Home | [101–110] << 111 112 113 114 115 116 117 118 119 120 >> [121–130] |
![]() |
Records | |||||
---|---|---|---|---|---|
Author | Marco Pedersoli; Andrea Vedaldi; Jordi Gonzalez; Xavier Roca | ||||
Title | A coarse-to-fine approach for fast deformable object detection | Type | Journal Article | ||
Year | 2015 | Publication | Pattern Recognition | Abbreviated Journal | PR |
Volume | 48 | Issue | 5 | Pages | 1844-1853 |
Keywords ![]() |
|||||
Abstract | We present a method that can dramatically accelerate object detection with part based models. The method is based on the observation that the cost of detection is likely to be dominated by the cost of matching each part to the image, and not by the cost of computing the optimal configuration of the parts as commonly assumed. Therefore accelerating detection requires minimizing the number of
part-to-image comparisons. To this end we propose a multiple-resolutions hierarchical part based model and a corresponding coarse-to-fine inference procedure that recursively eliminates from the search space unpromising part placements. The method yields a ten-fold speedup over the standard dynamic programming approach and is complementary to the cascade-of-parts approach of [9]. Compared to the latter, our method does not have parameters to be determined empirically, which simplifies its use during the training of the model. Most importantly, the two techniques can be combined to obtain a very significant speedup, of two orders of magnitude in some cases. We evaluate our method extensively on the PASCAL VOC and INRIA datasets, demonstrating a very high increase in the detection speed with little degradation of the accuracy. |
||||
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; 600.078; 602.005; 605.001; 302.012 | Approved | no | ||
Call Number | Admin @ si @ PVG2015 | Serial | 2628 | ||
Permanent link to this record | |||||
Author | Cristhian A. Aguilera-Carrasco; Angel Sappa; Ricardo Toledo | ||||
Title | LGHD: a Feature Descriptor for Matching Across Non-Linear Intensity Variations | Type | Conference Article | ||
Year | 2015 | Publication | 22th IEEE International Conference on Image Processing | Abbreviated Journal | |
Volume | Issue | Pages | 178 - 181 | ||
Keywords ![]() |
|||||
Abstract | |||||
Address | Quebec; Canada; 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 | ICIP | ||
Notes | ADAS; 600.076 | Approved | no | ||
Call Number | Admin @ si @ AST2015 | Serial | 2630 | ||
Permanent link to this record | |||||
Author | Jiaolong Xu | ||||
Title | Domain Adaptation of Deformable Part-based Models | Type | Book Whole | ||
Year | 2015 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords ![]() |
|||||
Abstract | On-board pedestrian detection is crucial for Advanced Driver Assistance Systems
(ADAS). An accurate classication is fundamental for vision-based pedestrian detection. The underlying assumption for learning classiers is that the training set and the deployment environment (testing) follow the same probability distribution regarding the features used by the classiers. However, in practice, there are dierent reasons that can break this constancy assumption. Accordingly, reusing existing classiers by adapting them from the previous training environment (source domain) to the new testing one (target domain) is an approach with increasing acceptance in the computer vision community. In this thesis we focus on the domain adaptation of deformable part-based models (DPMs) for pedestrian detection. As a prof of concept, we use a computer graphic based synthetic dataset, i.e. a virtual world, as the source domain, and adapt the virtual-world trained DPM detector to various real-world dataset. We start by exploiting the maximum detection accuracy of the virtual-world trained DPM. Even though, when operating in various real-world datasets, the virtualworld trained detector still suer from accuracy degradation due to the domain gap of virtual and real worlds. We then focus on domain adaptation of DPM. At the rst step, we consider single source and single target domain adaptation and propose two batch learning methods, namely A-SSVM and SA-SSVM. Later, we further consider leveraging multiple target (sub-)domains for progressive domain adaptation and propose a hierarchical adaptive structured SVM (HA-SSVM) for optimization. Finally, we extend HA-SSVM for the challenging online domain adaptation problem, aiming at making the detector to