Abstract: This paper surveys the state of the art on multimodal gesture recognition and introduces the JMLR special topic on gesture recognition 2011-2015. We began right at the start of the KinectTMrevolution when inexpensive infrared cameras providing image depth recordings became available. We published papers using this technology and other more conventional methods, including regular video cameras, to record data, thus providing a good overview of uses of machine learning and computer vision using multimodal data in this area of application. Notably, we organized a series of challenges and made available several datasets we recorded for that purpose, including tens of thousands
of videos, which are available to conduct further research. We also overview recent state of the art works on gesture recognition based on a proposed taxonomy for gesture recognition, discussing challenges and future lines of research.

Abstract: This work addresses the problem of human body segmentation from multi-modal visual cues as a first stage of automatic human behavior analysis. We propose a novel RGB–depth–thermal dataset along with a multi-modal segmentation baseline. The several modalities are registered using a calibration device and a registration algorithm. Our baseline extracts regions of interest using background subtraction, defines a partitioning of the foreground regions into cells, computes a set of image features on those cells using different state-of-the-art feature extractions, and models the distribution of the descriptors per cell using probabilistic models. A supervised learning algorithm then fuses the output likelihoods over cells in a stacked feature vector representation. The baseline, using Gaussian mixture models for the probabilistic modeling and Random Forest for the stacked learning, is superior to other state-of-the-art methods, obtaining an overlap above 75 % on the novel dataset when compared to the manually annotated ground-truth of human segmentations.

Abstract: In the context of human action recognition using skeleton data, the 3D trajectories of joint points may be considered as multi-dimensional time series. The traditional recognition technique in the literature is based on time series dis(similarity) measures (such as Dynamic Time Warping). For these general dis(similarity) measures, k-nearest neighbor algorithms are a natural choice. However, k-NN classifiers are known to be sensitive to noise and outliers. In this paper, a new class of Support Vector Machine that is applicable to trajectory classification, such as action recognition, is developed by incorporating an efficient time-series distances measure into the kernel function. More specifically, the derivative of Dynamic Time Warping (DTW) distance measure is employed as the SVM kernel. In addition, the pairwise proximity learning strategy is utilized in order to make use of non-positive semi-definite (PSD) kernels in the SVM formulation. The recognition results of the proposed technique on two action recognition datasets demonstrates the ourperformance of our methodology compared to the state-of-the-art methods. Remarkably, we obtained 89 % accuracy on the well-known MSRAction3D dataset using only 3D trajectories of body joints obtained by Kinect

Abstract: Despite the outperformance of Support Vector Machine (SVM) on many practical classification problems, the algorithm is not directly applicable to multi-dimensional trajectories having different lengths. In this paper, a new class of SVM that is applicable to trajectory classification, such as action recognition, is developed by incorporating two efficient time-series distances measures into the kernel function.
Dynamic Time Warping and Longest Common Subsequence distance measures along with their derivatives are
employed as the SVM kernel. In addition, the pairwise proximity learning strategy is utilized in order to make use of non-positive semi-definite kernels in the SVM formulation. The proposed method is employed for a challenging classification problem: action recognition by depth cameras using only skeleton data; and evaluated on three benchmark action datasets. Experimental results demonstrate the outperformance of our methodology compared to the state-ofthe-art on the considered datasets.

Abstract: In this paper is presented a novel multimodal emotion recognition system which is based on the analysis of audio and visual cues. MFCC-based features are extracted from the audio channel and facial landmark geometric relations are
computed from visual data. Both sets of features are learnt separately using state-of-the-art classifiers. In addition, we summarise each emotion video into a reduced set of key-frames, which are learnt in order to visually discriminate emotions by means of a Convolutional Neural Network. Finally, confidence
outputs of all classifiers from all modalities are used to define a new feature space to be learnt for final emotion prediction, in a late fusion/stacking fashion. The conducted experiments on eNTERFACE’05 database show significant performance improvements of our proposed system in comparison to state-of-the-art approaches.

Abstract: Reliable facial recognition systems are of crucial importance in various applications from entertainment to security. Thanks to the deep-learning concepts introduced in the field, a significant improvement in the performance of the unimodal facial recognition systems has been observed in the recent years. At the same time a multimodal facial recognition is a promising approach. This study combines the latest successes in both directions by applying deep learning convolutional neural networks (CNN) to the multimodal RGB, depth, and thermal (RGB-D-T) based facial recognition problem outperforming previously published results. Furthermore, a late fusion of the CNN-based recognition block with various hand-crafted features (local binary patterns, histograms of oriented gradients, Haar-like rectangular features, histograms of Gabor ordinal measures) is introduced, demonstrating even better recognition performance on a benchmark RGB-D-T database. The obtained results in this study show that the classical engineered features and CNN-based features can complement each other for recognition purposes.

Abstract: OBJECTIVES:
The proposal and implementation of a computational framework for the quantification of structural renal damage from 99mTc-dimercaptosuccinic acid (DMSA) scans. The aim of this work is to propose, implement, and validate a computational framework for the quantification of structural renal damage from DMSA scans and in an observer-independent manner.
MATERIALS AND METHODS:
From a set of 16 pediatric DMSA-positive scans and 16 matched controls and using both expert-guided and automatic approaches, a set of image-derived quantitative indicators was computed based on the relative size, intensity and histogram distribution of the lesion. A correlation analysis was conducted in order to investigate the association of these indicators with other clinical data of interest in this scenario, including C-reactive protein (CRP), white cell count, vesicoureteral reflux, fever, relative perfusion, and the presence of renal sequelae in a 6-month follow-up DMSA scan.
RESULTS:
A fully automatic lesion detection and segmentation system was able to successfully classify DMSA-positive from negative scans (AUC=0.92, sensitivity=81% and specificity=94%). The image-computed relative size of the lesion correlated with the presence of fever and CRP levels (p<0.05), and a measurement derived from the distribution histogram of the lesion obtained significant performance results in the detection of permanent renal damage (AUC=0.86, sensitivity=100% and specificity=75%).
CONCLUSIONS:
The proposal and implementation of a computational framework for the quantification of structural renal damage from DMSA scans showed a promising potential to complement visual diagnosis and non-imaging indicators.