Marta Diez-Ferrer, Debora Gil, Elena Carreño, Susana Padrones, Samantha Aso, Vanesa Vicens, et al. (2016). Positive Airway Pressure-Enhanced CT to Improve Virtual Bronchoscopic Navigation. CHEST - Chest Journal, 150(4), 1003A.
|
C. Alejandro Parraga. (2017). Colours and Colour Vision: An Introductory Survey. PER - Perception, 46(5), 640–641.
|
Fahad Shahbaz Khan, Joost Van de Weijer, Muhammad Anwer Rao, Andrew Bagdanov, Michael Felsberg, & Jorma. (2018). Scale coding bag of deep features for human attribute and action recognition. MVAP - Machine Vision and Applications, 29(1), 55–71.
Abstract: Most approaches to human attribute and action recognition in still images are based on image representation in which multi-scale local features are pooled across scale into a single, scale-invariant encoding. Both in bag-of-words and the recently popular representations based on convolutional neural networks, local features are computed at multiple scales. However, these multi-scale convolutional features are pooled into a single scale-invariant representation. We argue that entirely scale-invariant image representations are sub-optimal and investigate approaches to scale coding within a bag of deep features framework. Our approach encodes multi-scale information explicitly during the image encoding stage. We propose two strategies to encode multi-scale information explicitly in the final image representation. We validate our two scale coding techniques on five datasets: Willow, PASCAL VOC 2010, PASCAL VOC 2012, Stanford-40 and Human Attributes (HAT-27). On all datasets, the proposed scale coding approaches outperform both the scale-invariant method and the standard deep features of the same network. Further, combining our scale coding approaches with standard deep features leads to consistent improvement over the state of the art.
Keywords: Action recognition; Attribute recognition; Bag of deep features
|
Marc Bolaños, Alvaro Peris, Francisco Casacuberta, Sergi Solera, & Petia Radeva. (2018). Egocentric video description based on temporally-linked sequences. JVCIR - Journal of Visual Communication and Image Representation, 50, 205–216.
Abstract: Egocentric vision consists in acquiring images along the day from a first person point-of-view using wearable cameras. The automatic analysis of this information allows to discover daily patterns for improving the quality of life of the user. A natural topic that arises in egocentric vision is storytelling, that is, how to understand and tell the story relying behind the pictures.
In this paper, we tackle storytelling as an egocentric sequences description problem. We propose a novel methodology that exploits information from temporally neighboring events, matching precisely the nature of egocentric sequences. Furthermore, we present a new method for multimodal data fusion consisting on a multi-input attention recurrent network. We also release the EDUB-SegDesc dataset. This is the first dataset for egocentric image sequences description, consisting of 1,339 events with 3,991 descriptions, from 55 days acquired by 11 people. Finally, we prove that our proposal outperforms classical attentional encoder-decoder methods for video description.
Keywords: egocentric vision; video description; deep learning; multi-modal learning
|
Ivet Rafegas, & Maria Vanrell. (2018). Color encoding in biologically-inspired convolutional neural networks. VR - Vision Research, 151, 7–17.
Abstract: Convolutional Neural Networks have been proposed as suitable frameworks to model biological vision. Some of these artificial networks showed representational properties that rival primate performances in object recognition. In this paper we explore how color is encoded in a trained artificial network. It is performed by estimating a color selectivity index for each neuron, which allows us to describe the neuron activity to a color input stimuli. The index allows us to classify whether they are color selective or not and if they are of a single or double color. We have determined that all five convolutional layers of the network have a large number of color selective neurons. Color opponency clearly emerges in the first layer, presenting 4 main axes (Black-White, Red-Cyan, Blue-Yellow and Magenta-Green), but this is reduced and rotated as we go deeper into the network. In layer 2 we find a denser hue sampling of color neurons and opponency is reduced almost to one new main axis, the Bluish-Orangish coinciding with the dataset bias. In layers 3, 4 and 5 color neurons are similar amongst themselves, presenting different type of neurons that detect specific colored objects (e.g., orangish faces), specific surrounds (e.g., blue sky) or specific colored or contrasted object-surround configurations (e.g. blue blob in a green surround). Overall, our work concludes that color and shape representation are successively entangled through all the layers of the studied network, revealing certain parallelisms with the reported evidences in primate brains that can provide useful insight into intermediate hierarchical spatio-chromatic representations.