automatically adapt to the target domain online, without any human intervention. All of the proposed methods in this thesis do not require revisiting source domain data. The evaluations are done on the Caltech pedestrian detection benchmark. Results show that SA-SSVM slightly outperforms A-SSVM and avoids accuracy drops as high as 15 points when comparing with a non-adapted detector. The hierarchical model learned by HA-SSVM further boosts the domain adaptation performance. Finally, the online domain adaptation method has demonstrated that it can achieve comparable accuracy to the batch learned models while not requiring manually label target domain examples. Domain adaptation for pedestrian detection is of paramount importance and a relatively unexplored area. We humbly hope the work in this thesis could provide foundations for future work in this area. |
||||
Address | April 2015 | ||||
Corporate Author | Thesis | Ph.D. thesis | |||
Publisher | Place of Publication | Editor | Antonio Lopez | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | 978-84-943427-1-4 | Medium | ||
Area | Expedition | Conference | |||
Notes | ADAS; 600.076 | Approved | no | ||
Call Number | Admin @ si @ Xu2015 | Serial | 2631 | ||
Permanent link to this record | |||||
Author | Xavier Otazu; Olivier Penacchio; Xim Cerda-Company | ||||
Title | Brightness and colour induction through contextual influences in V1 | Type | Conference Article | ||
Year | 2015 | Publication | Scottish Vision Group 2015 SGV2015 | Abbreviated Journal | |
Volume | 12 | Issue | 9 | Pages | 1208-2012 |
Keywords ![]() |
|||||
Abstract | |||||
Address | Carnoustie; Scotland; March 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 | SGV | ||
Notes | NEUROBIT; | Approved | no | ||
Call Number | Admin @ si @ OPC2015a | Serial | 2632 | ||
Permanent link to this record | |||||
Author | Olivier Penacchio; Xavier Otazu; A. wilkins; J. Harris | ||||
Title | Uncomfortable images prevent lateral interactions in the cortex from providing a sparse code | Type | Conference Article | ||
Year | 2015 | Publication | European Conference on Visual Perception ECVP2015 | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords ![]() |
|||||
Abstract | |||||
Address | Liverpool; uk; August 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 | ECVP | ||
Notes | NEUROBIT; | Approved | no | ||
Call Number | Admin @ si @ POW2015 | Serial | 2633 | ||
Permanent link to this record | |||||
Author | Xavier Otazu; Olivier Penacchio; Xim Cerda-Company | ||||
Title | An excitatory-inhibitory firing rate model accounts for brightness induction, colour induction and visual discomfort | Type | Conference Article | ||
Year | 2015 | Publication | Barcelona Computational, Cognitive and Systems Neuroscience | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords ![]() |
|||||
Abstract | |||||
Address | Barcelona; June 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 | BARCCSYN | ||
Notes | NEUROBIT; | Approved | no | ||
Call Number | Admin @ si @ OPC2015b | Serial | 2634 | ||
Permanent link to this record | |||||
Author | Santiago Segui; Oriol Pujol; Jordi Vitria | ||||
Title | Learning to count with deep object features | Type | Conference Article | ||
Year | 2015 | Publication | Deep Vision: Deep Learning in Computer Vision, CVPR 2015 Workshop | Abbreviated Journal | |
Volume | Issue | Pages | 90-96 | ||
Keywords ![]() |
|||||
Abstract | Learning to count is a learning strategy that has been recently proposed in the literature for dealing with problems where estimating the number of object instances in a scene is the final objective. In this framework, the task of learning to detect and localize individual object instances is seen as a harder task that can be evaded by casting the problem as that of computing a regression value from hand-crafted image features. In this paper we explore the features that are learned when training a counting convolutional neural
network in order to understand their underlying representation. To this end we define a counting problem for MNIST data and show that the internal representation of the network is able to classify digits in spite of the fact that no direct supervision was provided for them during training. We also present preliminary results about a deep network that is able to count the number of pedestrians in a scene. |
||||
Address | Boston; USA; June 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 | CVPRW | ||
