Publications

FXPAL publishes in top scientific conferences and journals.

2015
Publication Details
  • International Symposium on Wearable Computers (ISWC)
  • Sep 8, 2015

Abstract

Close
To facilitate distributed communication in mobile settings, we developed a system for creating and sharing gaze anno-tations using head mounted displays, such as Google Glass. Gaze annotations make it possible to point out objects of interest within an image and add a verbal description to it. To create an annotation, the user simply looks at an object of interest in the image and speaks out the information connected to the object. The gaze location is recorded and inserted as a gaze marker and the voice is transcribed using speech recognition. After an annotation has been created, it can be shared with another person. We performed a user study that showed that users experienced that gaze annota-tions add precision and expressiveness compared to an annotation to the whole image.
Publication Details
  • DocEng 2015
  • Sep 8, 2015

Abstract

Close
We present a novel system for detecting and capturing paper documents on a tabletop using a 4K video camera mounted overhead on pan-tilt servos. Our automated system first finds paper documents on a cluttered tabletop based on a text probability map, and then takes a sequence of high-resolution frames of the located document to reconstruct a high quality and fronto-parallel document page image. The quality of the resulting images enables OCR processing on the whole page. We performed a preliminary evaluation on a small set of 10 document pages and our proposed system achieved 98% accuracy with the open source Tesseract OCR engine.
Publication Details
  • DocEng 2015
  • Sep 8, 2015

Abstract

Close
Web-based tools for remote collaboration are quickly becoming an established element of the modern workplace. During live meetings, people share web sites, edit presentation slides, and share code editors. It is common for participants to refer to previously spoken or shared content in the course of synchronous distributed collaboration. A simple approach is to index with Optical Character Recognition (OCR) the video frames, or key-frames, being shared and let user retrieve them with text queries. Here we show that a complementary approach is to look at the actions users take inside the live document streams. Based on observations of real meetings, we focus on two important signals: text editing and mouse cursor motion. We describe the detection of text and cursor motion, their implementation in our WebRTC-based system, and how users are better able to search live documents during a meeting based on these detected and indexed actions.

Abstract

Close
Location-enabled applications now permeate the mobile computing landscape. As technologies like Bluetooth Low Energy (BLE) and Apple's iBeacon protocols begin to see widespread adoption, we will no doubt see a proliferation of indoor location enabled application experiences. While not essential to each of these applications, many will require that the location of the device be true and verifiable. In this paper, we present LocAssure, a new framework for trusted indoor location estimation. The system leverages existing technologies like BLE and iBeacons, making the solution practical and compatible with technologies that are already in use today. In this work, we describe our system, situate it within a broad location assurance taxonomy, describe the protocols that enable trusted localization in our system, and provide an analysis of early deployment and use characteristics. Through developer APIs, LocAssure can provide critical security support for a broad range of indoor location applications.

Assistive Image Comment Robot - A Novel Mid-Level Concept-Based Representation

Publication Details
  • IEEE Transactions on Affective Computing
  • Aug 30, 2015

Abstract

Close
We present a general framework and working system for predicting likely affective responses of the viewers in the social media environment after an image is posted online. Our approach emphasizes a mid-level concept representation, in which intended affects of the image publisher is characterized by a large pool of visual concepts (termed PACs) detected from image content directly instead of textual metadata, evoked viewer affects are represented by concepts (termed VACs) mined from online comments, and statistical methods are used to model the correlations among these two types of concepts. We demonstrate the utilities of such approaches by developing an end-to-end Assistive Comment Robot application, which further includes components for multi-sentence comment generation, interactive interfaces, and relevance feedback functions. Through user studies, we showed machine suggested comments were accepted by users for online posting in 90% of completed user sessions, while very favorable results were also observed in various dimensions (plausibility, preference, and realism) when assessing the quality of the generated image comments.

Abstract

Close
In this paper we report findings from two user studies that explore the problem of establishing common viewpoint in the context of a wearable telepresence system. In our first study, we assessed the ability of a local person (the guide) to identify the view orientation of the remote person by looking at the physical pose of the telepresence device. In the follow-up study, we explored visual feedback methods for communicating the relative viewpoints of the remote user and the guide via a head-mounted display. Our results show that actively observing the pose of the device is useful for viewpoint estimation. However, in the case of telepresence devices without physical directional affordances, a live video feed may yield comparable results. Lastly, more abstract visualizations lead to significantly longer recognition times, but may be necessary in more complex environments.
Publication Details
  • IEEE Pervasive Computing
  • Jul 1, 2015

Abstract

Close
Tutorials are one of the most fundamental means of conveying knowledge. In this paper, we present a suite of applications that allow users to combine different types of media captured from handheld, standalone, or wearable devices to create multimedia tutorials. We conducted a study comparing standalone (camera on tripod) versus wearable capture (Google Glass). The results show that tutorial authors have a slight preference for wearable capture devices, especially when recording activities involving larger objects.

POLI: MOBILE AR BY HEARING POSITION FROM LIGHT

Publication Details
  • ICME 2015 Mobile Multimedia Workshop
  • Jun 29, 2015

Abstract

Close
Connecting digital information to physical objects can enrich their content and make them more vivid. Traditional augmented reality techniques reach this goal by augmenting physical objects or their surroundings with various markers and typically require end users to wear additional devices to explore the augmented content. In this paper, we propose POLI, which allows a system administrator to author digital content with his/her mobile device while allows end-users to explore the authored content with their mobile devices. POLI provides three novel interactive approaches for authoring digital content. It does not change the nature appearances of physical objects and does not require users to wear any additional hardware on their bodies.

Abstract

Close
As video-mediated communication reaches broad adoption, improving immersion and social interaction are important areas of focus in the design of tools for exploration and work-based communication. Here we present three threads of research focused on developing new ways of enabling exploration of a remote environment and interacting with the people and artifacts therein.
Publication Details
  • Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
  • Apr 18, 2015

Abstract

Close
Edge targets, such as buttons or menus along the edge of a screen, are known to afford fast acquisition performance in desktop mousing environments. As the popularity of touch based devices continues to grow, understanding the affordances of edge targets on touchscreen is needed. This paper describes results from two controlled experiments that examine in detail the effect of edge targets on performance in touch devices. Our results shows that on touch devices, a target's proximity to the edge has a significant negative effect on reaction time. We examine the effect in detail and explore mitigating factors. We discuss potential explanations for the effect and propose implications for the design of efficient interfaces for touch devices.
Publication Details
  • CHI 2015 (Extended Abstracts)
  • Apr 18, 2015

Abstract

Close
We present our ongoing research on automatic segmentation of motion gestures tracked by IMUs. We postulate that by recognizing gesture execution phases from motion data that we may be able to auto-delimit user gesture entries. We demonstrate that machine learning classifiers can be trained to recognize three distinct phases of gesture entry: the start, middle and end of a gesture motion. We further demonstrate that this type of classification can be done at the level of individual gestures. Furthermore, we describe how we captured a new data set for data exploration and discuss a tool we developed to allow manual annotations of gesture phase information. Initial results we obtained using the new data set annotated with our tool show a precision of 0.95 for recognition of the gesture phase and a precision of 0.93 for simultaneous recognition of the gesture phase and the gesture type.
Publication Details
  • CHI 2015
  • Apr 18, 2015

Abstract

Close
Websites can record individual users' activities and display them in a variety of ways. There is a tradeoff between detail and abstraction in visualization, especially when the amount of content increases and becomes more difficult to process. We conducted an experiment on Mechanical Turk varying the quality, detail, and visual presentation of information about an individual's past work to see how these design features affected perceptions of the worker. We found that providing detail in the display through text increased processing time and led to less positive evaluations. Visually abstract displays required less processing time but decreased confidence in evaluation. This suggests that different design parameters may engender differing psychological processes that influence reactions towards an unknown person.
Publication Details
  • CSCW 2015
  • Mar 14, 2015

Abstract

Close
Collaboration Map (CoMap) is an interactive visualization tool showing temporal changes of small group collaborations. As dynamic entities, collaboration groups have flexible features such as people involved, areas of work, and timings. CoMap shows a graph of collaborations during user-adjustable periods, providing overviews of collaborations' dynamic features. We demonstrate CoMap with a co-authorship dataset extracted from DBLP to visualize 587 publications by 29 researchers at a research organization.

Abstract

Close
In this paper, we report findings from a study that compared basic video-conferencing, emergent kinetic video-conferencing techniques, and face-to-face meetings. In our study, remote and co-located participants worked together in groups of three. We show, in agreement with prior literature, the strong adverse impact of being remote on participation-levels. We also show that local and remote participants perceived differently their own contributions and others. Extending prior work, we also show that local participants exhibited significantly more overlapping speech with remote participants who used an embodied proxy, than with remote participants in basic-video conferencing (and at a rate similar to overlapping speech for co-located groups). We also describe differences in how the technologies were used to follow conversation. We discuss how these findings extend our understanding of the promise and potential limitations of embodied video-conferencing solutions.

