| |
Records |
Links |
|
Author |
Jose Manuel Alvarez; Y. LeCun; Theo Gevers; Antonio Lopez |
|
| |
Title |
Semantic Road Segmentation via Multi-Scale Ensembles of Learned Features |
Type |
Conference Article |
| |
Year |
2012 |
Publication |
12th European Conference on Computer Vision – Workshops and Demonstrations |
Abbreviated Journal |
|
|
| |
Volume |
7584 |
Issue |
|
Pages |
586-595 |
|
| |
Keywords |
road detection |
|
| |
Abstract |
Semantic segmentation refers to the process of assigning an object label (e.g., building, road, sidewalk, car, pedestrian) to every pixel in an image. Common approaches formulate the task as a random field labeling problem modeling the interactions between labels by combining local and contextual features such as color, depth, edges, SIFT or HoG. These models are trained to maximize the likelihood of the correct classification given a training set. However, these approaches rely on hand–designed features (e.g., texture, SIFT or HoG) and a higher computational time required in the inference process.
Therefore, in this paper, we focus on estimating the unary potentials of a conditional random field via ensembles of learned features. We propose an algorithm based on convolutional neural networks to learn local features from training data at different scales and resolutions. Then, diversification between these features is exploited using a weighted linear combination. Experiments on a publicly available database show the effectiveness of the proposed method to perform semantic road scene segmentation in still images. The algorithm outperforms appearance based methods and its performance is similar compared to state–of–the–art methods using other sources of information such as depth, motion or stereo. |
|
| |
Address |
|
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
Springer Berlin Heidelberg |
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
0302-9743 |
ISBN |
978-3-642-33867-0 |
Medium |
|
|
| |
Area  |
|
Expedition |
|
Conference |
ECCVW |
|
| |
Notes |
ADAS;ISE |
Approved |
no |
|
| |
Call Number |
Admin @ si @ ALG2012; ADAS @ adas |
Serial |
2187 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Gemma Roig; Xavier Boix; R. de Nijs; Sebastian Ramos; K. Kühnlenz; Luc Van Gool |
|
| |
Title |
Active MAP Inference in CRFs for Efficient Semantic Segmentation |
Type |
Conference Article |
| |
Year |
2013 |
Publication |
15th IEEE International Conference on Computer Vision |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
2312 - 2319 |
|
| |
Keywords |
Semantic Segmentation |
|
| |
Abstract |
Most MAP inference algorithms for CRFs optimize an energy function knowing all the potentials. In this paper, we focus on CRFs where the computational cost of instantiating the potentials is orders of magnitude higher than MAP inference. This is often the case in semantic image segmentation, where most potentials are instantiated by slow classifiers fed with costly features. We introduce Active MAP inference 1) to on-the-fly select a subset of potentials to be instantiated in the energy function, leaving the rest of the parameters of the potentials unknown, and 2) to estimate the MAP labeling from such incomplete energy function. Results for semantic segmentation benchmarks, namely PASCAL VOC 2010 [5] and MSRC-21 [19], show that Active MAP inference achieves similar levels of accuracy but with major efficiency gains. |
|
| |
Address |
Sydney; Australia; December 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 |
1550-5499 |
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
ICCV |
|
| |
Notes |
ADAS; 600.057 |
Approved |
no |
|
| |
Call Number |
ADAS @ adas @ RBN2013 |
Serial |
2377 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Jiaolong Xu; David Vazquez; Antonio Lopez; Javier Marin; Daniel Ponsa |
|
| |
Title |
Learning a Multiview Part-based Model in Virtual World for Pedestrian Detection |
Type |
Conference Article |
| |
Year |
2013 |
Publication |
IEEE Intelligent Vehicles Symposium |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
467 - 472 |
|
| |
Keywords |
Pedestrian Detection; Virtual World; Part based |
|
| |
Abstract |
State-of-the-art deformable part-based models based on latent SVM have shown excellent results on human detection. In this paper, we propose to train a multiview deformable part-based model with automatically generated part examples from virtual-world data. The method is efficient as: (i) the part detectors are trained with precisely extracted virtual examples, thus no latent learning is needed, (ii) the multiview pedestrian detector enhances the performance of the pedestrian root model, (iii) a top-down approach is used for part detection which reduces the searching space. We evaluate our model on Daimler and Karlsruhe Pedestrian Benchmarks with publicly available Caltech pedestrian detection evaluation framework and the result outperforms the state-of-the-art latent SVM V4.0, on both average miss rate and speed (our detector is ten times faster). |
|
| |
Address |
Gold Coast; Australia; June 2013 |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
IEEE |
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
1931-0587 |
ISBN |
978-1-4673-2754-1 |
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
IV |
|
| |
Notes |
ADAS; 600.054; 600.057 |
Approved |
no |
|
| |
Call Number |
XVL2013; ADAS @ adas @ xvl2013a |
Serial |
2214 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Patricia Marquez; Debora Gil; Aura Hernandez-Sabate; Daniel Kondermann |
|
| |
Title |
When Is A Confidence Measure Good Enough? |
Type |
Conference Article |
| |
Year |
2013 |
Publication |
9th International Conference on Computer Vision Systems |
Abbreviated Journal |
|
|
| |
Volume |
7963 |
Issue |
|
Pages |
344-353 |
|
| |
Keywords |
Optical flow, confidence measure, performance evaluation |
|
| |
Abstract |
Confidence estimation has recently become a hot topic in image processing and computer vision.Yet, several definitions exist of the term “confidence” which are sometimes used interchangeably. This is a position paper, in which we aim to give an overview on existing definitions,
thereby clarifying the meaning of the used terms to facilitate further research in this field. Based on these clarifications, we develop a theory to compare confidence measures with respect to their quality. |
|
| |
Address |
St Petersburg; Russia; July 2013 |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
Springer Link |
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
0302-9743 |
ISBN |
978-3-642-39401-0 |
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
ICVS |
|
| |
Notes |
IAM;ADAS; 600.044; 600.057; 600.060; 601.145 |
Approved |
no |
|
| |
Call Number |
IAM @ iam @ MGH2013a |
Serial |
2218 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
David Vazquez; Jiaolong Xu; Sebastian Ramos; Antonio Lopez; Daniel Ponsa |
|
| |
Title |
Weakly Supervised Automatic Annotation of Pedestrian Bounding Boxes |
Type |
Conference Article |
| |
Year |
2013 |
Publication |
CVPR Workshop on Ground Truth – What is a good dataset? |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
706 - 711 |
|
| |
Keywords |
Pedestrian Detection; Domain Adaptation |
|
| |
Abstract |
Among the components of a pedestrian detector, its trained pedestrian classifier is crucial for achieving the desired performance. The initial task of the training process consists in collecting samples of pedestrians and background, which involves tiresome manual annotation of pedestrian bounding boxes (BBs). Thus, recent works have assessed the use of automatically collected samples from photo-realistic virtual worlds. However, learning from virtual-world samples and testing in real-world images may suffer the dataset shift problem. Accordingly, in this paper we assess an strategy to collect samples from the real world and retrain with them, thus avoiding the dataset shift, but in such a way that no BBs of real-world pedestrians have to be provided. In particular, we train a pedestrian classifier based on virtual-world samples (no human annotation required). Then, using such a classifier we collect pedestrian samples from real-world images by detection. After, a human oracle rejects the false detections efficiently (weak annotation). Finally, a new classifier is trained with the accepted detections. We show that this classifier is competitive with respect to the counterpart trained with samples collected by manually annotating hundreds of pedestrian BBs. |
|
| |
Address |
Portland; Oregon; June 2013 |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
IEEE |
Place of Publication |
|
Editor |
|
|
| |
Language |
English |
Summary Language |
English |
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
CVPRW |
|
| |
Notes |
ADAS; 600.054; 600.057; 601.217 |
Approved |
no |
|
| |
Call Number |
ADAS @ adas @ VXR2013a |
Serial |
2219 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Jiaolong Xu; David Vazquez; Sebastian Ramos; Antonio Lopez; Daniel Ponsa |
|
| |
Title |
Adapting a Pedestrian Detector by Boosting LDA Exemplar Classifiers |
Type |
Conference Article |
| |
Year |
2013 |
Publication |
CVPR Workshop on Ground Truth – What is a good dataset? |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
688 - 693 |
|
| |
Keywords |
Pedestrian Detection; Domain Adaptation |
|
| |
Abstract |
Training vision-based pedestrian detectors using synthetic datasets (virtual world) is a useful technique to collect automatically the training examples with their pixel-wise ground truth. However, as it is often the case, these detectors must operate in real-world images, experiencing a significant drop of their performance. In fact, this effect also occurs among different real-world datasets, i.e. detectors' accuracy drops when the training data (source domain) and the application scenario (target domain) have inherent differences. Therefore, in order to avoid this problem, it is required to adapt the detector trained with synthetic data to operate in the real-world scenario. In this paper, we propose a domain adaptation approach based on boosting LDA exemplar classifiers from both virtual and real worlds. We evaluate our proposal on multiple real-world pedestrian detection datasets. The results show that our method can efficiently adapt the exemplar classifiers from virtual to real world, avoiding drops in average precision over the 15%. |
|
| |
Address |
Portland; oregon; June 2013 |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
English |
Summary Language |
English |
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
CVPRW |
|
| |
Notes |
ADAS; 600.054; 600.057; 601.217 |
Approved |
yes |
|
| |
Call Number |
XVR2013; ADAS @ adas @ xvr2013a |
Serial |
2220 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Patricia Marquez; Debora Gil; R.Mester; Aura Hernandez-Sabate |
|
| |
Title |
Local Analysis of Confidence Measures for Optical Flow Quality Evaluation |
Type |
Conference Article |
| |
Year |
2014 |
Publication |
9th International Conference on Computer Vision Theory and Applications |
Abbreviated Journal |
|
|
| |
Volume |
3 |
Issue |
|
Pages |
450-457 |
|
| |
Keywords |
Optical Flow; Confidence Measure; Performance Evaluation. |
|
| |
Abstract |
Optical Flow (OF) techniques facing the complexity of real sequences have been developed in the last years. Even using the most appropriate technique for our specific problem, at some points the output flow might fail to achieve the minimum error required for the system. Confidence measures computed from either input data or OF output should discard those points where OF is not accurate enough for its further use. It follows that evaluating the capabilities of a confidence measure for bounding OF error is as important as the definition
itself. In this paper we analyze different confidence measures and point out their advantages and limitations for their use in real world settings. We also explore the agreement with current tools for their evaluation of confidence measures performance. |
|
| |
Address |
Lisboa; January 2014 |
|
| |
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 |
VISAPP |
|
| |
Notes |
IAM; ADAS; 600.044; 600.060; 600.057; 601.145; 600.076; 600.075 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ MGM2014 |
Serial |
2432 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Jiaolong Xu; Sebastian Ramos;David Vazquez; Antonio Lopez |
|
| |
Title |
Cost-sensitive Structured SVM for Multi-category Domain Adaptation |
Type |
Conference Article |
| |
Year |
2014 |
Publication |
22nd International Conference on Pattern Recognition |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
3886 - 3891 |
|
| |
Keywords |
Domain Adaptation; Pedestrian Detection |
|
| |
Abstract |
Domain adaptation addresses the problem of accuracy drop that a classifier may suffer when the training data (source domain) and the testing data (target domain) are drawn from different distributions. In this work, we focus on domain adaptation for structured SVM (SSVM). We propose a cost-sensitive domain adaptation method for SSVM, namely COSS-SSVM. In particular, during the re-training of an adapted classifier based on target and source data, the idea that we explore consists in introducing a non-zero cost even for correctly classified source domain samples. Eventually, we aim to learn a more targetoriented classifier by not rewarding (zero loss) properly classified source-domain training samples. We assess the effectiveness of COSS-SSVM on multi-category object recognition. |
|
| |
Address |
Stockholm; Sweden; August 2014 |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
IEEE |
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
1051-4651 |
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
ICPR |
|
| |
Notes |
ADAS; 600.057; 600.054; 601.217; 600.076 |
Approved |
no |
|
| |
Call Number |
ADAS @ adas @ XRV2014a |
Serial |
2434 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Katerine Diaz; Francesc J. Ferri; W. Diaz |
|
| |
Title |
Fast Approximated Discriminative Common Vectors using rank-one SVD updates |
Type |
Conference Article |
| |
Year |
2013 |
Publication |
20th International Conference On Neural Information Processing |
Abbreviated Journal |
|
|
| |
Volume |
8228 |
Issue |
III |
Pages |
368-375 |
|
| |
Keywords |
|
|
| |
Abstract |
An efficient incremental approach to the discriminative common vector (DCV) method for dimensionality reduction and classification is presented. The proposal consists of a rank-one update along with an adaptive restriction on the rank of the null space which leads to an approximate but convenient solution. The algorithm can be implemented very efficiently in terms of matrix operations and space complexity, which enables its use in large-scale dynamic application domains. Deep comparative experimentation using publicly available high dimensional image datasets has been carried out in order to properly assess the proposed algorithm against several recent incremental formulations.
K. Diaz-Chito, F.J. Ferri, W. Diaz |
|
| |
Address |
Daegu; Korea; November 2013 |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
Springer Berlin Heidelberg |
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
0302-9743 |
ISBN |
978-3-642-42050-4 |
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
ICONIP |
|
| |
Notes |
ADAS |
Approved |
no |
|
| |
Call Number |
Admin @ si @ DFD2013 |
Serial |
2439 |
|
| 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 |
|
|
| |
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 |
