Speech interfaces, such as personal assistants and screen readers, read image captions to users—but typically only one caption is available per image, which may not be adequate for all situations (e.g., browsing large quantities of images). Long provide a deeper understanding an but require more time listen to, whereas shorter allow thorough comprehension, yet have the advantage being faster co...

In this paper we evaluate techniques for browsing photographs on small displays. We present two new interaction techniques that replace conventional scrolling and zooming controls. Via a single user action, scrolling and zooming are inter-dependently controlled with AutoZoom and independently controlled with GestureZoom. Both techniques were evaluated in a large-scale, 72-subject usability expe...

The rectilinear Steiner tree problem i s t o find a manimum-length set of horizontal and vertical line segments that interconnect a given set of points in $he plane. Here we study the thumbnail rectilinear S te iner tree problem, where the inpvt points are drawn f r o m a small integer grid. Specifically, we devise a full-set decomposition algorithm for computing opt ima l thumbnail rectalinear...

Title of dissertation: Techniques for Image Retrieval: Deformation Insensitivity and Automatic Thumbnail Cropping Haibin Ling, Doctor of Philosophy, 2006 Dissertation directed by: Professor David W. Jacobs Department of Computer Science We study several problems in image retrieval systems. These problems and proposed techniques are divided into three parts. Part I: This part focuses on robust o...

Musical perception is non-visual and people cannot describe what a song sounds like without listening to it. To facilitate music browsing and searching, we explore the automatic generation of visual thumbnails for music. Targeting an expert user groups, DJs, we developed a concept named ThumbnailDJ: Based on a metaphor of music notation, a visual thumbnail can be automatically generated for an ...

Photomosaic is a technique which transforms an input image into a rectangular grid of thumbnail images preserving the overall appearance. The typical photomosaic algorithm searches from a large database of images one picture that approximates a block of pixels in the main image. Since the quality of the output depends on the size of the database, it turns out that the bottleneck in each photomo...