Stefan Rueger

High-dimensional visual vocabularies for image retrieval

In this paper we formulate image retrieval by text query as a vector space classification problem. This is achieved by creating a high-dimensional visual vocabulary that represents the image documents in great detail. We show how the representation of these image documents enables the application of well known text retrieval techniques such as Rocchio tf-idf and naíve Bayes to the semantic image retrieval problem. We tested these methods on a Corel images subset and achieve state-of-the-art retrieval performance using the proposed methods.

International workshop on recommendation and collaboration (ReColl 2008)

The International Workshop on Recommendation and Collaboration (ReColl 2008) aims to identify emerging trends in recommendation technology and collaborative environments in the context of intelligent user interfaces. We explore these two topics separately and the synergies between them.

ICMR 2014: 4th ACM International Conference on Multimedia Retrieval

ICMR was initially started as a workshop on challenges in image retrieval (in Newcastle in 1998 ) and later transformed into the Conference on Image and Video Retrieval (CIVR) series. In 2011 the CIVR and the ACM Workshop on Multimedia Information Retrieval were combined into a single conference that now forms the ICMR series. The 4th ACM International Conference on Multimedia Retrieval took place in Glasgow, Scotland, from 1 – 4 April 2014. This was the largest edition of ICMR to date with approximately 170 attendees from 25 different countries. ICMR is one of the premier scientific conference for multimedia retrieval held worldwide, with the stated mission “to illuminate the state of the art in multimedia retrieval by bringing together researchers and practitioners in the field of multimedia retrieval .” According to the Chinese Computing Federation Conference Ranking (2013), ACM ICMR is the number one multimedia retrieval conference worldwide and the number four conference in the category of multimedia and graphics. Although ICMR is about multimedia retrieval, in a wider sense, it is also about automated multimedia understanding. Much of the work in that area involves the analysis of media on a pixel, voxel, and wavelet level, but it also involves innovative retrieval, visualisation and interaction paradigms utilising the nature of the multimedia — be it video, images, speech, or more abstract (sensor) data. The conference aims to promote intellectual exchanges and interactions among scientists, engineers, students, and multimedia researchers in academia as well as industry through various events, including a keynote talk, oral, special and poster sessions focused on re search challenges and solutions, technical and industrial demonstrations of prototypes, tutorials, research, and an industrial panel. In the remainder of this report we will summarise the events that took place at the 4th ACM ICMR conference.

Movement description and gesture recognition for live media arts

The research aims to develop novel techniques able to recognise different sequential gestures, to the level where they will describe and compute articulated movements in real time. In the context of live media arts, the research outcomes would change the paradigm of creating, learning, performing, designing for live media arts, by giving feedback on performance after analysing, in real time, the streaming video of the performance.

ACM international conference on multimedia retrieval (ICMR 2014)

This article provides a recap of the 4th ACM International Conference on Multimedia Retrieval, which took place in Glasgow, Scotland, from 1-4 April 2014.

Multimedia information retrieval

This tutorial is concerned with creating the best possible multimedia search experience. The intriguing bit here is that the query itself can be a multimedia excerpt: For example, when you walk around in an unknown place and stumble across an interesting landmark, would it not be great if you could just take a picture with your mobile phone and send it to a service that finds a similar picture in a database and tells you more about the building - and about its significance for that matter? The ideas for this type of search have been around for a decade, but this tutorial will look at recent successes and take stock of the state-of-the-art. It examines the full matrix of a variety of query modes versus document types. How do you retrieve a music piece by humming? What if you want to find news video clips on forest fires using a still image? The tutorial discusses underlying techniques and common approaches to facilitate multimedia search engines: metadata driven search; piggy-back text search where automated processes create text surrogates for multimedia; automated image annotation; content-based search. The latter is studied in more depth looking at features and distances, and how to effectively combine them for efficient retrieval, to a point where the participants have the ingredients and recipe in their hands for building their own visual search engines. Supporting users in their resource discovery mission when hunting for multimedia material is not a technological indexing problem alone. We will briefly look at interactive ways of engaging with repositories through browsing and relevance feedback, roping in geographical context, and providing visual summaries for videos. The tutorial emphasises state-of-the-art research in the area of multimedia information retrieval, which gives an indication of the research and development trends and, thereby, a glimpse of the future world.

Dimension-Specific Search for Multimedia Retrieval

Observing that current Global Similarity Measures (GSM) which average the effect of few significant differences on all dimensions may cause possible performance limitation, we propose the first Dimension-specific Similarity Measure (DSM) to take local dimension-specific constraints into consideration. The rationale for DSM is that significant differences on some individual dimensions may lead to different semantics. An efficient search algorithm is proposed to achieve fast Dimension-specific KNN (DKNN) retrieval. Experiment results show that our methods outperform traditional methods by large gaps.