Home [111–120] << 121 122 123 124 125 126 127 128 129 130 >> [131–140]
List View
 | 
Citations
 | 
Details
   web
Records
Author Katerine Diaz; Francesc J. Ferri
Title Extensiones del método de vectores comunes discriminantes Aplicadas a la clasificación de imágenes Type Book Whole
Year 2013 Publication Extensiones del método de vectores comunes discriminantes Aplicadas a la clasificación de imágenes Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Los métodos basados en subespacios son una herramienta muy utilizada en aplicaciones de visión por computador. Aquí se presentan y validan algunos algoritmos que hemos propuesto en este campo de investigación. El primer algoritmo está relacionado con una extensión del método de vectores comunes discriminantes con kernel, que reinterpreta el espacio nulo de la matriz de dispersión intra-clase del conjunto de entrenamiento para obtener las características discriminantes. Dentro de los métodos basados en subespacios existen diferentes tipos de entrenamiento. Uno de los más populares, pero no por ello uno de los más eficientes, es el aprendizaje por lotes. En este tipo de aprendizaje, todas las muestras del conjunto de entrenamiento tienen que estar disponibles desde el inicio. De este modo, cuando nuevas muestras se ponen a disposición del algoritmo, el sistema tiene que ser reentrenado de nuevo desde cero. Una alternativa a este tipo de entrenamiento es el aprendizaje incremental. Aquí­ se proponen diferentes algoritmos incrementales del método de vectores comunes discriminantes.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title (up)
Series Volume Series Issue Edition
ISSN ISBN 978-3-639-55339-0 Medium
Area Expedition Conference
Notes ADAS Approved no
Call Number Admin @ si @ DiF2013 Serial 2440
Permanent link to this record
 
 
Author Mohammad Ali Bagheri; Qigang Gao; Sergio Escalera
Title Combining Local and Global Learners in the Pairwise Multiclass Classification Type Journal Article
Year 2015 Publication Pattern Analysis and Applications Abbreviated Journal PAA
Volume 18 Issue 4 Pages 845-860
Keywords Multiclass classification; Pairwise approach; One-versus-one
Abstract Pairwise classification is a well-known class binarization technique that converts a multiclass problem into a number of two-class problems, one problem for each pair of classes. However, in the pairwise technique, nuisance votes of many irrelevant classifiers may result in a wrong class prediction. To overcome this problem, a simple, but efficient method is proposed and evaluated in this paper. The proposed method is based on excluding some classes and focusing on the most probable classes in the neighborhood space, named Local Crossing Off (LCO). This procedure is performed by employing a modified version of standard K-nearest neighbor and large margin nearest neighbor algorithms. The LCO method takes advantage of nearest neighbor classification algorithm because of its local learning behavior as well as the global behavior of powerful binary classifiers to discriminate between two classes. Combining these two properties in the proposed LCO technique will avoid the weaknesses of each method and will increase the efficiency of the whole classification system. On several benchmark datasets of varying size and difficulty, we found that the LCO approach leads to significant improvements using different base learners. The experimental results show that the proposed technique not only achieves better classification accuracy in comparison to other standard approaches, but also is computationally more efficient for tackling classification problems which have a relatively large number of target classes.
Address
Corporate Author Thesis
Publisher Springer London Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title (up)
Series Volume Series Issue Edition
ISSN 1433-7541 ISBN Medium
Area Expedition Conference
Notes HuPBA;MILAB Approved no
Call Number Admin @ si @ BGE2014 Serial 2441
Permanent link to this record
 
 
Author Oscar Lopes; Miguel Reyes; Sergio Escalera; Jordi Gonzalez
Title Spherical Blurred Shape Model for 3-D Object and Pose Recognition: Quantitative Analysis and HCI Applications in Smart Environments Type Journal Article
Year 2014 Publication IEEE Transactions on Systems, Man and Cybernetics (Part B) Abbreviated Journal TSMCB
Volume 44 Issue 12 Pages 2379-2390
Keywords
Abstract The use of depth maps is of increasing interest after the advent of cheap multisensor devices based on structured light, such as Kinect. In this context, there is a strong need of powerful 3-D shape descriptors able to generate rich object representations. Although several 3-D descriptors have been already proposed in the literature, the research of discriminative and computationally efficient descriptors is still an open issue. In this paper, we propose a novel point cloud descriptor called spherical blurred shape model (SBSM) that successfully encodes the structure density and local variabilities of an object based on shape voxel distances and a neighborhood propagation strategy. The proposed SBSM is proven to be rotation and scale invariant, robust to noise and occlusions, highly discriminative for multiple categories of complex objects like the human hand, and computationally efficient since the SBSM complexity is linear to the number of object voxels. Experimental evaluation in public depth multiclass object data, 3-D facial expressions data, and a novel hand poses data sets show significant performance improvements in relation to state-of-the-art approaches. Moreover, the effectiveness of the proposal is also proved for object spotting in 3-D scenes and for real-time automatic hand pose recognition in human computer interaction scenarios.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title (up)
Series Volume Series Issue Edition
ISSN 2168-2267 ISBN Medium
Area Expedition Conference
Notes HuPBA; ISE; 600.078;MILAB Approved no
Call Number Admin @ si @ LRE2014 Serial 2442
Permanent link to this record
 
 
Author Xavier Perez Sala; Sergio Escalera; Cecilio Angulo; Jordi Gonzalez
Title A survey on model based approaches for 2D and 3D visual human pose recovery Type Journal Article
Year 2014 Publication Sensors Abbreviated Journal SENS
Volume 14 Issue 3 Pages 4189-4210
Keywords human pose recovery; human body modelling; behavior analysis; computer vision
Abstract Human Pose Recovery has been studied in the field of Computer Vision for the last 40 years. Several approaches have been reported, and significant improvements have been obtained in both data representation and model design. However, the problem of Human Pose Recovery in uncontrolled environments is far from being solved. In this paper, we define a general taxonomy to group model based approaches for Human Pose Recovery, which is composed of five main modules: appearance, viewpoint, spatial relations, temporal consistence, and behavior. Subsequently, a methodological comparison is performed following the proposed taxonomy, evaluating current SoA approaches in the aforementioned five group categories. As a result of this comparison, we discuss the main advantages and drawbacks of the reviewed literature.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title (up)
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes HuPBA; ISE; 600.046; 600.063; 600.078;MILAB Approved no
Call Number Admin @ si @ PEA2014 Serial 2443
Permanent link to this record
 
 
Author Frederic Sampedro; Anna Domenech; Sergio Escalera
Title Obtaining quantitative global tumoral state indicators based on whole-body PET/CT scans: A breast cancer case study Type Journal Article
Year 2014 Publication Nuclear Medicine Communications Abbreviated Journal NMC
Volume 35 Issue 4 Pages 362-371
Keywords
Abstract Objectives: In this work we address the need for the computation of quantitative global tumoral state indicators from oncological whole-body PET/computed tomography scans. The combination of such indicators with other oncological information such as tumor markers or biopsy results would prove useful in oncological decision-making scenarios.

Materials and methods: From an ordering of 100 breast cancer patients on the basis of oncological state through visual analysis by a consensus of nuclear medicine specialists, a set of numerical indicators computed from image analysis of the PET/computed tomography scan is presented, which attempts to summarize a patient’s oncological state in a quantitative manner taking into consideration the total tumor volume, aggressiveness, and spread.

Results: Results obtained by comparative analysis of the proposed indicators with respect to the experts’ evaluation show up to 87% Pearson’s correlation coefficient when providing expert-guided PET metabolic tumor volume segmentation and 64% correlation when using completely automatic image analysis techniques.

Conclusion: Global quantitative tumor information obtained by whole-body PET/CT image analysis can prove useful in clinical nuclear medicine settings and oncological decision-making scenarios. The completely automatic computation of such indicators would improve its impact as time efficiency and specialist independence would be achieved.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title (up)
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes HuPBA;MILAB Approved no
Call Number SDE2014a Serial 2444
Permanent link to this record
 
 
Author Mohammad Ali Bagheri; Qigang Gao; Sergio Escalera
Title Generic Subclass Ensemble: A Novel Approach to Ensemble Classification Type Conference Article
Year 2014 Publication 22nd International Conference on Pattern Recognition Abbreviated Journal
Volume Issue Pages 1254 - 1259
Keywords
Abstract Multiple classifier systems, also known as classifier ensembles, have received great attention in recent years because of their improved classification accuracy in different applications. In this paper, we propose a new general approach to ensemble classification, named generic subclass ensemble, in which each base classifier is trained with data belonging to a subset of classes, and thus discriminates among a subset of target categories. The ensemble classifiers are then fused using a combination rule. The proposed approach differs from existing methods that manipulate the target attribute, since in our approach individual classification problems are not restricted to two-class problems. We perform a series of experiments to evaluate the efficiency of the generic subclass approach on a set of benchmark datasets. Experimental results with multilayer perceptrons show that the proposed approach presents a viable alternative to the most commonly used ensemble classification approaches.
Address Stockholm; August 2014
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title (up)
Series Volume Series Issue Edition
ISSN 1051-4651 ISBN Medium
Area Expedition Conference ICPR
Notes HuPBA;MILAB Approved no
Call Number Admin @ si @ BGE2014b Serial 2445
Permanent link to this record
 
 
Author Mohammad Ali Bagheri; Gang Hu; Qigang Gao; Sergio Escalera
Title A Framework of Multi-Classifier Fusion for Human Action Recognition Type Conference Article
Year 2014 Publication 22nd International Conference on Pattern Recognition Abbreviated Journal
Volume Issue Pages 1260 - 1265
Keywords
Abstract The performance of different action-recognition methods using skeleton joint locations have been recently studied by several computer vision researchers. However, the potential improvement in classification through classifier fusion by ensemble-based methods has remained unattended. In this work, we evaluate the performance of an ensemble of five action learning techniques, each performing the recognition task from a different perspective. The underlying rationale of the fusion approach is that different learners employ varying structures of input descriptors/features to be trained. These varying structures cannot be attached and used by a single learner. In addition, combining the outputs of several learners can reduce the risk of an unfortunate selection of a poorly performing learner. This leads to having a more robust and general-applicable framework. Also, we propose two simple, yet effective, action description techniques. In order to improve the recognition performance, a powerful combination strategy is utilized based on the Dempster-Shafer theory, which can effectively make use of diversity of base learners trained on different sources of information. The recognition results of the individual classifiers are compared with those obtained from fusing the classifiers' output, showing advanced performance of the proposed methodology.
Address Stockholm; Sweden; August 2014
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title (up)
Series Volume Series Issue Edition
ISSN 1051-4651 ISBN Medium
Area Expedition Conference ICPR
Notes HuPBA;MILAB Approved no
Call Number Admin @ si @ BHG2014 Serial 2446
Permanent link to this record
 
 
Author Naveen Onkarappa
Title Optical Flow in Driver Assistance Systems Type Book Whole
Year 2013 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Motion perception is one of the most important attributes of the human brain. Visual motion perception consists in inferring speed and direction of elements in a scene based on visual inputs. Analogously, computer vision is assisted by motion cues in the scene. Motion detection in computer vision is useful in solving problems such as segmentation, depth from motion, structure from motion, compression, navigation and many others. These problems are common in several applications, for instance, video surveillance, robot navigation and advanced driver assistance systems (ADAS). One of the most widely used techniques for motion detection is the optical flow estimation. The work in this thesis attempts to make optical flow suitable for the requirements and conditions of driving scenarios. In this context, a novel space-variant representation called reverse log-polar representation is proposed that is shown to be better than the traditional log-polar space-variant representation for ADAS. The space-variant representations reduce the amount of data to be processed. Another major contribution in this research is related to the analysis of the influence of specific characteristics from driving scenarios on the optical flow accuracy. Characteristics such as vehicle speed and
road texture are considered in the aforementioned analysis. From this study, it is inferred that the regularization weight has to be adapted according to the required error measure and for different speeds and road textures. It is also shown that polar represented optical flow suits driving scenarios where predominant motion is translation. Due to the requirements of such a study and by the lack of needed datasets a new synthetic dataset is presented; it contains: i) sequences of different speeds and road textures in an urban scenario; ii) sequences with complex motion of an on-board camera; and iii) sequences with additional moving vehicles in the scene. The ground-truth optical flow is generated by the ray-tracing technique. Further, few applications of optical flow in ADAS are shown. Firstly, a robust RANSAC based technique to estimate horizon line is proposed. Then, an egomotion estimation is presented to compare the proposed space-variant representation with the classical one. As a final contribution, a modification in the regularization term is proposed that notably improves the results
in the ADAS applications. This adaptation is evaluated using a state of the art optical flow technique. The experiments on a public dataset (KITTI) validate the advantages of using the proposed modification.
Address Bellaterra
Corporate Author Thesis Ph.D. thesis
Publisher Ediciones Graficas Rey Place of Publication Editor Angel Sappa
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title (up)
Series Volume Series Issue Edition
ISSN ISBN 978-84-940902-1-9 Medium
Area Expedition Conference
Notes ADAS Approved no
Call Number Admin @ si @ Nav2013 Serial 2447
Permanent link to this record
 
