Sergio Escalera, Junior Fabian, Pablo Pardo, Xavier Baro, Jordi Gonzalez, Hugo Jair Escalante, et al. (2015). ChaLearn Looking at People 2015: Apparent Age and Cultural Event Recognition Datasets and Results. In 16th IEEE International Conference on Computer Vision Workshops (pp. 243–251).
Abstract: Following previous series on Looking at People (LAP) competitions [14, 13, 11, 12, 2], in 2015 ChaLearn ran two new competitions within the field of Looking at People: (1) age estimation, and (2) cultural event recognition, both in
still images. We developed a crowd-sourcing application to collect and label data about the apparent age of people (as opposed to the real age). In terms of cultural event recognition, one hundred categories had to be recognized. These
tasks involved scene understanding and human body analysis. This paper summarizes both challenges and data, as well as the results achieved by the participants of the competition.
|
Josep M. Gonfaus, Marco Pedersoli, Jordi Gonzalez, Andrea Vedaldi, & Xavier Roca. (2015). Factorized appearances for object detection. CVIU - Computer Vision and Image Understanding, 138, 92–101.
Abstract: Deformable object models capture variations in an object’s appearance that can be represented as image deformations. Other effects such as out-of-plane rotations, three-dimensional articulations, and self-occlusions are often captured by considering mixture of deformable models, one per object aspect. A more scalable approach is representing instead the variations at the level of the object parts, applying the concept of a mixture locally. Combining a few part variations can in fact cheaply generate a large number of global appearances.
A limited version of this idea was proposed by Yang and Ramanan [1], for human pose dectection. In this paper we apply it to the task of generic object category detection and extend it in several ways. First, we propose a model for the relationship between part appearances more general than the tree of Yang and Ramanan [1], which is more suitable for generic categories. Second, we treat part locations as well as their appearance as latent variables so that training does not need part annotations but only the object bounding boxes. Third, we modify the weakly-supervised learning of Felzenszwalb et al. and Girshick et al. [2], [3] to handle a significantly more complex latent structure.
Our model is evaluated on standard object detection benchmarks and is found to improve over existing approaches, yielding state-of-the-art results for several object categories.
Keywords: Object recognition; Deformable part models; Learning and sharing parts; Discovering discriminative parts
|
Julie Digne, Mariella Dimiccoli, Neus Sabater, & Philippe Salembier. (2015). Neighborhood Filters and the Recovery of 3D Information. In Handbook of Mathematical Methods in Imaging (pp. 1645–1673). Springer New York.
Abstract: Following their success in image processing (see Chapter Local Smoothing Neighborhood Filters), neighborhood filters have been extended to 3D surface processing. This adaptation is not straightforward. It has led to several variants for surfaces depending on whether the surface is defined as a mesh, or as a raw data point set. The image gray level in the bilateral similarity measure is replaced by a geometric information such as the normal or the curvature. The first section of this chapter reviews the variants of 3D mesh bilateral filters and compares them to the simplest possible isotropic filter, the mean curvature motion.In a second part, this chapter reviews applications of the bilateral filter to a data composed of a sparse depth map (or of depth cues) and of the image on which they have been computed. Such sparse depth cues can be obtained by stereovision or by psychophysical techniques. The underlying assumption to these applications is that pixels with similar intensity around a region are likely to have similar depths. Therefore, when diffusing depth information with a bilateral filter based on locality and color similarity, the discontinuities in depth are assured to be consistent with the color discontinuities, which is generally a desirable property. In the reviewed applications, this ends up with the reconstruction of a dense perceptual depth map from the joint data of an image and of depth cues.
|
Jean-Pascal Jacob, Mariella Dimiccoli, & Lionel Moisan. (2016). Active skeleton for bacteria modeling. CMBBE - Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization, 5(4), 274–286.
Abstract: The investigation of spatio-temporal dynamics of bacterial cells and their molecular components requires automated image analysis tools to track cell shape properties and molecular component locations inside the cells. In the study of bacteria aging, the molecular components of interest are protein aggregates accumulated near bacteria boundaries. This particular location makes very ambiguous the correspondence between aggregates and cells, since computing accurately bacteria boundaries in phase-contrast time-lapse imaging is a challenging task. This paper proposes an active skeleton formulation for bacteria modeling which provides several advantages: an easy computation of shape properties (perimeter, length, thickness, orientation), an improved boundary accuracy in noisy images, and a natural bacteria-centered coordinate system that permits the intrinsic location of molecular components inside the cell. Starting from an initial skeleton estimate, the medial axis of the bacterium is obtained by minimizing an energy function which incorporates bacteria shape constraints. Experimental results on biological images and comparative evaluation of the performances validate the proposed approach for modeling cigar-shaped bacteria like Escherichia coli. The Image-J plugin of the proposed method can be found online at this http URL
Keywords: Bacteria modelling; medial axis; active contours; active skeleton; shape contraints
|
Marc Bolaños, Mariella Dimiccoli, & Petia Radeva. (2017). Towards Storytelling from Visual Lifelogging: An Overview. THMS - IEEE Transactions on Human-Machine Systems, 47(1), 77–90.
