P. Punitha

TV news story segmentation based on semantic coherence and content similarity

In this paper, we introduce and evaluate two novel approaches, one using video stream and the other using close-caption text stream, for segmenting TV news into stories. The segmentation of the video stream into stories is achieved by detecting anchor person shots and the text stream is segmented into stories using a Latent Dirichlet Allocation (LDA) based approach. The benefit of the proposed LDA based approach is that along with the story segmentation it also provides the topic distribution associated with each segment. We evaluated our techniques on the TRECVid 2003 benchmark database and found that though the individual systems give comparable results, a combination of the outputs of the two systems gives a significant improvement over the performance of the individual systems.

Diversity, Assortment, Dissimilarity, Variety: A Study of Diversity Measures Using Low Level Features for Video Retrieval

In this paper we present a number of methods for re-ranking video search results in order to introduce diversity into the set of search results. The usefulness of these approaches is evaluated in comparison with similarity based measures, for the TRECVID 2007 collection and tasks [11]. For the MAP of the search results we find that some of our approaches perform as well as similarity based methods. We also find that some of these results can improve the P@N values for some of the lower N values. The most successful of these approaches was then implemented in an interactive search system for the TRECVID 2008 interactive search tasks. The responses from the users indicate that they find the more diverse search results extremely useful.

Statement-Based Semantic Annotation of Media Resources

Currently the media production domain lacks efficient ways to organize and search for media assets. Ontology-based applications have been identified as a viable solution to this problem, however, sometimes being too complex for non-experienced users. We present a fast and easy to use approach to create semantic annotations and relationships of media resources. The approach is implemented in the SALERO Intelligent Media Annotation & Search system. It combines the simplicity of free text tagging and the power of semantic technologies and by that makes a compromise in the complexity of full semantic annotations. We present the implementation of the approach in the system and an evaluation of different user interface techniques for creating annotations.

Video redundancy detection in rushes collection

The rushes is a collection of raw material videos. There are various redundancies, such as rainbow screen, clipboard shot, white/black view, and unnecessary re-take. This paper develops a set of solutions to remove these video redundancies as well as an effective system for video summarisation. We regard manual editing effects, e.g. clipboard shots, as differentiators in the visual language. A rushes video is therefore divided into a group of subsequences, each of which stands for a re-take instance. A graph matching algorithm is proposed to estimate the similarity between re-takes and suggests the best instance for content presentation. The experiments on the Rushes 2008 collection show that a video can be shortened to 4%-16% of the original size by redundancy detection. This significantly reduces the complexity in content selection and leads to an effective and efficient video summarisation system.

Topic prerogative feature selection using multiple query examples for automatic video retrieval

Well acceptance of relevance feedback and collaborative systems has given the users to express their preferences in terms of multiple query examples. The technology devised to utilize these user preferences, is expected to mine the semantic knowledge embedded within these query examples. In this paper, we propose a video mining framework based on dynamic learning from queries, using a statistical model for topic prerogative feature selection. The proposed method is specifically designed for multiple query example scenarios. The effectiveness of the proposed framework has been established with an extensive experimentation on TRECVid2007 data collection. The results reveal that our approach achieves a performance that is in par with the best results for this corpus without the requirement of any textual data.

Concept, content and the convict

This paper describes the concepts behind and implementation of the multimedia art work Alan01 / AlanOnline, which wakes up the 1952 criminally convicted Alan Turing as a piece of code within the art work - thus fulfilling Turings own vision of preserving human consciousness in a computer. The works context is described within the development of associative storytelling structures built up by interactive user feedback via an image and video retrieval system. The input to the retrieval system is generated by Alan01 / AlanOnline via their respective sketch interfaces, the output of the retrieval system being fed back to Alan01 / AlanOnline for further processing and presentation to the user within the context of the overall artistic experience. This paper, in addition to presenting the productions and image retrieval system, also presents the installation and online production user reception and some of the issues and observations made during the development of the systems.

University of Glasgow at ImageCLEFPhoto 2009: optimising similarity and diversity in image retrieval

In this paper we describe the approaches adopted to generate the runs submitted to ImageCLEFPhoto 2009 with an aim to promote document diversity in the rankings. Four of our runs are text based approaches that employ textual statistics extracted from the captions of images, i.e. MMR [1] as a state of the art method for result diversification, two approaches that combine relevance information and clustering techniques, and an instantiation of Quantum Probability Ranking Principle. The fifth run exploits visual features of the provided images to re-rank the initial results by means of Factor Analysis. The results reveal that our methods based on only text captions consistently improve the performance of the respective baselines, while the approach that combines visual features with textual statistics shows lower levels of improvements.