Home [71–80] << 81 82 83 84 85 86 87 88 89 90 >> [91–100]
List View
 | 
Citations
 | 
Details
   web
Records
Author Mohammed Al Rawi; Ernest Valveny
Title Compact and Efficient Multitask Learning in Vision, Language and Speech Type Conference Article
Year 2019 Publication IEEE International Conference on Computer Vision Workshops Abbreviated Journal
Volume Issue Pages 2933-2942
Keywords
Abstract (up) Across-domain multitask learning is a challenging area of computer vision and machine learning due to the intra-similarities among class distributions. Addressing this problem to cope with the human cognition system by considering inter and intra-class categorization and recognition complicates the problem even further. We propose in this work an effective holistic and hierarchical learning by using a text embedding layer on top of a deep learning model. We also propose a novel sensory discriminator approach to resolve the collisions between different tasks and domains. We then train the model concurrently on textual sentiment analysis, speech recognition, image classification, action recognition from video, and handwriting word spotting of two different scripts (Arabic and English). The model we propose successfully learned different tasks across multiple domains.
Address Seul; Korea; October 2019
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 ICCVW
Notes DAG; 600.121; 600.129 Approved no
Call Number Admin @ si @ RaV2019 Serial 3365
Permanent link to this record
 
 
Author Albert Clapes
Title Learning to recognize human actions: from hand-crafted to deep-learning based visual representations Type Book Whole
Year 2019 Publication PhD Thesis, Universitat de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract (up) Action recognition is a very challenging and important problem in computer vi­sion. Researchers working on this field aspire to provide computers with the abil­ ity to visually perceive human actions – that is, to observe, interpret, and under­ stand human-related events that occur in the physical environment merely from visual data. The applications of this technology are numerous: human-machine interaction, e-health, monitoring/surveillance, and content-based video retrieval, among others. Hand-crafted methods dominated the field until the apparition of the first successful deep learning-based action recognition works. Although ear­ lier deep-based methods underperformed with respect to hand-crafted approaches, these slowly but steadily improved to become state-of-the-art, eventually achieving better results than hand-crafted ones. Still, hand-crafted approaches can be advan­ tageous in certain scenarios, specially when not enough data is available to train very large deep models or simply to be combined with deep-based methods to fur­ ther boost the performance. Hence, showing how hand-crafted features can provide extra knowledge the deep networks are notable to easily learn about human actions.
This Thesis concurs in time with this change of paradigm and, hence, reflects it into two distinguished parts. In the first part, we focus on improving current suc­ cessful hand-crafted approaches for action recognition and we do so from three dif­ ferent perspectives. Using the dense trajectories framework as a backbone: first, we explore the use of multi-modal and multi-view input
data to enrich the trajectory de­ scriptors. Second, we focus on the classification part of action recognition pipelines and propose an ensemble learning approach, where each classifier leams from a dif­ferent set of local spatiotemporal features to then combine their outputs following an strategy based on the Dempster-Shaffer Theory. And third, we propose a novel hand-crafted feature extraction method that constructs a rnid-level feature descrip­ tion to better modellong-term spatiotemporal dynarnics within action videos. Moving to the second part of the Thesis, we start with a comprehensive study of the current deep-learning based action recognition methods. We review both fun­ damental and cutting edge methodologies reported during the last few years and introduce a taxonomy of deep-leaming methods dedicated to action recognition. In particular, we analyze and discuss how these handle
the temporal dimension of data. Last but not least, we propose a residual recurrent network for action recogni­ tion that naturally integrates all our previous findings in a powerful and prornising framework.
Address January 2019
Corporate Author Thesis Ph.D. thesis
Publisher Ediciones Graficas Rey Place of Publication Editor Sergio Escalera
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-948531-2-8 Medium
Area Expedition Conference
Notes HUPBA Approved no
Call Number Admin @ si @ Cla2019 Serial 3219
Permanent link to this record
 
