toggle visibility Search & Display Options
Select All    Deselect All << 1 2 3 4 5 6 7 8 9 10 >> [11–20]
List View
 | 
Citations
 | 
Details
  Records Links
Author Jose Carlos Rubio; Joan Serrat; Antonio Lopez; N. Paragios edit   pdf
url  isbn
openurl 
  Title Image Contextual Representation and Matching through Hierarchies and Higher Order Graphs Type Conference Article
  Year 2012 Publication 21st International Conference on Pattern Recognition Abbreviated Journal  
  Volume Issue Pages (down) 2664 - 2667  
  Keywords  
  Abstract We present a region matching algorithm which establishes correspondences between regions from two segmented images. An abstract graph-based representation conceals the image in a hierarchical graph, exploiting the scene properties at two levels. First, the similarity and spatial consistency of the image semantic objects is encoded in a graph of commute times. Second, the cluttered regions of the semantic objects are represented with a shape descriptor. Many-to-many matching of regions is specially challenging due to the instability of the segmentation under slight image changes, and we explicitly handle it through high order potentials. We demonstrate the matching approach applied to images of world famous buildings, captured under different conditions, showing the robustness of our method to large variations in illumination and viewpoint.  
  Address Tsukuba Science City, Japan  
  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 1051-4651 ISBN 978-1-4673-2216-4 Medium  
  Area Expedition Conference ICPR  
  Notes ADAS Approved no  
  Call Number Admin @ si @ RSL2012a; Serial 2032  
Permanent link to this record
 
 
Author Cesar de Souza; Adrien Gaidon; Yohann Cabon; Antonio Lopez edit   pdf
doi  openurl
  Title Procedural Generation of Videos to Train Deep Action Recognition Networks Type Conference Article
  Year 2017 Publication 30th IEEE Conference on Computer Vision and Pattern Recognition Abbreviated Journal  
  Volume Issue Pages (down) 2594-2604  
  Keywords  
  Abstract Deep learning for human action recognition in videos is making significant progress, but is slowed down by its dependency on expensive manual labeling of large video collections. In this work, we investigate the generation of synthetic training data for action recognition, as it has recently shown promising results for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation and other computer graphics techniques of modern game engines. We generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for ”Procedural Human Action Videos”. It contains a total of 39, 982 videos, with more than 1, 000 examples for each action of 35 categories. Our approach is not limited to existing motion capture sequences, and we procedurally define 14 synthetic actions. We introduce a deep multi-task representation learning architecture to mix synthetic and real videos, even if the action categories differ. Our experiments on the UCF101 and HMDB51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance, significantly
outperforming fine-tuning state-of-the-art unsupervised generative models of videos.		  
  Address Honolulu; Hawaii; July 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 CVPR  
  Notes ADAS; 600.076; 600.085; 600.118 Approved no  
  Call Number Admin @ si @ SGC2017 Serial 3051  
Permanent link to this record
 
 
Author Javier Marin; David Vazquez; Antonio Lopez; Jaume Amores; Bastian Leibe edit   pdf
doi  openurl
  Title Random Forests of Local Experts for Pedestrian Detection Type Conference Article
  Year 2013 Publication 15th IEEE International Conference on Computer Vision Abbreviated Journal  
  Volume Issue Pages (down) 2592 - 2599  
  Keywords ADAS; Random Forest; Pedestrian Detection  
  Abstract Pedestrian detection is one of the most challenging tasks in computer vision, and has received a lot of attention in the last years. Recently, some authors have shown the advantages of using combinations of part/patch-based detectors in order to cope with the large variability of poses and the existence of partial occlusions. In this paper, we propose a pedestrian detection method that efficiently combines multiple local experts by means of a Random Forest ensemble. The proposed method works with rich block-based representations such as HOG and LBP, in such a way that the same features are reused by the multiple local experts, so that no extra computational cost is needed with respect to a holistic method. Furthermore, we demonstrate how to integrate the proposed approach with a cascaded architecture in order to achieve not only high accuracy but also an acceptable efficiency. In particular, the resulting detector operates at five frames per second using a laptop machine. We tested the proposed method with well-known challenging datasets such as Caltech, ETH, Daimler, and INRIA. The method proposed in this work consistently ranks among the top performers in all the datasets, being either the best method or having a small difference with the best one.  
  Address Sydney; Australia; December 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 1550-5499 ISBN Medium  
  Area Expedition Conference ICCV  
  Notes ADAS; 600.057; 600.054 Approved no  
  Call Number ADAS @ adas @ MVL2013 Serial 2333  
Permanent link to this record
 
