Multimedia information retrieval

Creating descriptors for trajectories has many ap- plications in robotics/human motion analysis and video copy detection. Here, we propose a novel descriptor for 2D trajectories: Histogram of Ori- ented Displacements (HOD). Each displacement in the trajectory votes with its length in a his- togram of orientation angles. 3D trajectories are described by the HOD of their three projections. We use

The objective of this work is to recognize all the frontal faces of a character in the closed world of a movie or situation comedy, given a small number of query faces. This is challenging because faces in a feature-length film are relatively uncontrolled with a wide variability of scale, pose, illumination, and expressions, and also may be partially occluded. We develop a recognition method based on a cascade of processing steps that normalize for the effects of the changing imaging environment. In particular there are three areas of novelty: (i) we suppress the background surrounding the face, enabling the maximum area of the face to be retained for recognition rather than a subset; (ii) we include a pose refinement step to optimize the registration between the test image and face exemplar; and (iii) we use robust distance to a sub-space to allow for partial occlusion and expression change. The method is applied and evaluated on several feature length films. It is demonstrated that high recall rates (over 92%) can be achieved whilst maintaining good precision (over 93%).

This paper describes an experimental study on the detection of emotion from speech. As computer-based characters such as avatars and virtual chat faces become more common, the use of emotion to drive the expression of the virtual characters becomes more important. This study utilizes a corpus containing emotional speech with 721 short utterances expressing four emotions: anger, happiness, sadness, and the neutral (unemotional) state, which were captured manually from movies and teleplays. We introduce a new concept to evaluate emotions in speech. Emotions are so complex that most speech sentences cannot be precisely assigned to a particular emotion category; however, most emotional states nevertheless can be described as a mixture of multiple emotions. Based on this concept we have trained SVMs (support vector machines) to recognize utterances within these four categories and developed an agent that can recognize and express emotions.

Content-Based Image Retrieval (CBIR) locates, retrieves and displays images alike to one given as a query, using a set of features. It demands accessible data in medical archives and from medical equipment, to infer meaning after some processing. A problem similar in some sense to the target image can aid clinicians. CBIR complements text-based retrieval and improves evidence-based diagnosis, administration, teaching, and research in healthcare. It facilitates visual/automatic diagnosis and decision-making in real-time remote consultation/screening, store-and-forward tests, home care assistance and overall patient surveillance. Metrics help comparing visual data and improve diagnostic. Specially designed architectures can benefit from the application scenario. CBIR use calls for file storage standardization, querying procedures, efficient image transmission, realistic databases, global availability, access simplicity, and Internet-based structures. This chapter recommends important and complex aspects required to handle visual content in healthcare.

Binaural cue coding (BCC) was introduced as an efficient representation method for MPEG-4 SAC (Spatial Audio Coding). However, in a low bit-rate environment, the spectrum of BCC output signals degrades with respect to the perceptual level. The proposed system in this paper estimates VSLI (virtual source location information) as the side information. The VSLI is the angle representation of spatial images between channels on playback layout. The subjective assessment results show that the proposed method provides better audio quality than the BCC method for encoding multi-channel signals.

Achieving illumination invariance in the presence of large pose changes remains one of the most challenging aspects of automatic face recognition from low resolution imagery. In this paper, we propose a novel recognition methodology for their robust and efficient matching. The framework is based on outputs of simple image processing filters that compete with unprocessed greyscale input to yield a single matching score between two individuals. Specifically, we show how the discrepancy of the illumination conditions between query input and training (gallery) data set can be estimated implicitly and used to weight the contributions of the two competing representations. The weighting parameters are representation-specific (i.e. filter-specific), but not gallery-specific. Thus, the computationally demanding, learning stage of our algorithm is offline-based and needs to be performed only once, making the added online overhead minimal. Finally, we describe an extensive empirical evaluation of the proposed method in both a video and still image-based setup performed on five databases, totalling 333 individuals, over 1660 video sequences and 650 still images, containing extreme variation in illumination, pose and head motion. On this challenging data set our algorithm consistently demonstrated a dramatic performance improvement over traditional filtering approaches. We demonstrate a reduction of 50–75% in recognition error rates, the best performing method-filter combination correctly recognizing 97% of the individuals.

The problem of object recognition is of immense practical importance and potential, and the last decade has witnessed a number of breakthroughs in the state of the art. Most of the past object recognition work focuses on textured objects and local appearance descriptors extracted around salient points in an image. These methods fail in the matching of smooth, untextured objects for which salient point detection does not produce robust results. The recently proposed bag of boundaries (BoB) method is the first to directly address this problem. Since the texture of smooth objects is largely uninformative, BoB focuses on describing and matching objects based on their post-segmentation boundaries. Herein we address three major weaknesses of this work. The first of these is the uniform treatment of all boundary segments. Instead, we describe a method for detecting the locations and scales of salient boundary segments. Secondly, while the BoB method uses an image based elementary descriptor (HoGs + occupancy matrix), we propose a more compact descriptor based on the local profile of boundary normals' directions. Lastly, we conduct a far more systematic evaluation, both of the bag of boundaries method and the method proposed here. Using a large public database, we demonstrate that our method exhibits greater robustness while at the same time achieving a major computational saving -- object representation is extracted from an image in only 6%  of the time needed to extract a bag of boundaries, and the storage requirement is similarly reduced to less than 8%.