Abstract: In this paper we propose a contextual rescoring method for predicting the position of body parts in a human pose estimation framework. A set of poselets is incorporated in the model, and their detections are used to extract spatial and score-related features relative to other body part hypotheses. A method is proposed for the automatic discovery of a compact subset of poselets that covers the different poses in a set of validation images while maximizing precision. A rescoring mechanism is defined as a set-based boosting classifier that computes a new score for each body joint detection, given its relationship to detections of other body joints and mid-level parts in the image. This new score is incorporated in the pictorial structure model as an additional unary potential, following the recent work of Pishchulin et al. Experiments on two benchmarks show comparable results to Pishchulin et al. while reducing the size of the mid-level representation by an order of magnitude, reducing the execution time by 68 % accordingly.

Abstract: This paper introduces the use of single-layer and deep convolutional networks for remote sensing data analysis. Direct application to multi- and hyperspectral imagery of supervised (shallow or deep) convolutional networks is very challenging given the high input data dimensionality and the relatively small amount of available labeled data. Therefore, we propose the use of greedy layerwise unsupervised pretraining coupled with a highly efficient algorithm for unsupervised learning of sparse features. The algorithm is rooted on sparse representations and enforces both population and lifetime sparsity of the extracted features, simultaneously. We successfully illustrate the expressive power of the extracted representations in several scenarios: classification of aerial scenes, as well as land-use classification in very high resolution or land-cover classification from multi- and hyperspectral images. The proposed algorithm clearly outperforms standard principal component analysis (PCA) and its kernel counterpart (kPCA), as well as current state-of-the-art algorithms of aerial classification, while being extremely computationally efficient at learning representations of data. Results show that single-layer convolutional networks can extract powerful discriminative features only when the receptive field accounts for neighboring pixels and are preferred when the classification requires high resolution and detailed results. However, deep architectures significantly outperform single-layer variants, capturing increasing levels of abstraction and complexity throughout the feature hierarchy.

Abstract: Wearable cameras offer a hands-free way to record egocentric images of daily experiences, where social events are of special interest. The first step towards detection of social events is to track the appearance of multiple persons involved in them. In this paper, we propose a novel method to find correspondences of multiple faces in low temporal resolution egocentric videos acquired through a wearable camera. This kind of photo-stream imposes additional challenges to the multi-tracking problem with respect to conventional videos. Due to the free motion of the camera and to its low temporal resolution, abrupt changes in the field of view, in illumination condition and in the target location are highly frequent. To overcome such difficulties, we propose a multi-face tracking method that generates a set of tracklets through finding correspondences along the whole sequence for each detected face and takes advantage of the tracklets redundancy to deal with unreliable ones. Similar tracklets are grouped into the so called extended bag-of-tracklets (eBoT), which is aimed to correspond to a specific person. Finally, a prototype tracklet is extracted for each eBoT, where the occurred occlusions are estimated by relying on a new measure of confidence. We validated our approach over an extensive dataset of egocentric photo-streams and compared it to state of the art methods, demonstrating its effectiveness and robustness.

Abstract: This paper presents a computational model to recover the most likely interpretation
of the 3D scene structure from a planar image, where some objects may occlude others. The estimated scene interpretation is obtained by integrating some global and local cues and provides both the complete disoccluded objects that form the scene and their ordering according to depth.
Our method first computes several distal scenes which are compatible with the proximal planar image. To compute these different hypothesized scenes, we propose a perceptually inspired object disocclusion method, which works by minimizing the Euler's elastica as well as by incorporating the relatability of partially occluded contours and the convexity of the disoccluded objects. Then, to estimate the preferred scene we rely on a Bayesian model and define probabilities taking into account the global complexity of the objects in the hypothesized scenes as well as the effort of bringing these objects in their relative position in the planar image, which is also measured by an Euler's elastica-based quantity. The model is illustrated with numerical experiments on, both, synthetic and real images showing the ability of our model to reconstruct the occluded objects and the preferred perceptual order among them. We also present results on images of the Berkeley dataset with provided figure-ground ground-truth labeling.

Abstract: By definition, local image features provide a compact representation of the image in which most of the image information is preserved. This capability offered by local features has been overlooked, despite being relevant in many application scenarios. In this paper, we analyze and discuss the performance of feature-driven Maximally Stable Extremal Regions (MSER) in terms of the coverage of informative image parts (completeness). This type of features results from an MSER extraction on saliency maps in which features related to objects boundaries or even symmetry axes are highlighted. These maps are intended to be suitable domains for MSER detection, allowing this detector to provide a better coverage of informative image parts. Our experimental results, which were based on a large-scale evaluation, show that feature-driven MSER have relatively high completeness values and provide more complete sets than a traditional MSER detection even when sets of similar cardinality are considered.

Abstract: This paper introduces a new automatic technique for garment retexturing using a single static image along with the depth and infrared information obtained using the Microsoft Kinect II as the RGB-D acquisition device. First, the garment is segmented out from the image using either the Breadth-First Search algorithm or the semi-automatic procedure provided by the GrabCut method. Then texture domain coordinates are computed for each pixel belonging to the garment using normalised 3D information. Afterwards, shading is applied to the new colours from the texture image. As the main contribution of the proposed method, the latter information is obtained based on extracting a linear map transforming the colour present on the infrared image to that of the RGB colour channels. One of the most important impacts of this strategy is that the resulting retexturing algorithm is colour-, pattern- and lighting-invariant. The experimental results show that it can be used to produce realistic representations, which is substantiated through implementing it under various experimentation scenarios, involving varying lighting intensities and directions. Successful results are accomplished also on video sequences, as well as on images of subjects taking different poses. Based on the Mean Opinion Score analysis conducted on many randomly chosen users, it has been shown to produce more realistic-looking results compared to the existing state-of-the-art methods suggested in the literature. From a wide perspective, the proposed method can be used for retexturing all sorts of segmented surfaces, although the focus of this study is on garment retexturing, and the investigation of the configurations is steered accordingly, since the experiments target an application in the context of virtual fitting rooms.

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.