Notes | MILAB; HuPBA; OR;MV | Approved | no | ||
Call Number | Admin @ si @ SPV2015 | Serial | 2636 | ||
Permanent link to this record | |||||
Author | Marc Bolaños; Maite Garolera; Petia Radeva | ||||
Title | Active labeling application applied to food-related object recognition | Type | Conference Article | ||
Year | 2013 | Publication | 5th International Workshop on Multimedia for Cooking & Eating Activities | Abbreviated Journal | |
Volume | Issue | Pages | 45-50 | ||
Keywords ![]() |
|||||
Abstract | Every day, lifelogging devices, available for recording different aspects of our daily life, increase in number, quality and functions, just like the multiple applications that we give to them. Applying wearable devices to analyse the nutritional habits of people is a challenging application based on acquiring and analyzing life records in long periods of time. However, to extract the information of interest related to the eating patterns of people, we need automatic methods to process large amount of life-logging data (e.g. recognition of food-related objects). Creating a rich set of manually labeled samples to train the algorithms is slow, tedious and subjective. To address this problem, we propose a novel method in the framework of Active Labeling for construct- ing a training set of thousands of images. Inspired by the hierarchical sampling method for active learning [6], we propose an Active forest that organizes hierarchically the data for easy and fast labeling. Moreover, introducing a classifier into the hierarchical structures, as well as transforming the feature space for better data clustering, additionally im- prove the algorithm. Our method is successfully tested to label 89.700 food-related objects and achieves significant reduction in expert time labelling.
Active labeling application applied to food-related object recognition ResearchGate. Available from: http://www.researchgate.net/publication/262252017Activelabelingapplicationappliedtofood-relatedobjectrecognition [accessed Jul 14, 2015]. |
||||
Address | Barcelona; October 2013 | ||||
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 | ACM-CEA | ||
Notes | MILAB | Approved | no | ||
Call Number | Admin @ si @ BGR2013b | Serial | 2637 | ||
Permanent link to this record | |||||
Author | Nuria Cirera; Alicia Fornes; Josep Llados | ||||
Title | Hidden Markov model topology optimization for handwriting recognition | Type | Conference Article | ||
Year | 2015 | Publication | 13th International Conference on Document Analysis and Recognition ICDAR2015 | Abbreviated Journal | |
Volume | Issue | Pages | 626-630 | ||
Keywords ![]() |
|||||
Abstract | In this paper we present a method to optimize the topology of linear left-to-right hidden Markov models. These models are very popular for sequential signals modeling on tasks such as handwriting recognition. Many topology definition methods select the number of states for a character model based
on character length. This can be a drawback when characters are shorter than the minimum allowed by the model, since they can not be properly trained nor recognized. The proposed method optimizes the number of states per model by automatically including convenient skip-state transitions and therefore it avoids the aforementioned problem.We discuss and compare our method with other character length-based methods such the Fixed, Bakis and Quantile methods. Our proposal performs well on off-line handwriting recognition task. |
||||
Address | Nancy; France; August 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 | ICDAR | ||
Notes | DAG; 600.061; 602.006; 600.077 | Approved | no | ||
Call Number | Admin @ si @ CFL2015 | Serial | 2639 | ||
Permanent link to this record | |||||
Author | Tadashi Araki; Nobutaka Ikeda; Nilanjan Dey; Sayan Chakraborty; Luca Saba; Dinesh Kumar; Elisa Cuadrado Godia; Xiaoyi Jiang; Ajay Gupta; Petia Radeva; John R. Laird; Andrew Nicolaides; Jasjit S. Suri | ||||
Title | A comparative approach of four different image registration techniques for quantitative assessment of coronary artery calcium lesions using intravascular ultrasound | Type | Journal Article | ||
Year | 2015 | Publication | Computer Methods and Programs in Biomedicine | Abbreviated Journal | CMPB |
Volume | 118 | Issue | 2 | Pages | 158-172 |
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 | MILAB | Approved | no | ||
Call Number | Admin @ si @ AID2015 | Serial | 2640 | ||
Permanent link to this record | |||||