 
Author Fahad Shahbaz Khan; Jiaolong Xu; Muhammad Anwer Rao; Joost Van de Weijer; Andrew Bagdanov; Antonio Lopez
Title Recognizing Actions through Action-specific Person Detection Type Journal Article
Year 2015 Publication IEEE Transactions on Image Processing Abbreviated Journal TIP
Volume 24 Issue 11 Pages 4422-4432
Keywords
Abstract (up) Action recognition in still images is a challenging problem in computer vision. To facilitate comparative evaluation independently of person detection, the standard evaluation protocol for action recognition uses an oracle person detector to obtain perfect bounding box information at both training and test time. The assumption is that, in practice, a general person detector will provide candidate bounding boxes for action recognition. In this paper, we argue that this paradigm is suboptimal and that action class labels should already be considered during the detection stage. Motivated by the observation that body pose is strongly conditioned on action class, we show that: 1) the existing state-of-the-art generic person detectors are not adequate for proposing candidate bounding boxes for action classification; 2) due to limited training examples, the direct training of action-specific person detectors is also inadequate; and 3) using only a small number of labeled action examples, the transfer learning is able to adapt an existing detector to propose higher quality bounding boxes for subsequent action classification. To the best of our knowledge, we are the first to investigate transfer learning for the task of action-specific person detection in still images. We perform extensive experiments on two benchmark data sets: 1) Stanford-40 and 2) PASCAL VOC 2012. For the action detection task (i.e., both person localization and classification of the action performed), our approach outperforms methods based on general person detection by 5.7% mean average precision (MAP) on Stanford-40 and 2.1% MAP on PASCAL VOC 2012. Our approach also significantly outperforms the state of the art with a MAP of 45.4% on Stanford-40 and 31.4% on PASCAL VOC 2012. We also evaluate our action detection approach for the task of action classification (i.e., recognizing actions without localizing them). For this task, our approach, without using any ground-truth person localization at test tim- , outperforms on both data sets state-of-the-art methods, which do use person locations.
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 1057-7149 ISBN Medium
Area Expedition Conference
Notes ADAS; LAMP; 600.076; 600.079 Approved no
Call Number Admin @ si @ KXR2015 Serial 2668
Permanent link to this record
 
 
Author Cesar de Souza; Adrien Gaidon; Eleonora Vig; Antonio Lopez
Title Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition Type Conference Article
Year 2016 Publication 14th European Conference on Computer Vision Abbreviated Journal
Volume Issue Pages 697-716
Keywords
Abstract (up) Action recognition in videos is a challenging task due to the complexity of the spatio-temporal patterns to model and the difficulty to acquire and learn on large quantities of video data. Deep learning, although a breakthrough for image classification and showing promise for videos, has still not clearly superseded action recognition methods using hand-crafted features, even when training on massive datasets. In this paper, we introduce hybrid video classification architectures based on carefully designed unsupervised representations of hand-crafted spatio-temporal features classified by supervised deep networks. As we show in our experiments on five popular benchmarks for action recognition, our hybrid model combines the best of both worlds: it is data efficient (trained on 150 to 10000 short clips) and yet improves significantly on the state of the art, including recent deep models trained on millions of manually labelled images and videos.
Address Amsterdam; The Netherlands; October 2016
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference ECCV
Notes ADAS; 600.076; 600.085 Approved no
Call Number Admin @ si @ SGV2016 Serial 2824
Permanent link to this record
 
 
Author Ikechukwu Ofodile; Ahmed Helmi; Albert Clapes; Egils Avots; Kerttu Maria Peensoo; Sandhra Mirella Valdma; Andreas Valdmann; Heli Valtna Lukner; Sergey Omelkov; Sergio Escalera; Cagri Ozcinar; Gholamreza Anbarjafari
Title Action recognition using single-pixel time-of-flight detection Type Journal Article
Year 2019 Publication Entropy Abbreviated Journal ENTROPY
Volume 21 Issue 4 Pages 414
Keywords single pixel single photon image acquisition; time-of-flight; action recognition
Abstract (up) Action recognition is a challenging task that plays an important role in many robotic systems, which highly depend on visual input feeds. However, due to privacy concerns, it is important to find a method which can recognise actions without using visual feed. In this paper, we propose a concept for detecting actions while preserving the test subject’s privacy. Our proposed method relies only on recording the temporal evolution of light pulses scattered back from the scene.
Such data trace to record one action contains a sequence of one-dimensional arrays of voltage values acquired by a single-pixel detector at 1 GHz repetition rate. Information about both the distance to the object and its shape are embedded in the traces. We apply machine learning in the form of recurrent neural networks for data analysis and demonstrate successful action recognition. The experimental results show that our proposed method could achieve on average 96.47% accuracy on the actions walking forward, walking backwards, sitting down, standing up and waving hand, using recurrent
neural network.
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 HuPBA; no proj Approved no
Call Number Admin @ si @ OHC2019 Serial 3319
Permanent link to this record
 