 
Author Victor Vaquero; German Ros; Francesc Moreno-Noguer; Antonio Lopez; Alberto Sanfeliu edit   pdf
doi  openurl
  Title Joint coarse-and-fine reasoning for deep optical flow Type Conference Article
  Year 2017 Publication 24th International Conference on Image Processing Abbreviated Journal  
  Volume Issue Pages (down) 2558-2562  
  Keywords  
  Abstract We propose a novel representation for dense pixel-wise estimation tasks using CNNs that boosts accuracy and reduces training time, by explicitly exploiting joint coarse-and-fine reasoning. The coarse reasoning is performed over a discrete classification space to obtain a general rough solution, while the fine details of the solution are obtained over a continuous regression space. In our approach both components are jointly estimated, which proved to be beneficial for improving estimation accuracy. Additionally, we propose a new network architecture, which combines coarse and fine components by treating the fine estimation as a refinement built on top of the coarse solution, and therefore adding details to the general prediction. We apply our approach to the challenging problem of optical flow estimation and empirically validate it against state-of-the-art CNN-based solutions trained from scratch and tested on large optical flow datasets.  
  Address Beijing; China; September 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 ICIP  
  Notes ADAS; 600.118 Approved no  
  Call Number Admin @ si @ VRM2017 Serial 2898  
Permanent link to this record
 
 
Author Miguel Oliveira; L. Seabra Lopes; G. Hyun Lim; S. Hamidreza Kasaei; Angel Sappa; A. Tom edit   pdf
url  doi
openurl 
  Title Concurrent Learning of Visual Codebooks and Object Categories in Openended Domains Type Conference Article
  Year 2015 Publication International Conference on Intelligent Robots and Systems Abbreviated Journal  
  Volume Issue Pages (down) 2488 - 2495  
  Keywords Visual Learning; Computer Vision; Autonomous Agents  
  Abstract In open-ended domains, robots must continuously learn new object categories. When the training sets are created offline, it is not possible to ensure their representativeness with respect to the object categories and features the system will find when operating online. In the Bag of Words model, visual codebooks are constructed from training sets created offline. This might lead to non-discriminative visual words and, as a consequence, to poor recognition performance. This paper proposes a visual object recognition system which concurrently learns in an incremental and online fashion both the visual object category representations as well as the codebook words used to encode them. The codebook is defined using Gaussian Mixture Models which are updated using new object views. The approach contains similarities with the human visual object recognition system: evidence suggests that the development of recognition capabilities occurs on multiple levels and is sustained over large periods of time. Results show that the proposed system with concurrent learning of object categories and codebooks is capable of learning more categories, requiring less examples, and with similar accuracies, when compared to the classical Bag of Words approach using offline constructed codebooks.  
  Address Hamburg; Germany; October 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 IROS  
  Notes ADAS; 600.076 Approved no  
  Call Number Admin @ si @ OSL2015 Serial 2664  
Permanent link to this record
 
 
Author Jiaolong Xu; Peng Wang; Heng Yang; Antonio Lopez edit   pdf
url  doi
openurl 
  Title Training a Binary Weight Object Detector by Knowledge Transfer for Autonomous Driving Type Conference Article
  Year 2019 Publication IEEE International Conference on Robotics and Automation Abbreviated Journal  
  Volume Issue Pages (down) 2379-2384  
  Keywords  
  Abstract Autonomous driving has harsh requirements of small model size and energy efficiency, in order to enable the embedded system to achieve real-time on-board object detection. Recent deep convolutional neural network based object detectors have achieved state-of-the-art accuracy. However, such models are trained with numerous parameters and their high computational costs and large storage prohibit the deployment to memory and computation resource limited systems. Low-precision neural networks are popular techniques for reducing the computation requirements and memory footprint. Among them, binary weight neural network (BWN) is the extreme case which quantizes the float-point into just bit. BWNs are difficult to train and suffer from accuracy deprecation due to the extreme low-bit representation. To address this problem, we propose a knowledge transfer (KT) method to aid the training of BWN using a full-precision teacher network. We built DarkNet-and MobileNet-based binary weight YOLO-v2 detectors and conduct experiments on KITTI benchmark for car, pedestrian and cyclist detection. The experimental results show that the proposed method maintains high detection accuracy while reducing the model size of DarkNet-YOLO from 257 MB to 8.8 MB and MobileNet-YOLO from 193 MB to 7.9 MB.  
  Address Montreal; Canada; May 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 ICRA  
  Notes ADAS; 600.124; 600.116; 600.118 Approved no  
  Call Number Admin @ si @ XWY2018 Serial 3182  
Permanent link to this record
 