Author | Pau Riba; Josep Llados; Alicia Fornes | ||||
Title | Handwritten Word Spotting by Inexact Matching of Grapheme Graphs | Type | Conference Article | ||
Year | 2015 | Publication | 13th International Conference on Document Analysis and Recognition ICDAR2015 | Abbreviated Journal | |
Volume | Issue | Pages | 781 - 785 | ||
Keywords ![]() |
|||||
Abstract | This paper presents a graph-based word spotting for handwritten documents. Contrary to most word spotting techniques, which use statistical representations, we propose a structural representation suitable to be robust to the inherent deformations of handwriting. Attributed graphs are constructed using a part-based approach. Graphemes extracted from shape convexities are used as stable units of handwriting, and are associated to graph nodes. Then, spatial relations between them determine graph edges. Spotting is defined in terms of an error-tolerant graph matching using bipartite-graph matching algorithm. To make the method usable in large datasets, a graph indexing approach that makes use of binary embeddings is used as preprocessing. Historical documents are used as experimental framework. The approach is comparable to statistical ones in terms of time and memory requirements, especially when dealing with large document collections. | ||||
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 | ICDAR | ||
Notes | DAG; 600.077; 600.061; 602.006 | Approved | no | ||
Call Number | Admin @ si @ RLF2015b | Serial | 2642 | ||
Permanent link to this record | |||||
Author | Andres Traumann; Gholamreza Anbarjafari; Sergio Escalera | ||||
Title | Accurate 3D Measurement Using Optical Depth Information | Type | Journal Article | ||
Year | 2015 | Publication | Electronic Letters | Abbreviated Journal | EL |
Volume | 51 | Issue | 18 | Pages | 1420-1422 |
Keywords ![]() |
|||||
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. | ||||
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;MILAB | Approved | no | ||
Call Number | Admin @ si @ TAE2015 | Serial | 2647 | ||
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 | 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 | Isabelle Guyon; Kristin Bennett; Gavin Cawley; Hugo Jair Escalante; Sergio Escalera | ||||
Title | The AutoML challenge on codalab | Type | Conference Article | ||
Year | 2015 | Publication | IEEE International Joint Conference on Neural Networks IJCNN2015 | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords ![]() |
|||||
Abstract | |||||
Address | Killarney; Ireland; July 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 | IJCNN | ||
Notes | HuPBA;MILAB | Approved | no | ||
Call Number | Admin @ si @ GBC2015b | Serial | 2650 | ||
Permanent link to this record | |||||
Author | Gerard Canal; Cecilio Angulo; Sergio Escalera | ||||
Title | Gesture based Human Multi-Robot interaction | Type | Conference Article | ||
Year | 2015 | Publication | IEEE International Joint Conference on Neural Networks IJCNN2015 | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords ![]() |
|||||
Abstract | The emergence of robot applications for nontechnical users implies designing new ways of interaction between robotic platforms and users. The main goal of this work is the development of a gestural interface to interact with robots
in a similar way as humans do, allowing the user to provide information of the task with non-verbal communication. The gesture recognition application has been implemented using the Microsoft’s KinectTM v2 sensor. Hence, a real-time algorithm based on skeletal features is described to deal with both, static gestures and dynamic ones, being the latter recognized using a weighted Dynamic Time Warping method. The gesture recognition application has been implemented in a multi-robot case. A NAO humanoid robot is in charge of interacting with the users and respond to the visual signals they produce. Moreover, a wheeled Wifibot robot carries both the sensor and the NAO robot, easing navigation when necessary. A broad set of user tests have been carried out demonstrating that the system is, indeed, a natural approach to human robot interaction, with a fast response and easy to use, showing high gesture recognition rates. |
||||
Address | Killarney; Ireland; July 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 | IJCNN | ||
Notes | HuPBA;MILAB | Approved | no | ||
Call Number | CAE2015a | Serial | 2651 | ||
Permanent link to this record |