 
Author Mohamed Ilyes Lakhal; Albert Clapes; Sergio Escalera; Oswald Lanz; Andrea Cavallaro
Title Residual Stacked RNNs for Action Recognition Type Conference Article
Year 2018 Publication 9th International Workshop on Human Behavior Understanding Abbreviated Journal
Volume Issue Pages 534-548
Keywords Action recognition; Deep residual learning; Two-stream RNN
Abstract (up) Action recognition pipelines that use Recurrent Neural Networks (RNN) are currently 5–10% less accurate than Convolutional Neural Networks (CNN). While most works that use RNNs employ a 2D CNN on each frame to extract descriptors for action recognition, we extract spatiotemporal features from a 3D CNN and then learn the temporal relationship of these descriptors through a stacked residual recurrent neural network (Res-RNN). We introduce for the first time residual learning to counter the degradation problem in multi-layer RNNs, which have been successful for temporal aggregation in two-stream action recognition pipelines. Finally, we use a late fusion strategy to combine RGB and optical flow data of the two-stream Res-RNN. Experimental results show that the proposed pipeline achieves competitive results on UCF-101 and state of-the-art results for RNN-like architectures on the challenging HMDB-51 dataset.
Address Munich; September 2018
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 ECCVW
Notes HUPBA; no proj Approved no
Call Number Admin @ si @ LCE2018b Serial 3206
Permanent link to this record
 
 
Author Kamal Nasrollahi; Sergio Escalera; P. Rasti; Gholamreza Anbarjafari; Xavier Baro; Hugo Jair Escalante; Thomas B. Moeslund
Title Deep Learning based Super-Resolution for Improved Action Recognition Type Conference Article
Year 2015 Publication 5th International Conference on Image Processing Theory, Tools and Applications IPTA2015 Abbreviated Journal
Volume Issue Pages 67 - 72
Keywords
Abstract (up) Action recognition systems mostly work with videos of proper quality and resolution. Even most challenging benchmark databases for action recognition, hardly include videos of low-resolution from, e.g., surveillance cameras. In videos recorded by such cameras, due to the distance between people and cameras, people are pictured very small and hence challenge action recognition algorithms. Simple upsampling methods, like bicubic interpolation, cannot retrieve all the detailed information that can help the recognition. To deal with this problem, in this paper we combine results of bicubic interpolation with results of a state-ofthe-art deep learning-based super-resolution algorithm, through an alpha-blending approach. The experimental results obtained on down-sampled version of a large subset of Hoolywood2 benchmark database show the importance of the proposed system in increasing the recognition rate of a state-of-the-art action recognition system for handling low-resolution videos.
Address Orleans; France; November 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 IPTA
Notes HuPBA;MV Approved no
Call Number Admin @ si @ NER2015 Serial 2648
Permanent link to this record
 
 
Author Javad Zolfaghari Bengar; Joost Van de Weijer; Laura Lopez-Fuentes; Bogdan Raducanu
Title Class-Balanced Active Learning for Image Classification Type Conference Article
Year 2022 Publication Winter Conference on Applications of Computer Vision Abbreviated Journal
Volume Issue Pages
Keywords
Abstract (up) Active learning aims to reduce the labeling effort that is required to train algorithms by learning an acquisition function selecting the most relevant data for which a label should be requested from a large unlabeled data pool. Active learning is generally studied on balanced datasets where an equal amount of images per class is available. However, real-world datasets suffer from severe imbalanced classes, the so called long-tail distribution. We argue that this further complicates the active learning process, since the imbalanced data pool can result in suboptimal classifiers. To address this problem in the context of active learning, we proposed a general optimization framework that explicitly takes class-balancing into account. Results on three datasets showed that the method is general (it can be combined with most existing active learning algorithms) and can be effectively applied to boost the performance of both informative and representative-based active learning methods. In addition, we showed that also on balanced datasets
our method 1 generally results in a performance gain.
Address Virtual; Waikoloa; Hawai; USA; January 2022
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 WACV
Notes LAMP; 602.200; 600.147; 600.120 Approved no
Call Number Admin @ si @ ZWL2022 Serial 3703
Permanent link to this record
 
