Home [201–210] << 211 212 213 214 215 216 217 218 219 220 >> [221–228]
List View
 | 
Citations
 | 
Details
   web
Records
Author Sergio Escalera; Xavier Baro; Oriol Pujol; Jordi Vitria; Petia Radeva
Title (up) Traffic-Sign Recognition Systems Type Book Whole
Year 2011 Publication SpringerBriefs in Computer Science Abbreviated Journal
Volume Issue Pages 5-13
Keywords
Abstract
Address
Corporate Author Thesis
Publisher Springer London Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-1-4471-2244-9 Medium
Area Expedition Conference
Notes MILAB; OR;HuPBA;MV Approved no
Call Number Admin @ si @ EBP2011 Serial 1801
Permanent link to this record
 
 
Author Jiaolong Xu; Peng Wang; Heng Yang; Antonio Lopez
Title (up) 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 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 Antonio Lopez; Gabriel Villalonga; Laura Sellart; German Ros; David Vazquez; Jiaolong Xu; Javier Marin; Azadeh S. Mozafari
Title (up) Training my car to see using virtual worlds Type Journal Article
Year 2017 Publication Image and Vision Computing Abbreviated Journal IMAVIS
Volume 38 Issue Pages 102-118
Keywords
Abstract Computer vision technologies are at the core of different advanced driver assistance systems (ADAS) and will play a key role in oncoming autonomous vehicles too. One of the main challenges for such technologies is to perceive the driving environment, i.e. to detect and track relevant driving information in a reliable manner (e.g. pedestrians in the vehicle route, free space to drive through). Nowadays it is clear that machine learning techniques are essential for developing such a visual perception for driving. In particular, the standard working pipeline consists of collecting data (i.e. on-board images), manually annotating the data (e.g. drawing bounding boxes around pedestrians), learning a discriminative data representation taking advantage of such annotations (e.g. a deformable part-based model, a deep convolutional neural network), and then assessing the reliability of such representation with the acquired data. In the last two decades most of the research efforts focused on representation learning (first, designing descriptors and learning classifiers; later doing it end-to-end). Hence, collecting data and, especially, annotating it, is essential for learning good representations. While this has been the case from the very beginning, only after the disruptive appearance of deep convolutional neural networks that it became a serious issue due to their data hungry nature. In this context, the problem is that manual data annotation is a tiresome work prone to errors. Accordingly, in the late 00’s we initiated a research line consisting of training visual models using photo-realistic computer graphics, especially focusing on assisted and autonomous driving. In this paper, we summarize such a work and show how it has become a new tendency with increasing acceptance.
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 ADAS; 600.118 Approved no
Call Number Admin @ si @ LVS2017 Serial 2985
Permanent link to this record
 
 
Author Ekta Vats; Anders Hast; Alicia Fornes
Title (up) Training-Free and Segmentation-Free Word Spotting using Feature Matching and Query Expansion Type Conference Article
Year 2019 Publication 15th International Conference on Document Analysis and Recognition Abbreviated Journal
Volume Issue Pages 1294-1299
Keywords Word spotting; Segmentation-free; Trainingfree; Query expansion; Feature matching
Abstract Historical handwritten text recognition is an interesting yet challenging problem. In recent times, deep learning based methods have achieved significant performance in handwritten text recognition. However, handwriting recognition using deep learning needs training data, and often, text must be previously segmented into lines (or even words). These limitations constrain the application of HTR techniques in document collections, because training data or segmented words are not always available. Therefore, this paper proposes a training-free and segmentation-free word spotting approach that can be applied in unconstrained scenarios. The proposed word spotting framework is based on document query word expansion and relaxed feature matching algorithm, which can easily be parallelised. Since handwritten words posses distinct shape and characteristics, this work uses a combination of different keypoint detectors
and Fourier-based descriptors to obtain a sufficient degree of relaxed matching. The effectiveness of the proposed method is empirically evaluated on well-known benchmark datasets using standard evaluation measures. The use of informative features along with query expansion significantly contributed in efficient performance of the proposed method.
Address Sydney; Australia; September 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 ICDAR
Notes DAG; 600.140; 600.121 Approved no
Call Number Admin @ si @ VHF2019 Serial 3356
Permanent link to this record
 
