Anuj Goyal

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.

TVNViewer: An interactive visualization tool for exploring networks that change over time or space

UNLABELLED The relationship between genes and proteins is a dynamic relationship that changes across time and differs in different cells. The study of these differences can reveal various insights into biological processes and disease progression, especially with the aid of proper tools for network visualization. Toward this purpose, we have developed TVNViewer, a novel visualization tool, which is specifically designed to aid in the exploration and analysis of dynamic networks. AVAILABILITY TVNViewer is freely available with documentation and tutorials on the web at http://sailing.cs.cmu.edu/tvnviewer. CONTACT epxing@cs.cmu.edu.

Split and Merge Based Story Segmentation in News Videos

Segmenting videos into smaller, semantically related segments which ease the access of the video data is a challenging open research. In this paper, we present a scheme for semantic story segmentation based on anchor person detection. The proposed model makes use of a split and merge mechanism to find story boundaries. The approach is based on visual features and text transcripts. The performance of the system was evaluated using TRECVid 2003 CNN and ABC videos. The results show that the system is in par with state-of-the-art classifier based systems.

Robust Watermarking in Transform Domain Using Edge Detection Technique

Digital Watermarking is used to embed copyright marks into the digital contents to check copyright violation. In this paper a novel robust watermarking technique is presented. The watermark is embedded robustly either in Discrete Hartley transform (DHT) domain or in discrete cosine transform (DCT) domain depending upon the number of edges in the blocks of the original image. The watermark is embedded invisibly block by block into the blocks of the original image. For this, the threshold number of edges in the original image acts as a key. To extract the watermark, the steps performed in the embedding process are executed in reverse sequence. This technique is demonstrated to be robust against various attacks like salt & pepper, JPEG compression etc. even with severe degradation to the watermarked image.

Enhancing the usability and performance of structured association mapping algorithms using automation, parallelization, and visualization in the GenAMap software system.

BackgroundStructured association mapping is proving to be a powerful strategy to find genetic polymorphisms associated with disease. However, these algorithms are often distributed as command line implementations that require expertise and effort to customize and put into practice. Because of the difficulty required to use these cutting-edge techniques, geneticists often revert to simpler, less powerful methods.ResultsTo make structured association mapping more accessible to geneticists, we have developed an automatic processing system called Auto-SAM. Auto-SAM enables geneticists to run structured association mapping algorithms automatically, using parallelization. Auto-SAM includes algorithms to discover gene-networks and find population structure. Auto-SAM can also run popular association mapping algorithms, in addition to five structured association mapping algorithms.ConclusionsAuto-SAM is available through GenAMap, a front-end desktop visualization tool. GenAMap and Auto-SAM are implemented in JAVA; binaries for GenAMap can be downloaded from http://sailing.cs.cmu.edu/genamap.

Feature subspace selection for efficient video retrieval

The curse of dimensionality is a major issue in video indexing. Extremely high dimensional feature space seriously degrades the efficiency and the effectiveness of video retrieval. In this paper, we exploit the characteristics of document relevance and propose a statistical approach to learn an effective sub feature space from a multimedia document collection. This involves four steps: (1) density based feature term extraction, (2) factor analysis, (3) bi-clustering and (4) communality based component selection. Discrete feature terms are a set of feature clusters which smooth feature distribution in order to enhance the discrimination power; factor analysis tries to depict correlation between different feature dimensions in a loading matrix; bi-clustering groups both components and factors in the factor loading matrix and selects feature components from each bi-cluster according to the communality. We have conducted extensive comparative video retrieval experiments on the TRECVid 2006 collection. Significant performance improvements are shown over the baseline, PCA based K-mean clustering.

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.

Topic Modeling for Content Based Image Retrieval

Latent Dirichlet allocation (LDA) topic model has taken a center stage in multimedia information retrieval, for example, LDA model was used by several participants in the recent TRECVid evaluation “Search” task. One of the common approaches while using LDA is to train the model on a set of test images and obtain their topic distribution. During retrieval, the likelihood of a query image is computed given the topic distribution of the test images, and the test images with the highest likelihood are returned as the most relevant images. In this paper we propose to project the unseen query images also in the topic space, and then estimate the similarity between a query image and the test images in the semantic topic space. The positive results obtained by the proposed method indicate that the semantic matching in topic space leads to a better performance than conventional likelihood based approach; there is an improvement of 25 % absolute in the number of relevant results extracted by the proposed LDA based system over the conventional likelihood based LDA system. Another not-so-obvious benefit of the proposed approach is a significant reduction in computational cost.

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.