 
Author Victor Campmany; Sergio Silva; Antonio Espinosa; Juan Carlos Moure; David Vazquez; Antonio Lopez edit   pdf
url  openurl
  Title GPU-based pedestrian detection for autonomous driving Type Conference Article
  Year 2016 Publication 16th International Conference on Computational Science Abbreviated Journal  
  Volume 80 Issue Pages (down) 2377-2381  
  Keywords Pedestrian detection; Autonomous Driving; CUDA  
  Abstract We propose a real-time pedestrian detection system for the embedded Nvidia Tegra X1 GPU-CPU hybrid platform. The pipeline is composed by the following state-of-the-art algorithms: Histogram of Local Binary Patterns (LBP) and Histograms of Oriented Gradients (HOG) features extracted from the input image; Pyramidal Sliding Window technique for foreground segmentation; and Support Vector Machine (SVM) for classification. Results show a 8x speedup in the target Tegra X1 platform and a better performance/watt ratio than desktop CUDA platforms in study.  
  Address San Diego; CA; USA; June 2016  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICCS  
  Notes ADAS; 600.085; 600.082; 600.076 Approved no  
  Call Number ADAS @ adas @ CSE2016 Serial 2741  
Permanent link to this record
 
 
Author Gemma Roig; Xavier Boix; R. de Nijs; Sebastian Ramos; K. Kühnlenz; Luc Van Gool edit   pdf
doi  openurl
  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 (down) 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 Xialei Liu; Marc Masana; Luis Herranz; Joost Van de Weijer; Antonio Lopez; Andrew Bagdanov edit   pdf
doi  openurl
  Title Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting Type Conference Article
  Year 2018 Publication 24th International Conference on Pattern Recognition Abbreviated Journal  
  Volume Issue Pages (down) 2262-2268  
  Keywords  
  Abstract In this paper we propose an approach to avoiding catastrophic forgetting in sequential task learning scenarios. Our technique is based on a network reparameterization that approximately diagonalizes the Fisher Information Matrix of the network parameters. This reparameterization takes the form of
a factorized rotation of parameter space which, when used in conjunction with Elastic Weight Consolidation (which assumes a diagonal Fisher Information Matrix), leads to significantly better performance on lifelong learning of sequential tasks. Experimental results on the MNIST, CIFAR-100, CUB-200 and
Stanford-40 datasets demonstrate that we significantly improve the results of standard elastic weight consolidation, and that we obtain competitive results when compared to the state-of-the-art in lifelong learning without forgetting.		  
  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 ICPR  
  Notes LAMP; ADAS; 601.305; 601.109; 600.124; 600.106; 602.200; 600.120; 600.118 Approved no  
  Call Number Admin @ si @ LMH2018 Serial 3160  
Permanent link to this record
 
 
Author Akhil Gurram; Onay Urfalioglu; Ibrahim Halfaoui; Fahd Bouzaraa; Antonio Lopez edit   pdf
doi  openurl
  Title Monocular Depth Estimation by Learning from Heterogeneous Datasets Type Conference Article
  Year 2018 Publication IEEE Intelligent Vehicles Symposium Abbreviated Journal  
  Volume Issue Pages (down) 2176 - 2181  
  Keywords  
  Abstract Depth estimation provides essential information to perform autonomous driving and driver assistance. Especially, Monocular Depth Estimation is interesting from a practical point of view, since using a single camera is cheaper than many other options and avoids the need for continuous calibration strategies as required by stereo-vision approaches. State-of-the-art methods for Monocular Depth Estimation are based on Convolutional Neural Networks (CNNs). A promising line of work consists of introducing additional semantic information about the traffic scene when training CNNs for depth estimation. In practice, this means that the depth data used for CNN training is complemented with images having pixel-wise semantic labels, which usually are difficult to annotate (eg crowded urban images). Moreover, so far it is common practice to assume that the same raw training data is associated with both types of ground truth, ie, depth and semantic labels. The main contribution of this paper is to show that this hard constraint can be circumvented, ie, that we can train CNNs for depth estimation by leveraging the depth and semantic information coming from heterogeneous datasets. In order to illustrate the benefits of our approach, we combine KITTI depth and Cityscapes semantic segmentation datasets, outperforming state-of-the-art results on Monocular Depth Estimation.  
  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 IV  
  Notes ADAS; 600.124; 600.116; 600.118 Approved no  
  Call Number Admin @ si @ GUH2018 Serial 3183  
Permanent link to this record
Select All    Deselect All << 1 2 3 4 5 6 7 8 9 10 >> [11–20]
List View
 | 
Citations
 | 
Details
toggle visibility
Save Citations:
Export Records: