Home | [81–90] << 91 92 93 94 95 96 97 98 99 100 >> [101–110] |
![]() |
Records | |||||
---|---|---|---|---|---|
Author | Fatemeh Noroozi; Marina Marjanovic; Angelina Njegus; Sergio Escalera; Gholamreza Anbarjafari | ||||
Title ![]() |
Fusion of Classifier Predictions for Audio-Visual Emotion Recognition | Type | Conference Article | ||
Year | 2016 | Publication | 23rd International Conference on Pattern Recognition Workshops | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | In this paper is presented a novel multimodal emotion recognition system which is based on the analysis of audio and visual cues. MFCC-based features are extracted from the audio channel and facial landmark geometric relations are
computed from visual data. Both sets of features are learnt separately using state-of-the-art classifiers. In addition, we summarise each emotion video into a reduced set of key-frames, which are learnt in order to visually discriminate emotions by means of a Convolutional Neural Network. Finally, confidence outputs of all classifiers from all modalities are used to define a new feature space to be learnt for final emotion prediction, in a late fusion/stacking fashion. The conducted experiments on eNTERFACE’05 database show significant performance improvements of our proposed system in comparison to state-of-the-art approaches. |
||||
Address | Cancun; Mexico; December 2016 | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | ICPRW | ||
Notes | HuPBA;MILAB; | Approved | no | ||
Call Number | Admin @ si @ NMN2016 | Serial | 2839 | ||
Permanent link to this record | |||||
Author | M. Gonzalez-Audicana; Xavier Otazu; O. Fors; R Garcia; J. Nuñez | ||||
Title ![]() |
Fusion of different spatial and spectral resolution images: development, apllication and comparison of new methods based on wavelets. | Type | Miscellaneous | ||
Year | 2002 | Publication | Proceedings of the 1st. International Symposium Recent Advances in Quantitative Remote Sensing. | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | |||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | CIC | Approved | no | ||
Call Number | CAT @ cat @ GOF2002 | Serial | 291 | ||
Permanent link to this record | |||||
Author | Robert Benavente; Maria Vanrell | ||||
Title ![]() |
Fuzzy Colour Naming Based on Sigmoid Membership Functions. | Type | Miscellaneous | ||
Year | 2004 | Publication | CGIV 2004 Second European Conference on Colour in Graphics, Imaging and Vision, 135:139 | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | |||||
Address | Aachen (Germany) | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | CIC | Approved | no | ||
Call Number | CAT @ cat @ BeV2004 | Serial | 441 | ||
Permanent link to this record | |||||
Author | Muhammad Muzzamil Luqman; Jean-Yves Ramel; Josep Llados; Thierry Brouard | ||||
Title ![]() |
Fuzzy Multilevel Graph Embedding | Type | Journal Article | ||
Year | 2013 | Publication | Pattern Recognition | Abbreviated Journal | PR |
Volume | 46 | Issue | 2 | Pages | 551-565 |
Keywords | Pattern recognition; Graphics recognition; Graph clustering; Graph classification; Explicit graph embedding; Fuzzy logic | ||||
Abstract | Structural pattern recognition approaches offer the most expressive, convenient, powerful but computational expensive representations of underlying relational information. To benefit from mature, less expensive and efficient state-of-the-art machine learning models of statistical pattern recognition they must be mapped to a low-dimensional vector space. Our method of explicit graph embedding bridges the gap between structural and statistical pattern recognition. We extract the topological, structural and attribute information from a graph and encode numeric details by fuzzy histograms and symbolic details by crisp histograms. The histograms are concatenated to achieve a simple and straightforward embedding of graph into a low-dimensional numeric feature vector. Experimentation on standard public graph datasets shows that our method outperforms the state-of-the-art methods of graph embedding for richly attributed graphs. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Elsevier | Place of Publication | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | 0031-3203 | ISBN | Medium | ||
Area | Expedition | Conference | |||
Notes | DAG; 600.042; 600.045; 605.203 | Approved | no | ||
Call Number | Admin @ si @ LRL2013a | Serial | 2270 | ||
Permanent link to this record | |||||
Author | Lei Kang; Pau Riba; Yaxing Wang; Marçal Rusiñol; Alicia Fornes; Mauricio Villegas | ||||
Title ![]() |
GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images | Type | Conference Article | ||
Year | 2020 | Publication | 16th European Conference on Computer Vision | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | Although current image generation methods have reached impressive quality levels, they are still unable to produce plausible yet diverse images of handwritten words. On the contrary, when writing by hand, a great variability is observed across different writers, and even when analyzing words scribbled by the same individual, involuntary variations are conspicuous. In this work, we take a step closer to producing realistic and varied artificially rendered handwritten words. We propose a novel method that is able to produce credible handwritten word images by conditioning the generative process with both calligraphic style features and textual content. Our generator is guided by three complementary learning objectives: to produce realistic images, to imitate a certain handwriting style and to convey a specific textual content. Our model is unconstrained to any predefined vocabulary, being able to render whatever input word. Given a sample writer, it is also able to mimic its calligraphic features in a few-shot setup. We significantly advance over prior art and demonstrate with qualitative, quantitative and human-based evaluations the realistic aspect of our synthetically produced images. | ||||
Address | Virtual; August 2020 | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | ECCV | ||
Notes | DAG; 600.140; 600.121; 600.129 | Approved | no | ||
Call Number | Admin @ si @ KPW2020 | Serial | 3426 | ||
Permanent link to this record | |||||
Author | Swathikiran Sudhakaran; Sergio Escalera; Oswald Lanz | ||||
Title ![]() |
Gate-Shift Networks for Video Action Recognition | Type | Conference Article | ||
Year | 2020 | Publication | 33rd IEEE Conference on Computer Vision and Pattern Recognition | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | Deep 3D CNNs for video action recognition are designed to learn powerful representations in the joint spatio-temporal feature space. In practice however, because of the large number of parameters and computations involved, they may under-perform in the lack of sufficiently large datasets for training them at scale. In this paper we introduce spatial gating in spatial-temporal decomposition of 3D kernels. We implement this concept with Gate-Shift Module (GSM). GSM is lightweight and turns a 2D-CNN into a highly efficient spatio-temporal feature extractor. With GSM plugged in, a 2D-CNN learns to adaptively route features through time and combine them, at almost no additional parameters and computational overhead. We perform an extensive evaluation of the proposed module to study its effectiveness in video action recognition, achieving state-of-the-art results on Something Something-V1 and Diving48 datasets, and obtaining competitive results on EPIC-Kitchens with far less model complexity. | ||||
Address | Virtual CVPR | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | CVPR | ||
Notes | HuPBA; no proj | Approved | no | ||
Call Number | Admin @ si @ SEL2020 | Serial | 3438 | ||
Permanent link to this record | |||||
Author | Swathikiran Sudhakaran; Sergio Escalera; Oswald Lanz | ||||
Title ![]() |
Gate-Shift-Fuse for Video Action Recognition | Type | Journal Article | ||
Year | 2023 | Publication | IEEE Transactions on Pattern Analysis and Machine Intelligence | Abbreviated Journal | TPAMI |
Volume | 45 | Issue | 9 | Pages | 10913-10928 |
Keywords | Action Recognition; Video Classification; Spatial Gating; Channel Fusion | ||||
Abstract | Convolutional Neural Networks are the de facto models for image recognition. However 3D CNNs, the straight forward extension of 2D CNNs for video recognition, have not achieved the same success on standard action recognition benchmarks. One of the main reasons for this reduced performance of 3D CNNs is the increased computational complexity requiring large scale annotated datasets to train them in scale. 3D kernel factorization approaches have been proposed to reduce the complexity of 3D CNNs. Existing kernel factorization approaches follow hand-designed and hard-wired techniques. In this paper we propose Gate-Shift-Fuse (GSF), a novel spatio-temporal feature extraction module which controls interactions in spatio-temporal decomposition and learns to adaptively route features through time and combine them in a data dependent manner. GSF leverages grouped spatial gating to decompose input tensor and channel weighting to fuse the decomposed tensors. GSF can be inserted into existing 2D CNNs to convert them into an efficient and high performing spatio-temporal feature extractor, with negligible parameter and compute overhead. We perform an extensive analysis of GSF using two popular 2D CNN families and achieve state-of-the-art or competitive performance on five standard action recognition benchmarks. | ||||
Address | 1 Sept. 2023 | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | HUPBA; no menciona | Approved | no | ||
Call Number | Admin @ si @ SEL2023 | Serial | 3814 | ||
Permanent link to this record | |||||
Author | Marco Cotogni; Fei Yang; Claudio Cusano; Andrew Bagdanov; Joost Van de Weijer | ||||
Title ![]() |
Gated Class-Attention with Cascaded Feature Drift Compensation for Exemplar-free Continual Learning of Vision Transformers | Type | Miscellaneous | ||
Year | 2022 | Publication | Arxiv | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | Marco Cotogni, Fei Yang, Claudio Cusano, Andrew D. Bagdanov, Joost van de Weijer | ||||
Abstract | We propose a new method for exemplar-free class incremental training of ViTs. The main challenge of exemplar-free continual learning is maintaining plasticity of the learner without causing catastrophic forgetting of previously learned tasks. This is often achieved via exemplar replay which can help recalibrate previous task classifiers to the feature drift which occurs when learning new tasks. Exemplar replay, however, comes at the cost of retaining samples from previous tasks which for many applications may not be possible. To address the problem of continual ViT training, we first propose gated class-attention to minimize the drift in the final ViT transformer block. This mask-based gating is applied to class-attention mechanism of the last transformer block and strongly regulates the weights crucial for previous tasks. Importantly, gated class-attention does not require the task-ID during inference, which distinguishes it from other parameter isolation methods. Secondly, we propose a new method of feature drift compensation that accommodates feature drift in the backbone when learning new tasks. The combination of gated class-attention and cascaded feature drift compensation allows for plasticity towards new tasks while limiting forgetting of previous ones. Extensive experiments performed on CIFAR-100, Tiny-ImageNet and ImageNet100 demonstrate that our exemplar-free method obtains competitive results when compared to rehearsal based ViT methods. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | LAMP; no proj | Approved | no | ||
Call Number | Admin @ si @ CYC2022 | Serial | 3827 | ||
Permanent link to this record | |||||
Author | Xavier Roca; Jordi Vitria; Maria Vanrell; Juan J. Villanueva | ||||
Title ![]() |
Gaze control in a binocular robot systems | Type | Miscellaneous | ||
Year | 1999 | Publication | Abbreviated Journal | ||
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | |||||
Address | Barcelona | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | OR;ISE;CIC;MV | Approved | no | ||
Call Number | BCNPCL @ bcnpcl @ RVV1999b | Serial | 41 | ||
Permanent link to this record | |||||
Author | Onur Ferhat; Arcadi Llanza; Fernando Vilariño | ||||
Title ![]() |
Gaze interaction for multi-display systems using natural light eye-tracker | Type | Conference Article | ||
Year | 2015 | Publication | 2nd International Workshop on Solutions for Automatic Gaze Data Analysis | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | |||||
Address | Bielefeld; Germany; September 2015 | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | SAGA | ||
Notes | MV;SIAI | Approved | no | ||
Call Number | Admin @ si @ FLV2015b | Serial | 2676 | ||
Permanent link to this record | |||||
Author | Jaume Garcia | ||||
Title ![]() |
Generalized Active Shape Models Applied to Cardiac Function Analysis | Type | Report | ||
Year | 2004 | Publication | CVC Technical Report | Abbreviated Journal | |
Volume | Issue | 78 | Pages | ||
Keywords | Cardiac Analysis; Deformable Models; Active Contour Models; Active Shape Models; Tagged MRI; HARP; Contrast Echocardiography. | ||||
Abstract | Medical imaging is very useful in the assessment and treatment of many diseases. To deal with the great amount of data provided by imaging scanners and extract quantitative information that physicians can interpret, many analysis algorithms have been developed. Any process of analysis always consists of a first step of segmenting some particular structure. In medical imaging, structures are not always well defined and suffer from noise artifacts thus, ordinary segmentation methods are not well suited. The ones that seem to give better results are those based on deformable models. Nevertheless, despite their capability of mixing image features together with smoothness constraints that may compensate for image irregularities, these are naturally local methods, i. e., each node of the active contour evolve taking into account information about its neighbors and some other weak constraints about flexibility and smoothness, but not about the global shape that they should find. Due to the fact that structures to be segmented are the same for all cases but with some inter and intra-patient variation, the incorporation of a priori knowledge about shape in the segmentation method will provide robustness to it. Active Shape Models is an algorithm based on the creation of a shape model called Point Distribution Model. It performs a segmentation using only shapes similar than those previously learned from a training set that capture most of the variation presented by the structure. This algorithm works by updating shape nodes along a normal segment which often can be too restrictive. For this reason we propose a generalization of this algorithm that we call Generalized Active Shape Models and fully integrates the a priori knowledge given by the Point Distribution Model with deformable models or any other appropriate segmentation method. Two different applications to cardiac imaging of this generalized method are developed and promising results are shown. | ||||
Address | CVC (UAB) | ||||
Corporate Author | Thesis | Master's thesis | |||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | IAM; | Approved | no | ||
Call Number | IAM @ iam @ Gar2004 | Serial | 1513 | ||
Permanent link to this record | |||||
Author | Daniel Marczak; Grzegorz Rypesc; Sebastian Cygert; Tomasz Trzcinski; Bartłomiej Twardowski | ||||
Title ![]() |
Generalized Continual Category Discovery | Type | Miscellaneous | ||
Year | 2023 | Publication | arxiv | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | Most of Continual Learning (CL) methods push the limit of supervised learning settings, where an agent is expected to learn new labeled tasks and not forget previous knowledge. However, these settings are not well aligned with real-life scenarios, where a learning agent has access to a vast amount of unlabeled data encompassing both novel (entirely unlabeled) classes and examples from known classes. Drawing inspiration from Generalized Category Discovery (GCD), we introduce a novel framework that relaxes this assumption. Precisely, in any task, we allow for the existence of novel and known classes, and one must use continual version of unsupervised learning methods to discover them. We call this setting Generalized Continual Category Discovery (GCCD). It unifies CL and GCD, bridging the gap between synthetic benchmarks and real-life scenarios. With a series of experiments, we present that existing methods fail to accumulate knowledge from subsequent tasks in which unlabeled samples of novel classes are present. In light of these limitations, we propose a method that incorporates both supervised and unsupervised signals and mitigates the forgetting through the use of centroid adaptation. Our method surpasses strong CL methods adopted for GCD techniques and presents a superior representation learning performance. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | LAMP | Approved | no | ||
Call Number | Admin @ si @ MRC2023 | Serial | 3985 | ||
Permanent link to this record | |||||
Author | Arjan Gijsenij; Theo Gevers; Joost Van de Weijer | ||||
Title ![]() |
Generalized Gamut Mapping using Image Derivative Structures for Color Constancy | Type | Journal Article | ||
Year | 2010 | Publication | International Journal of Computer Vision | Abbreviated Journal | IJCV |
Volume | 86 | Issue | 2-3 | Pages | 127-139 |
Keywords | |||||