Abstract: Visual lifelogging consists of acquiring images that capture the daily experiences of the user by wearing a camera over a long period of time. The pictures taken offer considerable potential for knowledge mining concerning how people live their lives, hence, they open up new opportunities for many potential applications in fields including healthcare, security, leisure and
the quantified self. However, automatically building a story from a huge collection of unstructured egocentric data presents major challenges. This paper provides a thorough review of advances made so far in egocentric data analysis, and in view of the current state of the art, indicates new lines of research to move us towards storytelling from visual lifelogging.
|
Maedeh Aghaei, Mariella Dimiccoli, & Petia Radeva. (2015). Multi-Face Tracking by Extended Bag-of-Tracklets in Egocentric Videos.
Abstract: Egocentric images offer a hands-free way to record daily experiences and special events, where social interactions are of special interest. A natural question that arises is how to extract and track the appearance of multiple persons in a social event captured by a wearable camera. In this paper, we propose a novel method to find correspondences of multiple-faces in low temporal resolution egocentric sequences acquired through a wearable camera. This kind of sequences imposes additional challenges to the multitracking problem with respect to conventional videos. Due to the free motion of the camera and to its low temporal resolution (2 fpm), abrupt changes in the field of view, in illumination conditions and in the target location are very frequent. To overcome such a difficulty, we propose to generate, for each detected face, a set of correspondences along the whole sequence that we call tracklet and to take advantage of their redundancy to deal with both false positive face detections and unreliable tracklets. Similar tracklets are grouped into the so called extended bag-of-tracklets (eBoT), which are aimed to correspond to specific persons. Finally, a prototype tracklet is extracted for each eBoT. We validated our method over a dataset of 18.000 images from 38 egocentric sequences with 52 trackable persons and compared to the state-of-the-art methods, demonstrating its effectiveness and robustness.
|
Mariella Dimiccoli, Marc Bolaños, Estefania Talavera, Maedeh Aghaei, Stavri G. Nikolov, & Petia Radeva. (2017). SR-Clustering: Semantic Regularized Clustering for Egocentric Photo Streams Segmentation. CVIU - Computer Vision and Image Understanding, 155, 55–69.
Abstract: While wearable cameras are becoming increasingly popular, locating relevant information in large unstructured collections of egocentric images is still a tedious and time consuming processes. This paper addresses the problem of organizing egocentric photo streams acquired by a wearable camera into semantically meaningful segments. First, contextual and semantic information is extracted for each image by employing a Convolutional Neural Networks approach. Later, by integrating language processing, a vocabulary of concepts is defined in a semantic space. Finally, by exploiting the temporal coherence in photo streams, images which share contextual and semantic attributes are grouped together. The resulting temporal segmentation is particularly suited for further analysis, ranging from activity and event recognition to semantic indexing and summarization. Experiments over egocentric sets of nearly 17,000 images, show that the proposed approach outperforms state-of-the-art methods.
|
Suman Ghosh, & Ernest Valveny. (2015). Query by String word spotting based on character bi-gram indexing. In 13th International Conference on Document Analysis and Recognition ICDAR2015 (pp. 881–885).
Abstract: In this paper we propose a segmentation-free query by string word spotting method. Both the documents and query strings are encoded using a recently proposed word representa- tion that projects images and strings into a common atribute space based on a pyramidal histogram of characters(PHOC). These attribute models are learned using linear SVMs over the Fisher Vector representation of the images along with the PHOC labels of the corresponding strings. In order to search through the whole page, document regions are indexed per character bi- gram using a similar attribute representation. On top of that, we propose an integral image representation of the document using a simplified version of the attribute model for efficient computation. Finally we introduce a re-ranking step in order to boost retrieval performance. We show state-of-the-art results for segmentation-free query by string word spotting in single-writer and multi-writer standard datasets
|
Suman Ghosh, & Ernest Valveny. (2015). A Sliding Window Framework for Word Spotting Based on Word Attributes. In Pattern Recognition and Image Analysis, Proceedings of 7th Iberian Conference , ibPRIA 2015 (Vol. 9117, pp. 652–661). LNCS. Springer International Publishing.
Abstract: In this paper we propose a segmentation-free approach to word spotting. Word images are first encoded into feature vectors using Fisher Vector. Then, these feature vectors are used together with pyramidal histogram of characters labels (PHOC) to learn SVM-based attribute models. Documents are represented by these PHOC based word attributes. To efficiently compute the word attributes over a sliding window, we propose to use an integral image representation of the document using a simplified version of the attribute model. Finally we re-rank the top word candidates using the more discriminative full version of the word attributes. We show state-of-the-art results for segmentation-free query-by-example word spotting in single-writer and multi-writer standard datasets.
Keywords: Word spotting; Sliding window; Word attributes
|
Ciprian Corneanu, Marc Oliu, Jeffrey F. Cohn, & Sergio Escalera. (2016). Survey on RGB, 3D, Thermal, and Multimodal Approaches for Facial Expression Recognition: History. TPAMI - IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(8), 1548–1568.
Abstract: Facial expressions are an important way through which humans interact socially. Building a system capable of automatically recognizing facial expressions from images and video has been an intense field of study in recent years. Interpreting such expressions remains challenging and much research is needed about the way they relate to human affect. This paper presents a general overview of automatic RGB, 3D, thermal and multimodal facial expression analysis. We define a new taxonomy for the field, encompassing all steps from face detection to facial expression recognition, and describe and classify the state of the art methods accordingly. We also present the important datasets and the bench-marking of most influential methods. We conclude with a general discussion about trends, important questions and future lines of research.
Keywords: Facial expression; affect; emotion recognition; RGB; 3D; thermal; multimodal
|
Antonio Hernandez, Sergio Escalera, & Stan Sclaroff. (2016). Poselet-basedContextual Rescoring for Human Pose Estimation via Pictorial Structures. IJCV - International Journal of Computer Vision, 118(1), 49–64.
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.
Keywords: Contextual rescoring; Poselets; Human pose estimation
|
Fadi Dornaika, Bogdan Raducanu, & Alireza Bosaghzadeh. (2015). Facial expression recognition based on multi observations with application to social robotics. In Bruce Flores (Ed.), Emotional and Facial Expressions: Recognition, Developmental Differences and Social Importance (pp. 153–166). Nova Science publishers.
Abstract: Human-robot interaction is a hot topic nowadays in the social robotics
community. One crucial aspect is represented by the affective communication
which comes encoded through the facial expressions. In this chapter, we propose a novel approach for facial expression recognition, which exploits an efficient and adaptive graph-based label propagation (semi-supervised mode) in a multi-observation framework. The facial features are extracted using an appearance-based 3D face tracker, viewand texture independent. Our method has been extensively tested on the CMU dataset, and has been conveniently compared with other methods for graph construction. With the proposed approach, we developed an application for an AIBO robot, in which it mirrors the recognized facial
expression.
|
Juan Ramon Terven Salinas, Bogdan Raducanu, Maria Elena Meza-de-Luna, & Joaquin Salas. (2016). Head-gestures mirroring detection in dyadic social linteractions with computer vision-based wearable devices. NEUCOM - Neurocomputing, 175(B), 866–876.
Abstract: During face-to-face human interaction, nonverbal communication plays a fundamental role. A relevant aspect that takes part during social interactions is represented by mirroring, in which a person tends to mimic the non-verbal behavior (head and body gestures, vocal prosody, etc.) of the counterpart. In this paper, we introduce a computer vision-based system to detect mirroring in dyadic social interactions with the use of a wearable platform. In our context, mirroring is inferred as simultaneous head noddings displayed by the interlocutors. Our approach consists of the following steps: (1) facial features extraction; (2) facial features stabilization; (3) head nodding recognition; and (4) mirroring detection. Our system achieves a mirroring detection accuracy of 72% on a custom mirroring dataset.
Keywords: Head gestures recognition; Mirroring detection; Dyadic social interaction analysis; Wearable devices
|
Juan Ramon Terven Salinas, Bogdan Raducanu, Maria Elena Meza-de-Luna, & Joaquin Salas. (2015). Evaluating Real-Time Mirroring of Head Gestures using Smart Glasses. In 16th IEEE International Conference on Computer Vision Workshops (pp. 452–460).
Abstract: Mirroring occurs when one person tends to mimic the non-verbal communication of their counterparts. Even though mirroring is a complex phenomenon, in this study, we focus on the detection of head-nodding as a simple non-verbal communication cue due to its significance as a gesture displayed during social interactions. This paper introduces a computer vision-based method to detect mirroring through the analysis of head gestures using wearable cameras (smart glasses). In addition, we study how such a method can be used to explore perceived competence. The proposed method has been evaluated and the experiments demonstrate how static and wearable cameras seem to be equally effective to gather the information required for the analysis.
|
Adriana Romero, Carlo Gatta, & Gustavo Camps-Valls. (2016). Unsupervised Deep Feature Extraction for Remote Sensing Image Classification. TGRS - IEEE Transaction on Geoscience and Remote Sensing, 54(3), 1349–1362.
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.
|
