No abstract

Camera phones present new opportunities and challenges for mobile information association and retrieval. The visual input in the real environment is a new and rich interaction modality between a mobile user and vast information base connected to a user's device via rapidly advancing communication infrastructure. We have developed a system for tourist information access to provide scene description based on an image taken of the scene. In this paper, we describe the working system, the STOIC 101 database, and a new pattern discovery algorithm to learn image patches that are recurrent within a scene class and discriminative across others. We report preliminary scene recognition results on 90 scenes, trained on 5 images per scene, with an accuracy of 92% and 88% on a test set of 110 images, with and without location priming. MOBILE VISUAL COMMUNICATIONCamera phones are becoming ubiquitous imaging devices: almost 9 out of 10 (89%) consumers will have cameras on their phones by 2009 (as forecasted by InfoTrends/Cap Ventures at www.capv.com). In 2007, camera phones will outsell all standalone cameras (i.e. film, single-use, and digital cameras combined). With this new non-voice non-text input modality augmented on a pervasive communication and computing device such as mobile phone, we witness emerging social practices of personal visual information authoring and sharing [1] and exploratory technical innovations to engineer intuitive, efficient, and enjoyable interaction interfaces [2].In this paper, we present our study on using image input modalilty for information access in tourism applications. We describe a working system that provides multi-modal description (text, audio, and visual) of a tourist attraction based on its image captured and sent by a camera phone (Fig. 1). A recent field study [3] concludes that a significant number of tourists (37%) embraced the use of image-based object identification even when image recognition is a complex, lengthy and error-prone process. We aim to fulfill the strong desire of mobile tour guide users to obtain information on objects they come across during their visit, akin to pointing to a building or statue and asking a human tour guide "What's that?".The AGAMEMNON project [4] also focuses on the use of mobile devices with embedded cameras to enhance visits Fig. 1. Image-based mobile tour guide of both archeological sites and museums.With the working rules that the input images are taken without or with minimum clutter, occlusion, and imaging variances in scale, translation, and illumination, a 95% recognition rate on 113 test images with 115 training images of only 4 target objects from 2 sites using mainly edge-based features has been reported.The IDeixis system [5] is oriented towards using mobile image content with keywords extracted from matching webpages to display relevant websites for user to select and browse. The image database was constructed from 12, 000 web-crawled images where the qualities are difficult to control and the 50 test query images were centered arou...

No abstract

International audienceAutomatic query expansion techniques are widely applied for improving text retrieval performance, using a variety of approaches that exploit several data sources for finding expansion terms. Selecting expansion terms is challenging and requires a framework capable of extracting term relationships. Recently, several Natural Language Processing methods , based on Deep Learning, are proposed for learning high quality vector representations of terms from large amounts of unstructured text data with billions of words. These high quality vector representations capture a large number of term relationships. In this paper, we experimentally compare several expansion methods with expansion using these term vector representations. We use language models for information retrieval to evaluate expansion methods. The experiments are conducted on four CLEF collections show a statistically significant improvement over the language models and other expansion models

No abstract