Abstract

Close
In a variety of peer production settings, from Wikipedia to open source software development to crowdsourcing, individuals may encounter, edit, or review the work of unknown others. Typically this is done without much context to the person's past behavior or performance. To understand how exposure to an unknown individual's activity history influences attitudes and behaviors, we conducted an online experiment on Mechanical Turk varying the content, quality, and presentation of information about another Turker's work history. Surprisingly, negative work history did not lead to negative outcomes, but in contrast, a positive work history led to positive initial impressions that persisted in the face of contrary information. This work provides insight into the impact of activity history design factors on psychological and behavioral outcomes that can be of use in other related settings.

Abstract

Close
Our research focuses on improving the effectiveness and usability of driving mobile telepresence robots by increasing the user's sense of immersion during the navigation task. To this end we developed a robot platform that allows immersive navigation using head-tracked stereoscopic video and a HMD. We present the result of an initial user study that compares System Usability Scale (SUS) ratings of a robot teleoperation task using head-tracked stereo vision with a baseline fixed video feed and the effect of a low or high placement of the camera(s). Our results show significantly higher ratings for the fixed video condition and no effect of the camera placement. Future work will focus on examining the reasons for the lower ratings of stereo video and and also exploring further visual navigation interfaces.
Publication Details
  • The Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI-15)
  • Jan 25, 2015

Abstract

Close
Name of an identity is strongly influenced by his/her cultural background such as gender and ethnicity, both vital attributes for user profiling, attribute-based retrieval, etc. Typically, the associations between names and attributes (e.g., people named "Amy" are mostly females) are annotated manually or provided by the census data of governments. We propose to associate a name and its likely demographic attributes by exploiting click-throughs between name queries and images with automatically detected facial attributes. This is the first work attempting to translate an abstract name to demographic attributes in visual-data-driven manner, and it is adaptive to incremental data, more countries and even unseen names (the names out of click-through data) without additional manual labels. In the experiments, the automatic name-attribute associations can help gender inference with competitive accuracy by using manual labeling. It also benefits profiling social media users and keyword-based face image retrieval, especially for contributing 12% relative improvement of accuracy in adapting to unseen names.
2014

Synchronizing Web Documents with Style

Publication Details
  • ACM Brazilian Symposium on Multimedia and the Web
  • Nov 17, 2014

Abstract

Close
In this paper we report on our efforts to define a set of document extensions to Cascading Style Sheets (CSS) that allow for structured timing and synchronization of elements within a Web page. Our work considers the scenario in which the temporal structure can be decoupled from the content of the Web page in a similar way that CSS does with the layout, colors and fonts. Based on the SMIL (Synchronized Multimedia Integration Language) temporal model we propose CSS document extensions and discuss the design and implementation of a proof of concept that realizes our contributions. As HTML5 seems to move away from technologies like Flash and XML (eXtensible Markup Language), we believe our approach provides a flexible declarative solution to specify rich media experiences that is more aligned with current Web practices.
Publication Details
  • ACM International Workshop on Understanding and Modeling Multiparty, Multimodal Interactions (UMMMI)
  • Nov 15, 2014

Abstract

Close
In this paper we discuss communication problems in video-mediated small group discussions. We present results from a study in which ad-hoc groups of five people, with moderator, solved a quiz question-select answer style task over a video-conferencing system. The task was performed under different delay conditions, of up to 2000ms additional one-way delay. Even with a delay up to 2000ms, we could not observe any effect on the achieved quiz scores. In contrast, the subjective satisfaction was severely negatively affected. While we would have suspected a clear conversational breakdown with such a high delay, groups adapted their communication style and thus still managed to solve the task. This is, most groups decided to switch to a more explicit turn-taking scheme. We argue that future video-conferencing systems can provide a better experience if they are aware of the current conversational situation and can provide compensation mechanisms. Thus we provide an overview of what cues are relevant and how they are affected by the video-conferencing system and how recent advancements in computational social science can be leveraged. Further, we provide an analysis of the suitability of normal webcam data for such cue recognition. Based on our observations, we suggest strategies that can be implemented to alleviate the problems.
Publication Details
  • ACM International Workshop on Socially-aware Multimedia (SAM)
  • Nov 6, 2014

Abstract

Close
As commercial, off-the-shelf, services enable people to easily connect with friends and relatives, video-mediated communication is filtering into our daily activities. With the proliferation of broadband and powerful devices, multi-party gatherings are becoming a reality in home environments. With the technical infrastructure in place and has been accepted by a large user base, researchers and system designers are concentrating on understanding and optimizing the Quality of Experience (QoE) for participants. Theoretical foundations for QoE have identified three crucial factors for understanding the impact on the individual’s perception: system, context, and user. While most of the current research tends to focus on the system factors (delay, bandwidth, resolution), in this paper we offer a more complete analysis that takes into consideration context and user factors. In particular, we investigate the influence of delay (constant system factor) in the QoE of multi-party conversations. Regarding the context, we extend the typical one-to-one condition to explore conversations between small groups (up to five people). In terms of user factors, we take into account conversation analysis, turn-taking and role-theory, for better understanding the impact of different user profiles. Our investigation allows us to report a detailed analysis on how delay influences the QoE, concluding that the actual interactivity pattern of each participant in the conversation results on different noticeability thresholds of delays. Such results have a direct impact on how we should design and construct video-communication services for multi-party conversations, where user activity should be considered as a prime adaptation and optimization parameter.

