Abstract: In this chapter we describe a system for document retrieval and classification following the interactive-predictive framework. In particular, the system addresses two different scenarios of document analysis: document classification based on visual appearance and logo detection. These two classical problems of document analysis are formulated following the interactive-predictive model, taking the user interaction into account to make easier the process of annotating and labelling the documents. A system implementing this model in a real scenario is presented and analyzed. This system also takes advantage of active learning techniques to speed up the task of labelling the documents.

Abstract: Workshop on Human Behavior Understanding
Human-machine interaction is a hot topic nowadays in the communities of multimedia and computer vision. In this context, face recognition algorithms (used as primary cue for a person’s identity assessment) work well under controlled conditions but degrade significantly when tested in real-world environments. Recently, graph-based label propagation for multi-observation face recognition was proposed. However, the associated graphs were constructed in an ad-hoc manner (e.g., using the KNN graph) that cannot adapt optimally to the data. In this paper, we propose a novel approach for efficient and adaptive graph construction that can be used for multi-observation face recognition as well as for other recognition problems. Experimental results performed on Honda video face database, show a distinct advantage of the proposed method over the standard graph construction methods.

Abstract: State-of-the-art texture descriptors typically operate on grey scale images while ignoring color information. A common way to obtain a joint color-texture representation is to combine the two visual cues at the pixel level. However, such an approach provides sub-optimal results for texture categorisation task.
In this paper we investigate how to optimally exploit color information for texture recognition. We evaluate a variety of color descriptors, popular in image classification, for texture categorisation. In addition we analyze different fusion approaches to combine color and texture cues. Experiments are conducted on the challenging scenes and 10 class texture datasets. Our experiments clearly suggest that in all cases color names provide the best performance. Late fusion is the best strategy to combine color and texture. By selecting the best color descriptor with optimal fusion strategy provides a gain of 5% to 8% compared to texture alone on scenes and texture datasets.

Abstract: We present a novel method to auto-calibrate gaze estimators based on gaze patterns obtained from other viewers. Our method is based on the observation that the gaze patterns of humans are indicative of where a new viewer will look at [12]. When a new viewer is looking at a stimulus, we first estimate a topology of gaze points (initial gaze points). Next, these points are transformed so that they match the gaze patterns of other humans to find the correct gaze points. In a flexible uncalibrated setup with a web camera and no chin rest, the proposed method was tested on ten subjects and ten images. The method estimates the gaze points after looking at a stimulus for a few seconds with an average accuracy of 4.3 im. Although the reported performance is lower than what could be achieved with dedicated hardware or calibrated setup, the proposed method still provides a sufficient accuracy to trace the viewer attention. This is promising considering the fact that auto-calibration is done in a flexible setup , without the use of a chin rest, and based only on a few seconds of gaze initialization data. To the best of our knowledge, this is the first work to use human gaze patterns in order to auto-calibrate gaze estimators.

Abstract: Video alignment is important in different areas of computer vision such as wide baseline matching, action recognition, change detection, video copy detection and frame dropping prevention. Current video alignment methods usually deal with a relatively simple case of fixed or rigidly attached cameras or simultaneous acquisition. Therefore, in this paper we propose a joint video alignment for bringing two video sequences into a spatio-temporal alignment. Specifically, the novelty of the paper is to formulate the video alignment to fold the spatial and temporal alignment into a single alignment framework. This simultaneously satisfies a frame-correspondence and frame-alignment similarity; exploiting the knowledge among neighbor frames by a standard pairwise Markov random field (MRF). This new formulation is able to handle the alignment of sequences recorded at different times by independent moving cameras that follows a similar trajectory, and also generalizes the particular cases that of fixed geometric transformation and/or linear temporal mapping. We conduct experiments on different scenarios such as sequences recorded simultaneously or by moving cameras to validate the robustness of the proposed approach. The proposed method provides the highest video alignment accuracy compared to the state-of-the-art methods on sequences recorded from vehicles driving along the same track at different times.

Abstract: Deep understanding of myocardial structure linking morphology and function of the heart would unravel crucial knowledge for medical and surgical clinical procedures and studies. Several conceptual models of myocardial fiber organization have been proposed but the lack of an automatic and objective methodology prevented an agreement. We sought to deepen in this knowledge through advanced computer graphic representations of the myocardial fiber architecture by diffusion tensor magnetic resonance imaging (DT-MRI).
We performed automatic tractography reconstruction of unsegmented DT-MRI canine heart datasets coming from the public database of the Johns Hopkins University. Full scale tractographies have been build with 200 seeds and are composed by streamlines computed on the vectorial field of primary eigenvectors given at the diffusion tensor volumes. Also, we introduced a novel multi-scale visualization technique in order to obtain a simplified tractography. This methodology allowed to keep the main geometric features of the fiber tracts, making easier to decipher the main properties of the architectural organization of the heart.
On the analysis of the output from our tractographic representations we found exact correlation with low-level details of myocardial architecture, but also with the more abstract conceptualization of a continuous helical ventricular myocardial fiber array.
Objective analysis of myocardial architecture by an automated method, including the entire myocardium and using several 3D levels of complexity, reveals a continuous helical myocardial fiber arrangement of both right and left ventricles, supporting the anatomical model of the helical ventricular myocardial band described by Torrent-Guasp.

Abstract: In this paper we tackle the automatic detection of struts elements (metallic braces of a stent device) in Intravascular Ultrasound (IVUS) sequences. The proposed method is based on context-aware classification of IVUS images, where we use Multi-Class Multi-Scale Stacked Sequential Learning (M2SSL). Additionally, we introduce a novel technique to reduce the amount of required contextual features. The comparison with binary and multi-class learning is also performed, using a dataset of IVUS images with struts manually annotated by an expert. The best performing configuration reaches a F-measure F = 63.97% .