Vidya Setlur

Retargeting Images and Video for Preserving Information Saliency

A nonphotorealistic algorithm for retargeting images adapts large images so that important objects in the image are still recognizable when displayed at a lower target resolution. Unlike existing image manipulation techniques such as cropping and scaling, the retargeting algorithm can handle multiple important objects in an image. To identify the important objects in an image, we must first segment the image. We use mean-shift image segmentation to decompose an image into homogeneous regions.

The tilt cursor: enhancing stimulus-response compatibility by providing 3d orientation cue of pen

In order to improve stimulus-response compatibility of touchpad in pen-based user interface, we present the tilt cursor, i.e. a cursor dynamically reshapes itself to providing the 3D orientation cue of pen. We also present two experiments that evaluate the tilt cursors performance in circular menu selection and specific marking menu selection tasks. Results show that in a specific marking menu selection task, the tilt cursor significantly outperforms the shape-fixed arrow cursor and the live cursor [4]. In addition, results show that by using the tilt cursor, the response latencies for adjusting drawing directions are smaller than that by using the other two kinds of cursors.

Let's play chinese characters: mobile learning approaches via culturally inspired group games

In many developing countries such as India and China, low educational levels often hinder economic empowerment. In this paper, we argue that mobile learning games can play an important role in the Chinese literacy acquisition process. We report on the unique challenges in the learning Chinese language, especially its logographic writing system. Based on an analysis of 25 traditional Chinese games currently played by children in China, we present the design and implementation of two culturally inspired mobile group learning games, Multimedia Word and Drumming Strokes. These two mobile games are designed to match Chinese childrens understanding of everyday games. An informal evaluation reveals that these two games have the potential to enhance the intuitiveness and engagement of traditional games, and children may improve their knowledge of Chinese characters through group learning activities such as controversy, judgments and self-correction during the game play.

Mobile camera-based adaptive viewing

In this paper, we present an approach for facilitating user interaction on mobile devices, focusing on camera-enabled mobile phones. A user interacts with an application by moving their device. An on-board camera is used to capture incoming video and the scrolling direction and magnitude are estimated using a computer vision-based algorithm. The direction is used as the scroll direction in the application, and the magnitude is used to set the zoom level. The camera is treated as a pointing device and zoom level control in applications. Our approach generates mouse events, so any application that is mouse-driven can make use of this technique. The user is free to browse through large data sets on a limited size display with one hand, ideal for the mobile domain.

Camera-Based virtual environment interaction on mobile devices

Mobile virtual environments, with real-time 3D and 2D graphics, are now possible on smart phone and other camera-enabled devices. Using computer vision, the camera sensor can be treated as an input modality in applications by analyzing the incoming live video. We present our tracking algorithm and several mobile virtual environment and gaming prototypes including: a 3D first person shooter, a 2D puzzle game and a simple action game. Camera-based interaction provides a user experience that is not possible through traditional means, and maximizes the use of the limited display size.

Semanticons: Visual Metaphors as File Icons

Semanticons can enhance the representation of files by offering symbols that are both meaningful and easily distinguishable. The semantics of a file is estimated by parsing its name, location, and content to generate a ‘context’, which is used to query an image database. The resulting images are simplified by segmenting them, computing an importance value for each segmented region, and removing unimportant regions. The

Towards designing better map interfaces for the mobile: experiences from example

Creating user friendly map interfaces for the mobile platform presents several challenges that are uniquely different from those of their desktop counterparts. High resolution, photo realistic maps can now be displayed on mobile phones. While these graphics are visually pleasing, they do impact the users cognitive load. Further, small displays and limited interaction capabilities often make mobile map-based systems difficult to design and frustrating to use. In this paper, we discuss lessons learnt from designing and implementing mobile map interfaces through two examples: tourist maps and traffic maps. In particular, we discuss the rendering, user interaction, and system adaptations required for these mobile map interfaces.

Visual summaries of popular landmarks from community photo collections

We present a novel data-driven algorithm that leverages online image repositories such as Flickr for automatically generating tourist maps. Our hypothesis is that, given a large enough dataset of images with geo-based metadata, clusters of matching images from that dataset tend to provide reliable cues as to what the popular tourist spots for that location may be. Our algorithm takes the geographical area of interest as input and retrieves geotagged photos from online photo collections. By clustering the photos based on their locations and identifying the popular tags for each cluster, our algorithm generates a set of points of interest (POIs) for the area. After retrieving additional photos based on these discovered POI tags, we use image matching to find the most representative landmark view for each POI. Finally, we remove clutter from the representative image and apply non-photorealistic rendering techniques to generate a map icon for each landmark. We use our system to automatically generate maps showing popular tourist locations for several large cities.

Planning, apps, and the high-end smartphone: exploring the landscape of modern cross-device reaccess

The rapid growth of mobile devices has made it challenging for users to maintain a consistent digital history among all their personal devices. Even with a variety of cloud computing solutions, users continue to redo web searches and reaccess web content that they already interacted with on another device. This paper presents insights into the cross-device reaccess habits of 15 smart-phone users. We studied how they reaccessed content between their computer and smartphone through a combination of data logging, a screenshot-based diary study, and user interviews. From 1276 cross-device reaccess events we found that users reaccess content between their phone and computer with comparable frequency, and that users rarely planned ahead for their reaccess needs. Based on our findings, we present opportunities for building future mobile systems to support the unplanned activities and content reaccess needs of mobile users.

Automatic generation of semantic icon encodings for visualizations

Authors use icon encodings to indicate the semantics of categorical information in visualizations. The default icon libraries found in visualization tools often do not match the semantics of the data. Users often manually search for or create icons that are more semantically meaningful. This process can hinder the flow of visual analysis, especially when the amount of data is large, leading to a suboptimal user experience. We propose a technique for automatically generating semantically relevant icon encodings for categorical dimensions of data points. The algorithm employs natural language processing in order to find relevant imagery from the Internet. We evaluate our approach on Mechanical Turk by generating large libraries of icons using Tableau Public workbooks that represent real analytical effort by people out in the world. Our results show that the automatic algorithm does nearly as well as the manually created icons, and particularly has higher user satisfaction for larger cardinalities of data.