Adria Ruiz, Joost Van de Weijer, & Xavier Binefa. (2015). From emotions to action units with hidden and semi-hidden-task learning. In 16th IEEE International Conference on Computer Vision (pp. 3703–3711).
Abstract: Limited annotated training data is a challenging problem in Action Unit recognition. In this paper, we investigate how the use of large databases labelled according to the 6 universal facial expressions can increase the generalization ability of Action Unit classifiers. For this purpose, we propose a novel learning framework: Hidden-Task Learning. HTL aims to learn a set of Hidden-Tasks (Action Units)for which samples are not available but, in contrast, training data is easier to obtain from a set of related VisibleTasks (Facial Expressions). To that end, HTL is able to exploit prior knowledge about the relation between Hidden and Visible-Tasks. In our case, we base this prior knowledge on empirical psychological studies providing statistical correlations between Action Units and universal facial expressions. Additionally, we extend HTL to Semi-Hidden Task Learning (SHTL) assuming that Action Unit training samples are also provided. Performing exhaustive experiments over four different datasets, we show that HTL and SHTL improve the generalization ability of AU classifiers by training them with additional facial expression data. Additionally, we show that SHTL achieves competitive performance compared with state-of-the-art Transductive Learning approaches which face the problem of limited training data by using unlabelled test samples during training.
|
Adriana Romero. (2015). Assisting the training of deep neural networks with applications to computer vision (Carlo Gatta, & Petia Radeva, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Deep learning has recently been enjoying an increasing popularity due to its success in solving challenging tasks. In particular, deep learning has proven to be effective in a large variety of computer vision tasks, such as image classification, object recognition and image parsing. Contrary to previous research, which required engineered feature representations, designed by experts, in order to succeed, deep learning attempts to learn representation hierarchies automatically from data. More recently, the trend has been to go deeper with representation hierarchies.
Learning (very) deep representation hierarchies is a challenging task, which
involves the optimization of highly non-convex functions. Therefore, the search
for algorithms to ease the learning of (very) deep representation hierarchies from data is extensive and ongoing.
In this thesis, we tackle the challenging problem of easing the learning of (very) deep representation hierarchies. We present a hyper-parameter free, off-the-shelf, simple and fast unsupervised algorithm to discover hidden structure from the input data by enforcing a very strong form of sparsity. We study the applicability and potential of the algorithm to learn representations of varying depth in a handful of applications and domains, highlighting the ability of the algorithm to provide discriminative feature representations that are able to achieve top performance.
Yet, while emphasizing the great value of unsupervised learning methods when
labeled data is scarce, the recent industrial success of deep learning has revolved around supervised learning. Supervised learning is currently the focus of many recent research advances, which have shown to excel at many computer vision tasks. Top performing systems often involve very large and deep models, which are not well suited for applications with time or memory limitations. More in line with the current trends, we engage in making top performing models more efficient, by designing very deep and thin models. Since training such very deep models still appears to be a challenging task, we introduce a novel algorithm that guides the training of very thin and deep models by hinting their intermediate representations.
Very deep and thin models trained by the proposed algorithm end up extracting feature representations that are comparable or even better performing
than the ones extracted by large state-of-the-art models, while compellingly
reducing the time and memory consumption of the model.
|
Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, & Yoshua Bengio. (2015). FitNets: Hints for Thin Deep Nets. In 3rd International Conference on Learning Representations ICLR2015.
Abstract: While depth tends to improve network performances, it also makes gradient-based training more difficult since deeper networks tend to be more non-linear. The recently proposed knowledge distillation approach is aimed at obtaining small and fast-to-execute models, and it has shown that a student network could imitate the soft output of a larger teacher network or ensemble of networks. In this paper, we extend this idea to allow the training of a student that is deeper and thinner than the teacher, using not only the outputs but also the intermediate representations learned by the teacher as hints to improve the training process and final performance of the student. Because the student intermediate hidden layer will generally be smaller than the teacher's intermediate hidden layer, additional parameters are introduced to map the student hidden layer to the prediction of the teacher hidden layer. This allows one to train deeper students that can generalize better or run faster, a trade-off that is controlled by the chosen student capacity. For example, on CIFAR-10, a deep student network with almost 10.4 times less parameters outperforms a larger, state-of-the-art teacher network.
Keywords: Computer Science ; Learning; Computer Science ;Neural and Evolutionary Computing
|
Adriana Romero, Petia Radeva, & Carlo Gatta. (2015). Meta-parameter free unsupervised sparse feature learning. TPAMI - IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(8), 1716–1722.
Abstract: We propose a meta-parameter free, off-the-shelf, simple and fast unsupervised feature learning algorithm, which exploits a new way of optimizing for sparsity. Experiments on CIFAR-10, STL- 10 and UCMerced show that the method achieves the state-of-theart performance, providing discriminative features that generalize well.
|
Alejandro Gonzalez Alzate. (2015). Multi-modal Pedestrian Detection (David Vazquez, Antonio Lopez, &, Ed.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Pedestrian detection continues to be an extremely challenging problem in real scenarios, in which situations like illumination changes, noisy images, unexpected objects, uncontrolled scenarios and variant appearance of objects occur constantly. All these problems force the development of more robust detectors for relevant applications like vision-based autonomous vehicles, intelligent surveillance, and pedestrian tracking for behavior analysis. Most reliable vision-based pedestrian detectors base their decision on features extracted using a single sensor capturing complementary features, e.g., appearance, and texture. These features usually are extracted from the current frame, ignoring temporal information, or including it in a post process step e.g., tracking or temporal coherence. Taking into account these issues we formulate the following question: can we generate more robust pedestrian detectors by introducing new information sources in the feature extraction step?
In order to answer this question we develop different approaches for introducing new information sources to well-known pedestrian detectors. We start by the inclusion of temporal information following the Stacked Sequential Learning (SSL) paradigm which suggests that information extracted from the neighboring samples in a sequence can improve the accuracy of a base classifier.
We then focus on the inclusion of complementary information from different sensors like 3D point clouds (LIDAR – depth), far infrared images (FIR), or disparity maps (stereo pair cameras). For this end we develop a multi-modal framework in which information from different sensors is used for increasing detection accuracy (by increasing information redundancy). Finally we propose a multi-view pedestrian detector, this multi-view approach splits the detection problem in n sub-problems.
Each sub-problem will detect objects in a given specific view reducing in that way the variability problem faced when a single detectors is used for the whole problem. We show that these approaches obtain competitive results with other state-of-the-art methods but instead of design new features, we reuse existing ones boosting their performance.
|
Alejandro Gonzalez Alzate, Gabriel Villalonga, German Ros, David Vazquez, & Antonio Lopez. (2015). 3D-Guided Multiscale Sliding Window for Pedestrian Detection. In Pattern Recognition and Image Analysis, Proceedings of 7th Iberian Conference , ibPRIA 2015 (Vol. 9117, pp. 560–568).
Abstract: The most relevant modules of a pedestrian detector are the candidate generation and the candidate classification. The former aims at presenting image windows to the latter so that they are classified as containing a pedestrian or not. Much attention has being paid to the classification module, while candidate generation has mainly relied on (multiscale) sliding window pyramid. However, candidate generation is critical for achieving real-time. In this paper we assume a context of autonomous driving based on stereo vision. Accordingly, we evaluate the effect of taking into account the 3D information (derived from the stereo) in order to prune the hundred of thousands windows per image generated by classical pyramidal sliding window. For our study we use a multimodal (RGB, disparity) and multi-descriptor (HOG, LBP, HOG+LBP) holistic ensemble based on linear SVM. Evaluation on data from the challenging KITTI benchmark suite shows the effectiveness of using 3D information to dramatically reduce the number of candidate windows, even improving the overall pedestrian detection accuracy.
Keywords: Pedestrian Detection
|
Alejandro Gonzalez Alzate, Gabriel Villalonga, Jiaolong Xu, David Vazquez, Jaume Amores, & Antonio Lopez. (2015). Multiview Random Forest of Local Experts Combining RGB and LIDAR data for Pedestrian Detection. In IEEE Intelligent Vehicles Symposium IV2015 (pp. 356–361).
Abstract: Despite recent significant advances, pedestrian detection continues to be an extremely challenging problem in real scenarios. In order to develop a detector that successfully operates under these conditions, it becomes critical to leverage upon multiple cues, multiple imaging modalities and a strong multi-view classifier that accounts for different pedestrian views and poses. In this paper we provide an extensive evaluation that gives insight into how each of these aspects (multi-cue, multimodality and strong multi-view classifier) affect performance both individually and when integrated together. In the multimodality component we explore the fusion of RGB and depth maps obtained by high-definition LIDAR, a type of modality that is only recently starting to receive attention. As our analysis reveals, although all the aforementioned aspects significantly help in improving the performance, the fusion of visible spectrum and depth information allows to boost the accuracy by a much larger margin. The resulting detector not only ranks among the top best performers in the challenging KITTI benchmark, but it is built upon very simple blocks that are easy to implement and computationally efficient. These simple blocks can be easily replaced with more sophisticated ones recently proposed, such as the use of convolutional neural networks for feature representation, to further improve the accuracy.
Keywords: Pedestrian Detection
|
Alejandro Gonzalez Alzate, Sebastian Ramos, David Vazquez, Antonio Lopez, & Jaume Amores. (2015). Spatiotemporal Stacked Sequential Learning for Pedestrian Detection. In Pattern Recognition and Image Analysis, Proceedings of 7th Iberian Conference , ibPRIA 2015 (pp. 3–12).
Abstract: Pedestrian classifiers decide which image windows contain a pedestrian. In practice, such classifiers provide a relatively high response at neighbor windows overlapping a pedestrian, while the responses around potential false positives are expected to be lower. An analogous reasoning applies for image sequences. If there is a pedestrian located within a frame, the same pedestrian is expected to appear close to the same location in neighbor frames. Therefore, such a location has chances of receiving high classification scores during several frames, while false positives are expected to be more spurious. In this paper we propose to exploit such correlations for improving the accuracy of base pedestrian classifiers. In particular, we propose to use two-stage classifiers which not only rely on the image descriptors required by the base classifiers but also on the response of such base classifiers in a given spatiotemporal neighborhood. More specifically, we train pedestrian classifiers using a stacked sequential learning (SSL) paradigm. We use a new pedestrian dataset we have acquired from a car to evaluate our proposal at different frame rates. We also test on a well known dataset: Caltech. The obtained results show that our SSL proposal boosts detection accuracy significantly with a minimal impact on the computational cost. Interestingly, SSL improves more the accuracy at the most dangerous situations, i.e. when a pedestrian is close to the camera.
Keywords: SSL; Pedestrian Detection
|
Aleksandr Setkov, Fabio Martinez Carillo, Michele Gouiffes, Christian Jacquemin, Maria Vanrell, & Ramon Baldrich. (2015). DAcImPro: A Novel Database of Acquired Image Projections and Its Application to Object Recognition. In Advances in Visual Computing. Proceedings of 11th International Symposium, ISVC 2015 Part II (Vol. 9475, pp. 463–473). LNCS. Springer International Publishing.
Abstract: Projector-camera systems are designed to improve the projection quality by comparing original images with their captured projections, which is usually complicated due to high photometric and geometric variations. Many research works address this problem using their own test data which makes it extremely difficult to compare different proposals. This paper has two main contributions. Firstly, we introduce a new database of acquired image projections (DAcImPro) that, covering photometric and geometric conditions and providing data for ground-truth computation, can serve to evaluate different algorithms in projector-camera systems. Secondly, a new object recognition scenario from acquired projections is presented, which could be of a great interest in such domains, as home video projections and public presentations. We show that the task is more challenging than the classical recognition problem and thus requires additional pre-processing, such as color compensation or projection area selection.
Keywords: Projector-camera systems; Feature descriptors; Object recognition
|
Alvaro Cepero, Albert Clapes, & Sergio Escalera. (2015). Automatic non-verbal communication skills analysis: a quantitative evaluation. AIC - AI Communications, 28(1), 87–101.
Abstract: The oral communication competence is defined on the top of the most relevant skills for one's professional and personal life. Because of the importance of communication in our activities of daily living, it is crucial to study methods to evaluate and provide the necessary feedback that can be used in order to improve these communication capabilities and, therefore, learn how to express ourselves better. In this work, we propose a system capable of evaluating quantitatively the quality of oral presentations in an automatic fashion. The system is based on a multi-modal RGB, depth, and audio data description and a fusion approach in order to recognize behavioral cues and train classifiers able to eventually predict communication quality levels. The performance of the proposed system is tested on a novel dataset containing Bachelor thesis' real defenses, presentations from an 8th semester Bachelor courses, and Master courses' presentations at Universitat de Barcelona. Using as groundtruth the marks assigned by actual instructors, our system achieves high performance categorizing and ranking presentations by their quality, and also making real-valued mark predictions.
Keywords: Social signal processing; human behavior analysis; multi-modal data description; multi-modal data fusion; non-verbal communication analysis; e-Learning
|
Andres Traumann, Gholamreza Anbarjafari, & Sergio Escalera. (2015). Accurate 3D Measurement Using Optical Depth Information. EL - Electronic Letters, 51(18), 1420–1422.
Abstract: A novel three-dimensional measurement technique is proposed. The methodology consists in mapping from the screen coordinates reported by the optical camera to the real world, and integrating distance gradients from the beginning to the end point, while also minimising the error through fitting pixel locations to a smooth curve. The results demonstrate accuracy of less than half a centimetre using Microsoft Kinect II.
|
|
Andres Traumann, Sergio Escalera, & Gholamreza Anbarjafari. (2015). A New Retexturing Method for Virtual Fitting Room Using Kinect 2 Camera. In 2015 IEEE Conference on Computer Vision and Pattern Recognition Worshops (CVPRW) (pp. 75–79).
|
Anguelos Nicolaou, Andrew Bagdanov, Marcus Liwicki, & Dimosthenis Karatzas. (2015). Sparse Radial Sampling LBP for Writer Identification. In 13th International Conference on Document Analysis and Recognition ICDAR2015 (pp. 716–720).
Abstract: In this paper we present the use of Sparse Radial Sampling Local Binary Patterns, a variant of Local Binary Patterns (LBP) for text-as-texture classification. By adapting and extending the standard LBP operator to the particularities of text we get a generic text-as-texture classification scheme and apply it to writer identification. In experiments on CVL and ICDAR 2013 datasets, the proposed feature-set demonstrates State-Of-the-Art (SOA) performance. Among the SOA, the proposed method is the only one that is based on dense extraction of a single local feature descriptor. This makes it fast and applicable at the earliest stages in a DIA pipeline without the need for segmentation, binarization, or extraction of multiple features.
|
Aniol Lidon, Xavier Giro, Marc Bolaños, Petia Radeva, Markus Seidl, & Matthias Zeppelzauer. (2015). UPC-UB-STP @ MediaEval 2015 diversity task: iterative reranking of relevant images. In 2015 MediaEval Retrieving Diverse Images Task.
Abstract: This paper presents the results of the UPC-UB-STP team in the 2015 MediaEval Retrieving Diverse Images Task. The goal of the challenge is to provide a ranked list of Flickr photos for a predefined set of queries. Our approach firstly generates a ranking of images based on a query-independent estimation of its relevance. Only top results are kept and iteratively re-ranked based on their intra-similarity to introduce diversity.
|
Antoni Gurgui, Debora Gil, & Enric Marti. (2015). Laplacian Unitary Domain for Texture Morphing. In Proceedings of the 10th International Conference on Computer Vision Theory and Applications VISIGRAPP2015 (Vol. 1, pp. 693–699). SciTePress.
Abstract: Deformation of expressive textures is the gateway to realistic computer synthesis of expressions. By their good mathematical properties and flexible formulation on irregular meshes, most texture mappings rely on solutions to the Laplacian in the cartesian space. In the context of facial expression morphing, this approximation can be seen from the opposite point of view by neglecting the metric. In this paper, we use the properties of the Laplacian in manifolds to present a novel approach to warping expressive facial images in order to generate a morphing between them.
Keywords: Facial; metamorphosis;LaplacianMorphing
|