 
Author Mikhail Mozerov; Ariel Amato; Xavier Roca; Jordi Gonzalez
Title (up) Trajectory Occlusion Handling with Multiple View Distance Minimisation Clustering Type Journal
Year 2008 Publication Optical Engineering, vol. 47(04)04702, DOI:10.11781.2909665 Abbreviated Journal
Volume Issue Pages
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 ISE Approved no
Call Number ISE @ ise @ MAR2008c Serial 970
Permanent link to this record
 
 
Author Pau Baiget; Carles Fernandez; Xavier Roca; Jordi Gonzalez
Title (up) Trajectory-Based Abnormality Categorization for Learning Route Patterns in Surveillance Type Book Chapter
Year 2012 Publication Detection and Identification of Rare Audiovisual Cues, Studies in Computational Intelligence Abbreviated Journal
Volume 384 Issue 3 Pages 87-95
Keywords
Abstract The recognition of abnormal behaviors in video sequences has raised as a hot topic in video understanding research. Particularly, an important challenge resides on automatically detecting abnormality. However, there is no convention about the types of anomalies that training data should derive. In surveillance, these are typically detected when new observations differ substantially from observed, previously learned behavior models, which represent normality. This paper focuses on properly defining anomalies within trajectory analysis: we propose a hierarchical representation conformed by Soft, Intermediate, and Hard Anomaly, which are identified from the extent and nature of deviation from learned models. Towards this end, a novel Gaussian Mixture Model representation of learned route patterns creates a probabilistic map of the image plane, which is applied to detect and classify anomalies in real-time. Our method overcomes limitations of similar existing approaches, and performs correctly even when the tracking is affected by different sources of noise. The reliability of our approach is demonstrated experimentally.
Address
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1860-949X ISBN 978-3-642-24033-1 Medium
Area Expedition Conference
Notes ISE Approved no
Call Number Admin @ si @ BFR2012 Serial 2062
Permanent link to this record
 
 
Author Andreas Fischer; Volkmar Frinken; Alicia Fornes; Horst Bunke
Title (up) Transcription Alignment of Latin Manuscripts Using Hidden Markov Models Type Conference Article
Year 2011 Publication Proceedings of the 2011 Workshop on Historical Document Imaging and Processing Abbreviated Journal
Volume Issue Pages 29-36
Keywords
Abstract Transcriptions of historical documents are a valuable source for extracting labeled handwriting images that can be used for training recognition systems. In this paper, we introduce the Saint Gall database that includes images as well as the transcription of a Latin manuscript from the 9th century written in Carolingian script. Although the available transcription is of high quality for a human reader, the spelling of the words is not accurate when compared with the handwriting image. Hence, the transcription poses several challenges for alignment regarding, e.g., line breaks, abbreviations, and capitalization. We propose an alignment system based on character Hidden Markov Models that can cope with these challenges and efficiently aligns complete document pages. On the Saint Gall database, we demonstrate that a considerable alignment accuracy can be achieved, even with weakly trained character models.
Address
Corporate Author Thesis
Publisher ACM 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 HIP
Notes DAG Approved no
Call Number Admin @ si @ FFF2011b Serial 1824
Permanent link to this record
 
 
Author Alicia Fornes; Beata Megyesi; Joan Mas
Title (up) Transcription of Encoded Manuscripts with Image Processing Techniques Type Conference Article
Year 2017 Publication Digital Humanities Conference Abbreviated Journal
Volume Issue Pages 441-443
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 DH
Notes DAG; 600.097; 600.121 Approved no
Call Number Admin @ si @ FMM2017 Serial 3061
Permanent link to this record
 