Keywords: Color coding; Computer vision; Deep learning; Convolutional neural networks
|
Mohamed Ilyes Lakhal, Hakan Çevikalp, Sergio Escalera, & Ferda Ofli. (2018). Recurrent Neural Networks for Remote Sensing Image Classification. IETCV - IET Computer Vision, 12(7), 1040–1045.
Abstract: Automatically classifying an image has been a central problem in computer vision for decades. A plethora of models has been proposed, from handcrafted feature solutions to more sophisticated approaches such as deep learning. The authors address the problem of remote sensing image classification, which is an important problem to many real world applications. They introduce a novel deep recurrent architecture that incorporates high-level feature descriptors to tackle this challenging problem. Their solution is based on the general encoder–decoder framework. To the best of the authors’ knowledge, this is the first study to use a recurrent network structure on this task. The experimental results show that the proposed framework outperforms the previous works in the three datasets widely used in the literature. They have achieved a state-of-the-art accuracy rate of 97.29% on the UC Merced dataset.
|
Pau Rodriguez, Miguel Angel Bautista, Sergio Escalera, & Jordi Gonzalez. (2018). Beyond Oneshot Encoding: lower dimensional target embedding. IMAVIS - Image and Vision Computing, 75, 21–31.
Abstract: Target encoding plays a central role when learning Convolutional Neural Networks. In this realm, one-hot encoding is the most prevalent strategy due to its simplicity. However, this so widespread encoding schema assumes a flat label space, thus ignoring rich relationships existing among labels that can be exploited during training. In large-scale datasets, data does not span the full label space, but instead lies in a low-dimensional output manifold. Following this observation, we embed the targets into a low-dimensional space, drastically improving convergence speed while preserving accuracy. Our contribution is two fold: (i) We show that random projections of the label space are a valid tool to find such lower dimensional embeddings, boosting dramatically convergence rates at zero computational cost; and (ii) we propose a normalized eigenrepresentation of the class manifold that encodes the targets with minimal information loss, improving the accuracy of random projections encoding while enjoying the same convergence rates. Experiments on CIFAR-100, CUB200-2011, Imagenet, and MIT Places demonstrate that the proposed approach drastically improves convergence speed while reaching very competitive accuracy rates.
Keywords: Error correcting output codes; Output embeddings; Deep learning; Computer vision
|
Jianzhy Guo, Zhen Lei, Jun Wan, Egils Avots, Noushin Hajarolasvadi, Boris Knyazev, et al. (2018). Dominant and Complementary Emotion Recognition from Still Images of Faces. ACCESS - IEEE Access, 6, 26391–26403.
Abstract: Emotion recognition has a key role in affective computing. Recently, fine-grained emotion analysis, such as compound facial expression of emotions, has attracted high interest of researchers working on affective computing. A compound facial emotion includes dominant and complementary emotions (e.g., happily-disgusted and sadly-fearful), which is more detailed than the seven classical facial emotions (e.g., happy, disgust, and so on). Current studies on compound emotions are limited to use data sets with limited number of categories and unbalanced data distributions, with labels obtained automatically by machine learning-based algorithms which could lead to inaccuracies. To address these problems, we released the iCV-MEFED data set, which includes 50 classes of compound emotions and labels assessed by psychologists. The task is challenging due to high similarities of compound facial emotions from different categories. In addition, we have organized a challenge based on the proposed iCV-MEFED data set, held at FG workshop 2017. In this paper, we analyze the top three winner methods and perform further detailed experiments on the proposed data set. Experiments indicate that pairs of compound emotion (e.g., surprisingly-happy vs happily-surprised) are more difficult to be recognized if compared with the seven basic emotions. However, we hope the proposed data set can help to pave the way for further research on compound facial emotion recognition.
|
Pichao Wang, Wanqing Li, Philip Ogunbona, Jun Wan, & Sergio Escalera. (2018). RGB-D-based Human Motion Recognition with Deep Learning: A Survey. CVIU - Computer Vision and Image Understanding, 171, 118–139.
