Most image segmentation algorithms optimize some mathematical similarity criterion derived from several low-level image features. One possible way of combining different types of features, e.g. colorand texture features on different scales and/or different orientations, is to simply stack all the individual measurements into one high-dimensional feature vector. Due to the nature of such stacked...

Understanding of the scene content of a video sequence is very important for content-based indexing and retrieval of multimedia databases. Research in this area in the past several years has focused on the use of speech recognition and image analysis techniques. As a complimentary effort to the prior work, we have focused on using the associated audio information (mainly the nonspeech portion) ...

This paper describes our participations of LIG and LIRIS to the TRECVID 2008 High Level Features detection task. We evaluated several fusion strategies and especially rank fusion. Results show that including as many low-level and intermediate features as possible is the best strategy, that SIFT features are very important, that the way in which the fusion from the various low-level and intermed...

As part of the Interspeech 2016 COMPARE challenge, the two different sub-challenges Deception and Sincerity are addressed. The former refers to the identification of deceptive speech whereas the degree of perceived sincerity of speakers has to be estimated in the latter. In this paper, we investigate the potential of automatic phone recognition-based features for these use case scenarios. The s...

Semantic feature extraction of video shots and fast video sequence matching are important and required for efficient retrieval in a large video database. In this paper, a novel mechanism of similarity retrieval is proposed. Similarity measure between video sequences considering the spatio-temporal variation through consecutive frames is presented. For bridging the semantic gap between low-level...

A new approach, based on control charts, is presented for the task of recognition of events and scenarios in video image sequences. For each image in the sequence, low level image processing and feature extraction steps result in feature descriptors for objects of interest detected in the images. Control charts analysis is then explored to classify the nature of the activity depicted by the tem...

There is a rich literature of approaches to image feature extraction in computer vision. Many sophisticated approaches exist for lowand high-level feature extraction but can be complex to implement with parameter choice guided by experimentation, but impeded by speed of computation. We have developed new ways to extract features based on notional use of physical paradigms, with parameterisation...

We present a method for automatic feature extraction and cross-modal mapping using deep learning. Our system uses stacked autoencoders to learn a layered feature representation of the data. Feature vectors from two (or more) different domains are mapped to each other, effectively creating a cross-modal mapping. Our system can either run fully unsupervised, or it can use high-level labeling to f...

This paper proposes enhancements to the deformable models. Focusing on the problem of vessel segmentation, two general methods for improving the performance of the snakes are explained. The snake framework has a critical step when using the energy minimising scheme applied to the segmentation problem in computer vision: the potential map is based on the output of a low level feature detection o...

Physical analogies are an exciting paradigm for creating techniques for image feature extraction. A transform using an analogy to light rays has been developed for the detection of circular and tubular features. It uses a 2D ray tracing algorithm to follow rays through an image, interacting at a low level, to emphasise higher level features. It has been empirically tested as a pre-processor to ...