Abstract | The gamut mapping algorithm is one of the most promising methods to achieve computational color constancy. However, so far, gamut mapping algorithms are restricted to the use of pixel values to estimate the illuminant. Therefore, in this paper, gamut mapping is extended to incorporate the statistical nature of images. It is analytically shown that the proposed gamut mapping framework is able to include any linear filter output. The main focus is on the local n-jet describing the derivative structure of an image. It is shown that derivatives have the advantage over pixel values to be invariant to disturbing effects (i.e. deviations of the diagonal model) such as saturated colors and diffuse light. Further, as the n-jet based gamut mapping has the ability to use more information than pixel values alone, the combination of these algorithms are more stable than the regular gamut mapping algorithm. Different methods of combining are proposed. Based on theoretical and experimental results conducted on large scale data sets of hyperspectral, laboratory and realworld scenes, it can be derived that (1) in case of deviations of the diagonal model, the derivative-based approach outperforms the pixel-based gamut mapping, (2) state-of-the-art algorithms are outperformed by the n-jet based gamut mapping, (3) the combination of the different n-jet based gamut | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Kluwer Academic Publishers Hingham, MA, USA | Place of Publication | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | 0920-5691 | ISBN | Medium | ||
Area | Expedition | Conference | |||
Notes | ISE | Approved | no | ||
Call Number | CAT @ cat @ GGW2010 | Serial | 1274 | ||
Permanent link to this record | |||||
Author | Miquel Ferrer; Ernest Valveny; F. Serratosa; K. Riesen; Horst Bunke | ||||
Title ![]() |
Generalized Median Graph Computation by Means of Graph Embedding in Vector Spaces | Type | Journal Article | ||
Year | 2010 | Publication | Pattern Recognition | Abbreviated Journal | PR |
Volume | 43 | Issue | 4 | Pages | 1642–1655 |
Keywords | Graph matching; Weighted mean of graphs; Median graph; Graph embedding; Vector spaces | ||||
Abstract | The median graph has been presented as a useful tool to represent a set of graphs. Nevertheless its computation is very complex and the existing algorithms are restricted to use limited amount of data. In this paper we propose a new approach for the computation of the median graph based on graph embedding. Graphs are embedded into a vector space and the median is computed in the vector domain. We have designed a procedure based on the weighted mean of a pair of graphs to go from the vector domain back to the graph domain in order to obtain a final approximation of the median graph. Experiments on three different databases containing large graphs show that we succeed to compute good approximations of the median graph. We have also applied the median graph to perform some basic classification tasks achieving reasonable good results. These experiments on real data open the door to the application of the median graph to a number of more complex machine learning algorithms where a representative of a set of graphs is needed. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Elsevier | Place of Publication | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | DAG | Approved | no | ||
Call Number | DAG @ dag @ FVS2010 | Serial | 1294 | ||
Permanent link to this record | |||||
Author | Eloi Puertas; Sergio Escalera; Oriol Pujol | ||||
Title ![]() |
Generalized Multi-scale Stacked Sequential Learning for Multi-class Classification | Type | Journal Article | ||
Year | 2015 | Publication | Pattern Analysis and Applications | Abbreviated Journal | PAA |
Volume | 18 | Issue | 2 | Pages | 247-261 |
Keywords | Stacked sequential learning; Multi-scale; Error-correct output codes (ECOC); Contextual classification | ||||
Abstract | In many classification problems, neighbor data labels have inherent sequential relationships. Sequential learning algorithms take benefit of these relationships in order to improve generalization. In this paper, we revise the multi-scale sequential learning approach (MSSL) for applying it in the multi-class case (MMSSL). We introduce the error-correcting output codesframework in the MSSL classifiers and propose a formulation for calculating confidence maps from the margins of the base classifiers. In addition, we propose a MMSSL compression approach which reduces the number of features in the extended data set without a loss in performance. The proposed methods are tested on several databases, showing significant performance improvement compared to classical approaches. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Springer-Verlag | Place of Publication | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | 1433-7541 | ISBN | Medium | ||
Area | Expedition | Conference | |||
Notes | HuPBA;MILAB | Approved | no | ||
Call Number | Admin @ si @ PEP2013 | Serial | 2251 | ||
Permanent link to this record |