Abstract: Human motion recognition is one of the most important branches of human-centered research activities. In recent years, motion recognition based on RGB-D data has attracted much attention. Along with the development in artificial intelligence, deep learning techniques have gained remarkable success in computer vision. In particular, convolutional neural networks (CNN) have achieved great success for image-based tasks, and recurrent neural networks (RNN) are renowned for sequence-based problems. Specifically, deep learning methods based on the CNN and RNN architectures have been adopted for motion recognition using RGB-D data. In this paper, a detailed overview of recent advances in RGB-D-based motion recognition is presented. The reviewed methods are broadly categorized into four groups, depending on the modality adopted for recognition: RGB-based, depth-based, skeleton-based and RGB+D-based. As a survey focused on the application of deep learning to RGB-D-based motion recognition, we explicitly discuss the advantages and limitations of existing techniques. Particularly, we highlighted the methods of encoding spatial-temporal-structural information inherent in video sequence, and discuss potential directions for future research.
Keywords: Human motion recognition; RGB-D data; Deep learning; Survey
|
Jelena Gorbova, Egils Avots, Iiris Lusi, Mark Fishel, Sergio Escalera, & Gholamreza Anbarjafari. (2018). Integrating Vision and Language for First Impression Personality Analysis. MULTIMEDIA - IEEE Multimedia, 25(2), 24–33.
Abstract: The authors present a novel methodology for analyzing integrated audiovisual signals and language to assess a persons personality. An evaluation of their proposed multimodal method using a job candidate screening system that predicted five personality traits from a short video demonstrates the methods effectiveness.
|
Albert Clapes, Alex Pardo, Oriol Pujol, & Sergio Escalera. (2018). Action detection fusing multiple Kinects and a WIMU: an application to in-home assistive technology for the elderly. MVAP - Machine Vision and Applications, 29(5), 765–788.
Abstract: We present a vision-inertial system which combines two RGB-Depth devices together with a wearable inertial movement unit in order to detect activities of the daily living. From multi-view videos, we extract dense trajectories enriched with a histogram of normals description computed from the depth cue and bag them into multi-view codebooks. During the later classification step a multi-class support vector machine with a RBF- 2 kernel combines the descriptions at kernel level. In order to perform action detection from the videos, a sliding window approach is utilized. On the other hand, we extract accelerations, rotation angles, and jerk features from the inertial data collected by the wearable placed on the user’s dominant wrist. During gesture spotting, a dynamic time warping is applied and the aligning costs to a set of pre-selected gesture sub-classes are thresholded to determine possible detections. The outputs of the two modules are combined in a late-fusion fashion. The system is validated in a real-case scenario with elderly from an elder home. Learning-based fusion results improve the ones from the single modalities, demonstrating the success of such multimodal approach.
Keywords: Multimodal activity detection; Computer vision; Inertial sensors; Dense trajectories; Dynamic time warping; Assistive technology
|
Jun Wan, Sergio Escalera, Francisco Perales, & Josef Kittler. (2018). Articulated Motion and Deformable Objects. PR - Pattern Recognition, 79, 55–64.
Abstract: This guest editorial introduces the twenty two papers accepted for this Special Issue on Articulated Motion and Deformable Objects (AMDO). They are grouped into four main categories within the field of AMDO: human motion analysis (action/gesture), human pose estimation, deformable shape segmentation, and face analysis. For each of the four topics, a survey of the recent developments in the field is presented. The accepted papers are briefly introduced in the context of this survey. They contribute novel methods, algorithms with improved performance as measured on benchmarking datasets, as well as two new datasets for hand action detection and human posture analysis. The special issue should be of high relevance to the reader interested in AMDO recognition and promote future research directions in the field.
|
Joan Serrat, Felipe Lumbreras, & Idoia Ruiz. (2018). Learning to measure for preshipment garment sizing. MEASURE - Measurement, 130, 327–339.
Abstract: Clothing is still manually manufactured for the most part nowadays, resulting in discrepancies between nominal and real dimensions, and potentially ill-fitting garments. Hence, it is common in the apparel industry to manually perform measures at preshipment time. We present an automatic method to obtain such measures from a single image of a garment that speeds up this task. It is generic and extensible in the sense that it does not depend explicitly on the garment shape or type. Instead, it learns through a probabilistic graphical model to identify the different contour parts. Subsequently, a set of Lasso regressors, one per desired measure, can predict the actual values of the measures. We present results on a dataset of 130 images of jackets and 98 of pants, of varying sizes and styles, obtaining 1.17 and 1.22 cm of mean absolute error, respectively.