 
Author Javad Zolfaghari Bengar; Bogdan Raducanu; Joost Van de Weijer
Title When Deep Learners Change Their Mind: Learning Dynamics for Active Learning Type Conference Article
Year 2021 Publication 19th International Conference on Computer Analysis of Images and Patterns Abbreviated Journal
Volume 13052 Issue 1 Pages 403-413
Keywords
Abstract (up) Active learning aims to select samples to be annotated that yield the largest performance improvement for the learning algorithm. Many methods approach this problem by measuring the informativeness of samples and do this based on the certainty of the network predictions for samples. However, it is well-known that neural networks are overly confident about their prediction and are therefore an untrustworthy source to assess sample informativeness. In this paper, we propose a new informativeness-based active learning method. Our measure is derived from the learning dynamics of a neural network. More precisely we track the label assignment of the unlabeled data pool during the training of the algorithm. We capture the learning dynamics with a metric called label-dispersion, which is low when the network consistently assigns the same label to the sample during the training of the network and high when the assigned label changes frequently. We show that label-dispersion is a promising predictor of the uncertainty of the network, and show on two benchmark datasets that an active learning algorithm based on label-dispersion obtains excellent results.
Address September 2021
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 CAIP
Notes LAMP; OR Approved no
Call Number Admin @ si @ ZRV2021 Serial 3673
Permanent link to this record
 
 
Author M. Li; Xialei Liu; Joost Van de Weijer; Bogdan Raducanu
Title Learning to Rank for Active Learning: A Listwise Approach Type Conference Article
Year 2020 Publication 25th International Conference on Pattern Recognition Abbreviated Journal
Volume Issue Pages 5587-5594
Keywords
Abstract (up) Active learning emerged as an alternative to alleviate the effort to label huge amount of data for data hungry applications (such as image/video indexing and retrieval, autonomous driving, etc.). The goal of active learning is to automatically select a number of unlabeled samples for annotation (according to a budget), based on an acquisition function, which indicates how valuable a sample is for training the model. The learning loss method is a task-agnostic approach which attaches a module to learn to predict the target loss of unlabeled data, and select data with the highest loss for labeling. In this work, we follow this strategy but we define the acquisition function as a learning to rank problem and rethink the structure of the loss prediction module, using a simple but effective listwise approach. Experimental results on four datasets demonstrate that our method outperforms recent state-of-the-art active learning approaches for both image classification and regression tasks.
Address Virtual; January 2021
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 ICPR
Notes LAMP; 600.120 Approved no
Call Number Admin @ si @ LLW2020a Serial 3511
Permanent link to this record
 
 
Author Javad Zolfaghari Bengar; Joost Van de Weijer; Bartlomiej Twardowski; Bogdan Raducanu
Title Reducing Label Effort: Self- Supervised Meets Active Learning Type Conference Article
Year 2021 Publication International Conference on Computer Vision Workshops Abbreviated Journal
Volume Issue Pages 1631-1639
Keywords
Abstract (up) Active learning is a paradigm aimed at reducing the annotation effort by training the model on actively selected informative and/or representative samples. Another paradigm to reduce the annotation effort is self-training that learns from a large amount of unlabeled data in an unsupervised way and fine-tunes on few labeled samples. Recent developments in self-training have achieved very impressive results rivaling supervised learning on some datasets. The current work focuses on whether the two paradigms can benefit from each other. We studied object recognition datasets including CIFAR10, CIFAR100 and Tiny ImageNet with several labeling budgets for the evaluations. Our experiments reveal that self-training is remarkably more efficient than active learning at reducing the labeling effort, that for a low labeling budget, active learning offers no benefit to self-training, and finally that the combination of active learning and self-training is fruitful when the labeling budget is high. The performance gap between active learning trained either with self-training or from scratch diminishes as we approach to the point where almost half of the dataset is labeled.
Address October 2021
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 ICCVW
Notes LAMP; OR Approved no
Call Number Admin @ si @ ZVT2021 Serial 3672
Permanent link to this record
 