 
Author Jorge Bernal; Fernando Vilariño; F. Javier Sanchez; M. Arnold; Anarta Ghosh; Gerard Lacey
Title Experts vs Novices: Applying Eye-tracking Methodologies in Colonoscopy Video Screening for Polyp Search Type Conference Article
Year 2014 Publication 2014 Symposium on Eye Tracking Research and Applications Abbreviated Journal
Volume Issue Pages 223-226
Keywords
Abstract We present in this paper a novel study aiming at identifying the differences in visual search patterns between physicians of diverse levels of expertise during the screening of colonoscopy videos. Physicians were clustered into two groups -experts and novices- according to the number of procedures performed, and fixations were captured by an eye-tracker device during the task of polyp search in different video sequences. These fixations were integrated into heat maps, one for each cluster. The obtained maps were validated over a ground truth consisting of a mask of the polyp, and the comparison between experts and novices was performed by using metrics such as reaction time, dwelling time and energy concentration ratio. Experimental results show a statistically significant difference between experts and novices, and the obtained maps show to be a useful tool for the characterisation of the behaviour of each group.
Address USA; March 2014
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title (up)
Series Volume Series Issue Edition
ISSN ISBN 978-1-4503-2751-0 Medium
Area Expedition Conference ETRA
Notes MV; 600.047; 600.060;SIAI Approved no
Call Number Admin @ si @ BVS2014 Serial 2448
Permanent link to this record
 
 
Author Fahad Shahbaz Khan; Joost Van de Weijer; Andrew Bagdanov; Michael Felsberg
Title Scale Coding Bag-of-Words for Action Recognition Type Conference Article
Year 2014 Publication 22nd International Conference on Pattern Recognition Abbreviated Journal
Volume Issue Pages 1514-1519
Keywords
Abstract Recognizing human actions in still images is a challenging problem in computer vision due to significant amount of scale, illumination and pose variation. Given the bounding box of a person both at training and test time, the task is to classify the action associated with each bounding box in an image.
Most state-of-the-art methods use the bag-of-words paradigm for action recognition. The bag-of-words framework employing a dense multi-scale grid sampling strategy is the de facto standard for feature detection. This results in a scale invariant image representation where all the features at multiple-scales are binned in a single histogram. We argue that such a scale invariant
strategy is sub-optimal since it ignores the multi-scale information
available with each bounding box of a person.
This paper investigates alternative approaches to scale coding for action recognition in still images. We encode multi-scale information explicitly in three different histograms for small, medium and large scale visual-words. Our first approach exploits multi-scale information with respect to the image size. In our second approach, we encode multi-scale information relative to the size of the bounding box of a person instance. In each approach, the multi-scale histograms are then concatenated into a single representation for action classification. We validate our approaches on the Willow dataset which contains seven action categories: interacting with computer, photography, playing music,
riding bike, riding horse, running and walking. Our results clearly suggest that the proposed scale coding approaches outperform the conventional scale invariant technique. Moreover, we show that our approach obtains promising results compared to more complex state-of-the-art methods.
Address Stockholm; August 2014
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title (up)
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference ICPR
Notes CIC; LAMP; 601.240; 600.074; 600.079 Approved no
Call Number Admin @ si @ KWB2014 Serial 2450
Permanent link to this record
 
 
Author Shida Beigpour; Christian Riess; Joost Van de Weijer; Elli Angelopoulou
Title Multi-Illuminant Estimation with Conditional Random Fields Type Journal Article
Year 2014 Publication IEEE Transactions on Image Processing Abbreviated Journal TIP
Volume 23 Issue 1 Pages 83-95
Keywords color constancy; CRF; multi-illuminant
Abstract Most existing color constancy algorithms assume uniform illumination. However, in real-world scenes, this is not often the case. Thus, we propose a novel framework for estimating the colors of multiple illuminants and their spatial distribution in the scene. We formulate this problem as an energy minimization task within a conditional random field over a set of local illuminant estimates. In order to quantitatively evaluate the proposed method, we created a novel data set of two-dominant-illuminant images comprised of laboratory, indoor, and outdoor scenes. Unlike prior work, our database includes accurate pixel-wise ground truth illuminant information. The performance of our method is evaluated on multiple data sets. Experimental results show that our framework clearly outperforms single illuminant estimators as well as a recently proposed multi-illuminant estimation approach.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title (up)
Series Volume Series Issue Edition
ISSN 1057-7149 ISBN Medium
Area Expedition Conference
Notes CIC; LAMP; 600.074; 600.079 Approved no
Call Number Admin @ si @ BRW2014 Serial 2451
Permanent link to this record
 
