|
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.
|
|
|
Ivet Rafegas. (2017). Color in Visual Recognition: from flat to deep representations and some biological parallelisms (Maria Vanrell, Ed.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Visual recognition is one of the main problems in computer vision that attempts to solve image understanding by deciding what objects are in images. This problem can be computationally solved by using relevant sets of visual features, such as edges, corners, color or more complex object parts. This thesis contributes to how color features have to be represented for recognition tasks.
Image features can be extracted following two different approaches. A first approach is defining handcrafted descriptors of images which is then followed by a learning scheme to classify the content (named flat schemes in Kruger et al. (2013). In this approach, perceptual considerations are habitually used to define efficient color features. Here we propose a new flat color descriptor based on the extension of color channels to boost the representation of spatio-chromatic contrast that surpasses state-of-the-art approaches. However, flat schemes present a lack of generality far away from the capabilities of biological systems. A second approach proposes evolving these flat schemes into a hierarchical process, like in the visual cortex. This includes an automatic process to learn optimal features. These deep schemes, and more specifically Convolutional Neural Networks (CNNs), have shown an impressive performance to solve various vision problems. However, there is a lack of understanding about the internal representation obtained, as a result of automatic learning. In this thesis we propose a new methodology to explore the internal representation of trained CNNs by defining the Neuron Feature as a visualization of the intrinsic features encoded in each individual neuron. Additionally, and inspired by physiological techniques, we propose to compute different neuron selectivity indexes (e.g., color, class, orientation or symmetry, amongst others) to label and classify the full CNN neuron population to understand learned representations.
Finally, using the proposed methodology, we show an in-depth study on how color is represented on a specific CNN, trained for object recognition, that competes with primate representational abilities (Cadieu et al (2014)). We found several parallelisms with biological visual systems: (a) a significant number of color selectivity neurons throughout all the layers; (b) an opponent and low frequency representation of color oriented edges and a higher sampling of frequency selectivity in brightness than in color in 1st layer like in V1; (c) a higher sampling of color hue in the second layer aligned to observed hue maps in V2; (d) a strong color and shape entanglement in all layers from basic features in shallower layers (V1 and V2) to object and background shapes in deeper layers (V4 and IT); and (e) a strong correlation between neuron color selectivities and color dataset bias.
|
|
|
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
|
|
|
Stefan Lonn, Petia Radeva, & Mariella Dimiccoli. (2018). A picture is worth a thousand words but how to organize thousands of pictures?.
Abstract: We live in a society where the large majority of the population has a camera-equipped smartphone. In addition, hard drives and cloud storage are getting cheaper and cheaper, leading to a tremendous growth in stored personal photos. Unlike photo collections captured by a digital camera, which typically are pre-processed by the user who organizes them into event-related folders, smartphone pictures are automatically stored in the cloud. As a consequence, photo collections captured by a smartphone are highly unstructured and because smartphones are ubiquitous, they present a larger variability compared to pictures captured by a digital camera. To solve the need of organizing large smartphone photo collections automatically, we propose here a new methodology for hierarchical photo organization into topics and topic-related categories. Our approach successfully estimates latent topics in the pictures by applying probabilistic Latent Semantic Analysis, and automatically assigns a name to each topic by relying on a lexical database. Topic-related categories are then estimated by using a set of topic-specific Convolutional Neuronal Networks. To validate our approach, we ensemble and make public a large dataset of more than 8,000 smartphone pictures from 10 persons. Experimental results demonstrate better user satisfaction with respect to state of the art solutions in terms of organization.
|
|
|
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.
|
|
|
Cesar de Souza. (2018). Action Recognition in Videos: Data-efficient approaches for supervised learning of human action classification models for video (Antonio Lopez, & Naila Murray, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: In this dissertation, we explore different ways to perform human action recognition in video clips. We focus on data efficiency, proposing new approaches that alleviate the need for laborious and time-consuming manual data annotation. In the first part of this dissertation, we start by analyzing previous state-of-the-art models, comparing their differences and similarities in order to pinpoint where their real strengths come from. Leveraging this information, we then proceed to boost the classification accuracy of shallow models to levels that rival deep neural networks. We introduce hybrid video classification architectures based on carefully designed unsupervised representations of handcrafted spatiotemporal features classified by supervised deep networks. We show in our experiments that our hybrid model combine the best of both worlds: it is data efficient (trained on 150 to 10,000 short clips) and yet improved significantly on the state of the art, including deep models trained on millions of manually labeled images and videos. In the second part of this research, we investigate the generation of synthetic training data for action recognition, as it has recently shown promising results for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation and other computer graphics techniques of modern game engines. We generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for “Procedural Human Action Videos”. It contains a total of 39,982 videos, with more than 1,000 examples for each action of 35 categories. Our approach is not limited to existing motion capture sequences, and we procedurally define 14 synthetic actions. We then introduce deep multi-task representation learning architectures to mix synthetic and real videos, even if the action categories differ. Our experiments on the UCF-101 and HMDB-51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance, outperforming fine-tuning state-of-the-art unsupervised generative models of videos.
|
|