Multi-modal Language Models for Lecture Video Retrieval

Publication Details
  • ACM Multimedia 2014
  • Nov 2, 2014

Abstract

Close
We propose Multi-modal Language Models (MLMs), which adapt latent variable models for text document analysis to modeling co-occurrence relationships in multi-modal data. In this paper, we focus on the application of MLMs to indexing slide and spoken text associated with lecture videos, and subsequently employ a multi-modal probabilistic ranking function for lecture video retrieval. The MLM achieves highly competitive results against well established retrieval methods such as the Vector Space Model and Probabilistic Latent Semantic Analysis. Retrieval performance with MLMs is also shown to improve with the quality of the available extracted spoken text.

Social Media-based Profiling of Store Locations

Publication Details
  • ACM Multimedia Workshop on Geotagging and Its Applications in Multimedia
  • Nov 2, 2014

Abstract

Close
We present a method for profiling businesses at specific locations that is based on mining information from social media. The method matches geo-tagged tweets from Twitter against venues from Foursquare to identify the specific business mentioned in a tweet. By linking geo-coordinates to places, the tweets associated with a business, such as a store, can then be used to profile that business. We used a sentiment estimator developed for tweets to create sentiment profiles of the stores in a chain, computing the average sentiment of tweets associated with each store. We present the results as heatmaps which show how sentiment differs across stores in the same chain and how some chains have more positive sentiment than other chains. We also created profiles of social group size for businesses and show sample heatmaps illustrating how the size of a social group can vary.

On Aesthetics and Emotions in Scene Images: A Computational Perspective.

Publication Details
  • Book: Scene Vision, MIT Press, (Editors Kestas Kveraga and Moshe Bar).
  • Nov 1, 2014

Abstract

Close
In this chapter, we discuss the problem of computational inference of aesthetics and emotions from images. We draw inspiration from diverse disciplines such as philosophy, photography, art, and psychology to define and understand the key concepts of aesthetics and emotions. We introduce the primary computational problems that the research community has been striving to solve and the computational framework required for solving them. We also describe datasets available for performing assessment and outline several real-world applications where research in this domain can be employed. This chapter discusses the contributions of a significant number of research articles that have attempted to solve problems in aesthetics and emotion inference in the last several years. We conclude the chapter with directions for future research. Here’s a link to the book.
http://mitpress.mit.edu/books/scene-vision
Publication Details
  • UIST 2014
  • Oct 5, 2014

Abstract

Close
Video Text Retouch is a technique for retouching textual content found in many online videos such as screencasts, recorded presentations and many online e-learning videos. Viewed through our special, HTML5-based player, users can edit in real-time the textual content of the video frames, such as correcting typos or inserting new words between existing characters. Edits are overlaid and tracked at the desired position for as long as the original video content remains similar. We describe the interaction techniques, image processing algorithms and give implementation details of the system.

Abstract

Close
It is now possible to develop head-mounted devices (HMDs) that allow for ego-centric sensing of mid-air gestural input. Therefore, we explore the use of HMD-based gestural input techniques in smart space environments. We developed a usage scenario to evaluate HMD-based gestural interactions and conducted a user study to elicit qualitative feedback on several HMD-based gestural input techniques. Our results show that for the proposed scenario, mid-air hand gestures are preferred to head gestures for input and rated more favorably compared to non-gestural input techniques available on existing HMDs. Informed by these study results, we developed a prototype HMD system that supports gestural interactions as proposed in our scenario. We conducted a second user study to quantitatively evaluate our prototype comparing several gestural and non-gestural input techniques. The results of this study show no clear advantage or disadvantage of gestural inputs vs.~non-gestural input techniques on HMDs. We did find that voice control as (sole) input modality performed worst compared to the other input techniques we evaluated. Lastly, we present two further applications implemented with our system, demonstrating 3D scene viewing and ambient light control. We conclude by briefly discussing the implications of ego-centric vs.~exo-centric tracking for interaction in smart spaces.