the environment, participants, artefacts, and their interactions, in the context of expressive non-verbal interaction. We present the overall architecture of the environment, describing a model of the user, the interface (the interactive pillows and the devices it can interact with) and the context engine. We describe the representation and process modules of the context engine and demonstrate how they support real-time adaptation. We present an evaluation of the current prototype and conclude with plans for future work.
Keywords: haptic sensing, human-centred computing, input devices and strategies, presence, social interaction, tactile UIs, tangible UI, user experience design
Music emotion recognition: the role of individuality BIBAKFull-Text 13-22
  Yi-Hsuan Yang; Ya-Fan Su; Yu-Ching Lin; Homer H. Chen
It has been realized in the music emotion recognition (MER) community that personal difference, or individuality, has significant impact on the success of an MER system in practice. However, no previous work has explicitly taken individuality into consideration in an MER system. In this paper, the group-wise MER approach (GWMER) and personalized MER approach (PMER) are proposed to study the role of individuality. GWMER evaluates the importance of each individual factor such as sex, personality, and music experience, whereas PMER evaluates whether the prediction accuracy for a user is significantly improved if the MER system is personalized for the user. Experimental results demonstrate the effect of personalization and suggest the need for a better representation of individuality and for better prediction accuracy.
Keywords: individuality, music emotion recognition, personalization
Tracking pointing gesture in 3D space for wearable visual interfaces BIBAKFull-Text 23-30
  Yunde Jia; Shanqing Li; Yang Liu
This paper proposes a practical method of tracking pointing gesture in 3D space for wearable visual interfaces. We integrate dense depth maps and contour cues to achieve more stable tracking performance. A strategy of fusing information from selective attention maps and synthetical feature maps is presented for locating the focus of attention pointed at by pointing gesture. We have developed a wearable stereo vision system for pointing gesture tracking, called POGEST, with FPGA-based dense depth mapping at video rate. The system enables a wearer to locate and select an object in 3D space using his/her pointing hand. A common focus of attention shared by a wearer and a computer is established for natural human computer interaction. We also discuss an application of locating objects in 3D virtual environments.
Keywords: gesture recognition, hand tracking, real time system, visual interface, wearable vision
Affective multimodal mirror: sensing and eliciting laughter BIBAKFull-Text 31-40
  Willem A. Melder; Khiet P. Truong; Marten Den Uyl; David A. Van Leeuwen; Mark A. Neerincx; Lodewijk R. Loos; B. Stock Plum
In this paper, we present a multimodal affective mirror that senses and elicits laughter. Currently, the mirror contains a vocal and a facial affect-sensing module, a component that fuses the output of these two modules to achieve a user-state assessment, a user state transition model, and a component to present audiovisual affective feedback that should keep or bring the user in the intended state. Interaction with this intelligent interface involves a full cyclic process of sensing, interpreting, reacting, sensing (of the reaction effects), interpreting. The intention of the mirror is to evoke positive emotions, to make people laugh and to increase the laughter. The first user experiences tests showed that users show cooperative behavior, resulting in mutual user-mirror action-reaction cycles. Most users enjoyed the interaction with the mirror and immersed in an excellent user experience.
Keywords: affective mirror, face voice emotion expression, multi modal laughter recognition

Session 2

Towards open source authoring and presentation of multimedia content BIBAKFull-Text 41-46
  Nikitas M. Sgouros; Alexandros Margaritis
Open source principles and methodologies allow open access to both the development process and its products. This paper describes a number of significant research issues for the creation of novel development environments that support open source authoring of multimedia content and dynamic forms of personalization during content consumption. These environments should allow an unlimited number of users to modify existing media content and post their contributions on the net. In addition, they should allow users to visualize the current state of development in each project, select a subset of the various contributions and dynamically compose, view and share with other users new content versions containing all the selected contributions. Furthermore, the paper describes a pilot web-services-based implementation for such a system developed in C# that is now freely available on the Web.
Keywords: authoring paradigms, open source, personalization tools, visualization
Preattentive visualization of information relevance BIBAKFull-Text 47-56
  Matthias Deller; Achim Ebert; Michael Bender; Stefan Agne; Henning Barthel
When presenting complex, multidimensional data to users, emphasis of relevant information plays an important role. Especially when data is arranged according to several criteria, the simultaneous use of multiple visualization metaphors frequently results in information overload and unintuitive visualizations. In this paper, we present a comparison of preattentive visual features specifically for highlighting relevance of data extracted from electronic documents in an information-rich virtual environment. Several visual cues were evaluated with regard to their effectivity, comprehensibility and influence on other visualized features. At the same time we introduce two innovative data handling techniques to achieve practical applicability of our system: An intuitive way to reduce visual cluttering of information by filtering information based on its visual depth and a way to efficiently utilize visualizations of different dimensions -- dimensional congruence.
Keywords: human factors, performance, user-centered design
Local spatiotemporal descriptors for visual recognition of spoken phrases BIBAKFull-Text 57-66
  Guoying Zhao; Matti Pietikäinen; Abdenour Hadid
Visual speech information plays an important role in speech recognition under noisy conditions or for listeners with hearing impairment. In this paper, we propose local spatiotemporal descriptors to represent and recognize spoken isolated phrases based solely on visual input. Positions of the eyes determined by a robust face and eye detector are used for localizing the mouth regions in face images. Spatiotemporal local binary patterns extracted from these regions are used for describing phrase sequences. In our experiments with 817 sequences from ten phrases and 20 speakers, promising accuracies of 62% and 70% were obtained in speaker-independent and speaker-dependent recognition, respectively. In comparison with other methods on the Tulips1 audio-visual database, the accuracy 92.7% of our method clearly out performs the others. Advantages of our approach include local processing and robustness to monotonic gray-scale changes. Moreover, no error prone segmentation of moving lips is needed.
Keywords: face and eye detection, local spatiotemporal descriptors, mouth region localization, visual speech recognition
Interconnected media for human-centered understanding BIBAKFull-Text 67-76
  Katja Einsfeld; Achim Ebert; Jürgen Wölle
Today, there are many systems with large amounts of complex data sets. Visualizing these systems in a way that enlightens the user and provides a profound understanding ofthe respective information space is one of the big information visualization research challenges. Keim states that it is no longer possible to display an overview of these systems as proposed in Shneiderman's information seeking mantra. To overcome this incapacity and to provide a solution to the dilemma of time multiplexing vs. space multiplexing techniques, we propose the context-sensitive use of a collection of animated 3D metaphors. These metaphors are integrated in a flexible framework called HANNAH. This provides the possibility to interconnect media of various types in order to bridge the semantic gab as required for human-centered applications according to Elgammal.
Keywords: 3D, human centered interfaces, information visualization

Session 3

Multimedia and human-in-the-loop: interaction as content enrichment BIBAKFull-Text 77-84
  Bruno Emond
The current work is part of the broadband visual research program at the Institute for Information Technology (National Research Council Canada). The research program is currently focused on developing human-centered multimedia technology to support large group visual communication and collaboration. This paper outlines some conceptual foundations for the development of a human-centered multimedia research tool to capture interaction data, which could be linked to users cognitive processing. The approach is based on the notion of multimedia interaction as content enrichment and on cognitive modeling methodology.
Keywords: cognitive modeling, context, human interaction modeling from multimedia, task modeling in multimedia systems, unified theories of cognition, user
Too close for comfort?: adapting to the user's cultural background BIBAKFull-Text 85-94
  Matthias Rehm; Nikolaus Bee; Birgit Endrass; Michael Wissner; Elisabeth André
The cultural context of the user is a largely neglected aspect of human centered computing. This is because culture is a very fuzzy concept and even with a computational model of culture it remains difficult to derive the necessary information to recognize the user's cultural background. Such information is only indirectly available and has to be derived from the observable multimodal behavior of the user. We propose the usage of a dimensional model of culture that allows applying computational methods to derive a user's cultural background and to adjust the system's behavior accordingly. To this end, a Bayesian network is applied to allow for the necessary inferences despite the fact that the given knowledge about the user's behavior is incomplete and unreliable.
Keywords: Bayesian network modeling, cultural computing, embodied conversational agents
Human support improvements by natural man-machine collaboration BIBAKFull-Text 95-101
  Motoyuki Ozeki; Yasushi Miyata; Hideki Aoyama; Yuichi Nakamura
In this paper, we propose a novel framework that improves the recognition performance of human support systems, and then discuss why our framework is Human-Centered. A Human-Centered system should have a high recognition ability with minimum burden on the user. Our framework aims to satisfy this requirement by using an artificial agent between a recognition system and the user. If a system is in a difficult situation concerning recognition, an agent will require the user's help. For example, if an object that a system aims to recognize is hidden by the user's hand, the agent will ask the user to move his/her hand. Based on this idea, we implemented a prototype system with two modules: a recognition module to recognize objects and user's motions and an agent module to ask for a user's cooperative action. In the experiment, our prototype system recovers around 50%-70% of the recognition failures caused by three typical difficult situations. The user study reveals that our prototype system has the potential to realize natural and considerate human support systems.
Keywords: human-centered computing, interactive system