 
Author Alejandro Cartas; Mariella Dimiccoli; Petia Radeva
Title Batch-based activity recognition from egocentric photo-streams Type Conference Article
Year 2017 Publication 1st International workshop on Egocentric Perception, Interaction and Computing Abbreviated Journal
Volume Issue Pages
Keywords
Abstract (up) Activity recognition from long unstructured egocentric photo-streams has several applications in assistive technology such as health monitoring and frailty detection, just to name a few. However, one of its main technical challenges is to deal with the low frame rate of wearable photo-cameras, which causes abrupt appearance changes between consecutive frames. In consequence, important discriminatory low-level features from motion such as optical flow cannot be estimated. In this paper, we present a batch-driven approach for training a deep learning architecture that strongly rely on Long short-term units to tackle this problem. We propose two different implementations of the same approach that process a photo-stream sequence using batches of fixed size with the goal of capturing the temporal evolution of high-level features. The main difference between these implementations is that one explicitly models consecutive batches by overlapping them. Experimental results over a public dataset acquired by three users demonstrate the validity of the proposed architectures to exploit the temporal evolution of convolutional features over time without relying on event boundaries.
Address Venice; Italy; October 2017;
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 ICCV - EPIC
Notes MILAB; no menciona Approved no
Call Number Admin @ si @ CDR2017 Serial 3023
Permanent link to this record
 
 
Author Alejandro Cartas; Petia Radeva; Mariella Dimiccoli
Title Activities of Daily Living Monitoring via a Wearable Camera: Toward Real-World Applications Type Journal Article
Year 2020 Publication IEEE Access Abbreviated Journal ACCESS
Volume 8 Issue Pages 77344 - 77363
Keywords
Abstract (up) Activity recognition from wearable photo-cameras is crucial for lifestyle characterization and health monitoring. However, to enable its wide-spreading use in real-world applications, a high level of generalization needs to be ensured on unseen users. Currently, state-of-the-art methods have been tested only on relatively small datasets consisting of data collected by a few users that are partially seen during training. In this paper, we built a new egocentric dataset acquired by 15 people through a wearable photo-camera and used it to test the generalization capabilities of several state-of-the-art methods for egocentric activity recognition on unseen users and daily image sequences. In addition, we propose several variants to state-of-the-art deep learning architectures, and we show that it is possible to achieve 79.87% accuracy on users unseen during training. Furthermore, to show that the proposed dataset and approach can be useful in real-world applications, where data can be acquired by different wearable cameras and labeled data are scarcely available, we employed a domain adaptation strategy on two egocentric activity recognition benchmark datasets. These experiments show that the model learned with our dataset, can easily be transferred to other domains with a very small amount of labeled data. Taken together, those results show that activity recognition from wearable photo-cameras is mature enough to be tested in real-world applications.
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 MILAB; no proj Approved no
Call Number Admin @ si @ CRD2020 Serial 3436
Permanent link to this record
 
 
Author Pierluigi Casale; Oriol Pujol; Petia Radeva
Title Human Activity Recognition from Accelerometer Data using a Wearable Device Type Conference Article
Year 2011 Publication 5th Iberian Conference on Pattern Recognition and Image Analysis Abbreviated Journal
Volume 6669 Issue Pages 289-296
Keywords
Abstract (up) Activity Recognition is an emerging field of research, born from the larger fields of ubiquitous computing, context-aware computing and multimedia. Recently, recognizing everyday life activities becomes one of the challenges for pervasive computing. In our work, we developed a novel wearable system easy to use and comfortable to bring. Our wearable system is based on a new set of 20 computationally efficient features and the Random Forest classifier. We obtain very encouraging results with classification accuracy of human activities recognition of up to 94%.
Address Las Palmas de Gran Canaria. Spain
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor Vitria, Jordi; Sanches, João Miguel Raposo; Hernández, Mario
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-642-21256-7 Medium
Area Expedition Conference IbPRIA
Notes MILAB;HuPBA Approved no
Call Number Admin @ si @ CPR2011a Serial 1735
Permanent link to this record
 
 
Author V. Kober; Mikhail Mozerov; J. Alvarez-Borrego; I.A. Ovseyevich
Title Adaptive Correlation Filters for Pattern Recognition Type Journal
Year 2006 Publication Pattern Recognition and Image Analysis Abbreviated Journal
Volume 16 Issue 3 Pages 425-431
Keywords Pattern recognition, Correlation filters, A adaptive filters
Abstract (up) Adaptive correlation filters based on synthetic discriminant functions (SDFs) for reliable pattern recognition are proposed. A given value of discrimination capability can be achieved by adapting a SDF filter to the input scene. This can be done by iterative training. Computer simulation results obtained with the proposed filters are compared with those of various correlation filters in terms of recognition 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 ISE Approved no
Call Number ISE @ ise @ KMA2006a Serial 673
Permanent link to this record