Keywords: Apparel; Computer vision; Structured prediction; Regression
|
Debora Gil, Ruth Aris, Agnes Borras, Esmitt Ramirez, Rafael Sebastian, & Mariano Vazquez. (2019). Influence of fiber connectivity in simulations of cardiac biomechanics. IJCAR - International Journal of Computer Assisted Radiology and Surgery, 14(1), 63–72.
Abstract: PURPOSE:
Personalized computational simulations of the heart could open up new improved approaches to diagnosis and surgery assistance systems. While it is fully recognized that myocardial fiber orientation is central for the construction of realistic computational models of cardiac electromechanics, the role of its overall architecture and connectivity remains unclear. Morphological studies show that the distribution of cardiac muscular fibers at the basal ring connects epicardium and endocardium. However, computational models simplify their distribution and disregard the basal loop. This work explores the influence in computational simulations of fiber distribution at different short-axis cuts.
METHODS:
We have used a highly parallelized computational solver to test different fiber models of ventricular muscular connectivity. We have considered two rule-based mathematical models and an own-designed method preserving basal connectivity as observed in experimental data. Simulated cardiac functional scores (rotation, torsion and longitudinal shortening) were compared to experimental healthy ranges using generalized models (rotation) and Mahalanobis distances (shortening, torsion).
RESULTS:
The probability of rotation was significantly lower for ruled-based models [95% CI (0.13, 0.20)] in comparison with experimental data [95% CI (0.23, 0.31)]. The Mahalanobis distance for experimental data was in the edge of the region enclosing 99% of the healthy population.
CONCLUSIONS:
Cardiac electromechanical simulations of the heart with fibers extracted from experimental data produce functional scores closer to healthy ranges than rule-based models disregarding architecture connectivity.
Keywords: Cardiac electromechanical simulations; Diffusion tensor imaging; Fiber connectivity
|
Marta Diez-Ferrer, Arturo Morales, Rosa Lopez Lisbona, Noelia Cubero, Cristian Tebe, Susana Padrones, et al. (2019). Ultrathin Bronchoscopy with and without Virtual Bronchoscopic Navigation: Influence of Segmentation on Diagnostic Yield. RES - Respiration, 97(3), 252–258.
Abstract: Background: Bronchoscopy is a safe technique for diagnosing peripheral pulmonary lesions (PPLs), and virtual bronchoscopic navigation (VBN) helps guide the bronchoscope to PPLs. Objectives: We aimed to compare the diagnostic yield of VBN-guided and unguided ultrathin bronchoscopy (UTB) and explore clinical and technical factors associated with better results. We developed a diagnostic algorithm for deciding whether to use VBN to reach PPLs or choose an alternative diagnostic approach. Methods: We compared diagnostic yield between VBN-UTB (prospective cases) and unguided UTB (historical controls) and analyzed the VBN-UTB subgroup to identify clinical and technical variables that could predict the success of VBN-UTB. Results: Fifty-five cases and 110 controls were included. The overall diagnostic yield did not differ between the VBN-guided and unguided arms (47 and 40%, respectively; p = 0.354). Although the yield was slightly higher for PPLs ≤20 mm in the VBN-UTB arm, the difference was not significant (p = 0.069). No other clinical characteristics were associated with a higher yield in a subgroup analysis, but an 85% diagnostic yield was observed when segmentation was optimal and the PPL was endobronchial (vs. 30% when segmentation was suboptimal and 20% when segmentation was optimal but the PPL was extrabronchial). Conclusions: VBN-guided UTB is not superior to unguided UTB. A greater impact of VBN-guided over unguided UTB is highly dependent on both segmentation quality and an endobronchial location of the PPL. Segmentation quality should be considered before starting a procedure, when an alternative technique that may improve yield can be chosen, saving time and resources.
Keywords: Lung cancer; Peripheral lung lesion; Diagnosis; Bronchoscopy; Ultrathin bronchoscopy; Virtual bronchoscopic navigation
|