 
Author Q. Xue; Laura Igual; A. Berenguel; M. Guerrieri; L. Garrido
Title Active Contour Segmentation with Affine Coordinate-Based Parametrization Type Conference Article
Year 2014 Publication 9th International Conference on Computer Vision Theory and Applications Abbreviated Journal
Volume 1 Issue Pages 5-14
Keywords Active Contours; Affine Coordinates; Mean Value Coordinates
Abstract In this paper, we present a new framework for image segmentation based on parametrized active contours. The contour and the points of the image space are parametrized using a set of reduced control points that have to form a closed polygon in two dimensional problems and a closed surface in three dimensional problems. By moving the control points, the active contour evolves. We use mean value coordinates as the parametrization tool for the interface, which allows to parametrize any point of the space, inside or outside the closed polygon
or surface. Region-based energies such as the one proposed by Chan and Vese can be easily implemented in both two and three dimensional segmentation problems. We show the usefulness of our approach with several experiments.
Address Lisboa; January 2014
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title (up)
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference VISAPP
Notes OR;MILAB Approved no
Call Number Admin @ si @ XIB2014 Serial 2452
Permanent link to this record
 
 
Author David Masip; Michael S. North ; Alexander Todorov; Daniel N. Osherson
Title Automated Prediction of Preferences Using Facial Expressions Type Journal Article
Year 2014 Publication PloS one Abbreviated Journal Plos
Volume 9 Issue 2 Pages e87434
Keywords
Abstract We introduce a computer vision problem from social cognition, namely, the automated detection of attitudes from a person's spontaneous facial expressions. To illustrate the challenges, we introduce two simple algorithms designed to predict observers’ preferences between images (e.g., of celebrities) based on covert videos of the observers’ faces. The two algorithms are almost as accurate as human judges performing the same task but nonetheless far from perfect. Our approach is to locate facial landmarks, then predict preference on the basis of their temporal dynamics. The database contains 768 videos involving four different kinds of preferences. We make it publically available.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title (up)
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes OR;MV Approved no
Call Number Admin @ si @ MNT2014 Serial 2453
Permanent link to this record
 
 
Author Alejandro Gonzalez Alzate; Sebastian Ramos; David Vazquez; Antonio Lopez; Jaume Amores
Title Spatiotemporal Stacked Sequential Learning for Pedestrian Detection Type Conference Article
Year 2015 Publication Pattern Recognition and Image Analysis, Proceedings of 7th Iberian Conference , ibPRIA 2015 Abbreviated Journal
Volume Issue Pages 3-12
Keywords SSL; Pedestrian Detection
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.
Address Santiago de Compostela; España; June 2015
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title (up)
Series Volume Series Issue Edition
ISSN ISBN Medium
Area ACDC Expedition Conference IbPRIA
Notes ADAS; 600.057; 600.054; 600.076 Approved no
Call Number GRV2015; ADAS @ adas @ GRV2015 Serial 2454
Permanent link to this record
 
 
Author Jiaolong Xu; Sebastian Ramos; David Vazquez; Antonio Lopez
Title Incremental Domain Adaptation of Deformable Part-based Models Type Conference Article
Year 2014 Publication 25th British Machine Vision Conference Abbreviated Journal
Volume Issue Pages
Keywords Pedestrian Detection; Part-based models; Domain Adaptation
Abstract Nowadays, classifiers play a core role in many computer vision tasks. The underlying assumption for learning classifiers is that the training set and the deployment environment (testing) follow the same probability distribution regarding the features used by the classifiers. However, in practice, there are different reasons that can break this constancy assumption. Accordingly, reusing existing classifiers 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 paper we focus on the domain adaptation of deformable part-based models (DPMs) for object detection. In particular, we focus on a relatively unexplored scenario, i.e. incremental domain adaptation for object detection assuming weak-labeling. Therefore, our algorithm is ready to improve existing source-oriented DPM-based detectors as soon as a little amount of labeled target-domain training data is available, and keeps improving as more of such data arrives in a continuous fashion. For achieving this, we follow a multiple
instance learning (MIL) paradigm that operates in an incremental per-image basis. As proof of concept, we address the challenging scenario of adapting a DPM-based pedestrian detector trained with synthetic pedestrians to operate in real-world scenarios. The obtained results show that our incremental adaptive models obtain equally good accuracy results as the batch learned models, while being more flexible for handling continuously arriving target-domain data.
Address Nottingham; uk; September 2014
Corporate Author Thesis
Publisher BMVA Press Place of Publication Editor Valstar, Michel and French, Andrew and Pridmore, Tony
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title (up)
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference BMVC
Notes ADAS; 600.057; 600.054; 600.076 Approved no
Call Number XRV2014c; ADAS @ adas @ xrv2014c Serial 2455
Permanent link to this record