 
Author Francesc Net; Marc Folia; Pep Casals; Lluis Gomez
Title (up) Transductive Learning for Near-Duplicate Image Detection in Scanned Photo Collections Type Conference Article
Year 2023 Publication 17th International Conference on Document Analysis and Recognition Abbreviated Journal
Volume 14191 Issue Pages 3-17
Keywords Image deduplication; Near-duplicate images detection; Transductive Learning; Photographic Archives; Deep Learning
Abstract This paper presents a comparative study of near-duplicate image detection techniques in a real-world use case scenario, where a document management company is commissioned to manually annotate a collection of scanned photographs. Detecting duplicate and near-duplicate photographs can reduce the time spent on manual annotation by archivists. This real use case differs from laboratory settings as the deployment dataset is available in advance, allowing the use of transductive learning. We propose a transductive learning approach that leverages state-of-the-art deep learning architectures such as convolutional neural networks (CNNs) and Vision Transformers (ViTs). Our approach involves pre-training a deep neural network on a large dataset and then fine-tuning the network on the unlabeled target collection with self-supervised learning. The results show that the proposed approach outperforms the baseline methods in the task of near-duplicate image detection in the UKBench and an in-house private dataset.
Address San Jose; CA; USA; August 2023
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference ICDAR
Notes DAG Approved no
Call Number Admin @ si @ NFC2023 Serial 3859
Permanent link to this record
 
 
Author Jorge Charco; Angel Sappa; Boris X. Vintimilla; Henry Velesaca
Title (up) Transfer Learning from Synthetic Data in the Camera Pose Estimation Problem Type Conference Article
Year 2020 Publication 15th International Conference on Computer Vision Theory and Applications Abbreviated Journal
Volume Issue Pages
Keywords
Abstract This paper presents a novel Siamese network architecture, as a variant of Resnet-50, to estimate the relative camera pose on multi-view environments. In order to improve the performance of the proposed model a transfer learning strategy, based on synthetic images obtained from a virtual-world, is considered. The transfer learning consists of first training the network using pairs of images from the virtual-world scenario
considering different conditions (i.e., weather, illumination, objects, buildings, etc.); then, the learned weight
of the network are transferred to the real case, where images from real-world scenarios are considered. Experimental results and comparisons with the state of the art show both, improvements on the relative pose estimation accuracy using the proposed model, as well as further improvements when the transfer learning strategy (synthetic-world data transfer learning real-world data) is considered to tackle the limitation on the
training due to the reduced number of pairs of real-images on most of the public data sets.
Address Valletta; Malta; February 2020
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 MSIAU; 600.130; 601.349; 600.122 Approved no
Call Number Admin @ si @ CSV2020 Serial 3433
Permanent link to this record
 
 
Author Souhail Bakkali; Sanket Biswas; Zuheng Ming; Mickael Coustaty; Marçal Rusiñol; Oriol Ramos Terrades; Josep Llados
Title (up) TransferDoc: A Self-Supervised Transferable Document Representation Learning Model Unifying Vision and Language Type Miscellaneous
Year 2023 Publication Arxiv Abbreviated Journal
Volume Issue Pages
Keywords
Abstract The field of visual document understanding has witnessed a rapid growth in emerging challenges and powerful multi-modal strategies. However, they rely on an extensive amount of document data to learn their pretext objectives in a ``pre-train-then-fine-tune'' paradigm and thus, suffer a significant performance drop in real-world online industrial settings. One major reason is the over-reliance on OCR engines to extract local positional information within a document page. Therefore, this hinders the model's generalizability, flexibility and robustness due to the lack of capturing global information within a document image. We introduce TransferDoc, a cross-modal transformer-based architecture pre-trained in a self-supervised fashion using three novel pretext objectives. TransferDoc learns richer semantic concepts by unifying language and visual representations, which enables the production of more transferable models. Besides, two novel downstream tasks have been introduced for a ``closer-to-real'' industrial evaluation scenario where TransferDoc outperforms other state-of-the-art approaches.
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 DAG Approved no
Call Number Admin @ si @ BBM2023 Serial 3995
Permanent link to this record
 
 
Author Yaxing Wang; Hector Laria Mantecon; Joost Van de Weijer; Laura Lopez-Fuentes; Bogdan Raducanu
Title (up) TransferI2I: Transfer Learning for Image-to-Image Translation from Small Datasets Type Conference Article
Year 2021 Publication 19th IEEE International Conference on Computer Vision Abbreviated Journal
Volume Issue Pages 13990-13999
Keywords
Abstract Image-to-image (I2I) translation has matured in recent years and is able to generate high-quality realistic images. However, despite current success, it still faces important challenges when applied to small domains. Existing methods use transfer learning for I2I translation, but they still require the learning of millions of parameters from scratch. This drawback severely limits its application on small domains. In this paper, we propose a new transfer learning for I2I translation (TransferI2I). We decouple our learning process into the image generation step and the I2I translation step. In the first step we propose two novel techniques: source-target initialization and self-initialization of the adaptor layer. The former finetunes the pretrained generative model (e.g., StyleGAN) on source and target data. The latter allows to initialize all non-pretrained network parameters without the need of any data. These techniques provide a better initialization for the I2I translation step. In addition, we introduce an auxiliary GAN that further facilitates the training of deep I2I systems even from small datasets. In extensive experiments on three datasets, (Animal faces, Birds, and Foods), we show that we outperform existing methods and that mFID improves on several datasets with over 25 points.
Address Virtual; October 2021
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference ICCV
Notes LAMP; 600.147; 602.200; 600.120 Approved no
Call Number Admin @ si @ WLW2021 Serial 3604
Permanent link to this record
 
 
Author Yaxing Wang
Title (up) Transferring and Learning Representations for Image Generation and Translation Type Book Whole
Year 2020 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Image generation is arguably one of the most attractive, compelling, and challenging tasks in computer vision. Among the methods which perform image generation, generative adversarial networks (GANs) play a key role. The most common image generation models based on GANs can be divided into two main approaches. The first one, called simply image generation takes random noise as an input and synthesizes an image which follows the same distribution as the images in the training set. The second class, which is called image-to-image translation, aims to map an image from a source domain to one that is indistinguishable from those in the target domain. Image-to-image translation methods can further be divided into paired and unpaired image-to-image translation based on whether they require paired data or not. In this thesis, we aim to address some challenges of both image generation and image-to-image generation.GANs highly rely upon having access to vast quantities of data, and fail to generate realistic images from random noise when applied to domains with few images. To address this problem, we aim to transfer knowledge from a model trained on a large dataset (source domain) to the one learned on limited data (target domain). We find that both GANs andconditional GANs can benefit from models trained on large datasets. Our experiments show that transferring the discriminator is more important than the generator. Using both the generator and discriminator results in the best performance. We found, however, that this method suffers from overfitting, since we update all parameters to adapt to the target data. We propose a novel architecture, which is tailored to address knowledge transfer to very small target domains. Our approach effectively exploreswhich part of the latent space is more related to the target domain. Additionally, the proposed method is able to transfer knowledge from multiple pretrained GANs. Although image-to-image translation has achieved outstanding performance, it still facesseveral problems. First, for translation between complex domains (such as translations between different modalities) image-to-image translation methods require paired data. We show that when only some of the pairwise translations have been seen (i.e. during training), we can infer the remaining unseen translations (where training pairs are not available). We propose a new approach where we align multiple encoders and decoders in such a way that the desired translation can be obtained by simply cascadingthe source encoder and the target decoder, even when they have not interacted during the training stage (i.e. unseen). Second, we address the issue of bias in image-to-image translation. Biased datasets unavoidably contain undesired changes, which are dueto the fact that the target dataset has a particular underlying visual distribution. We use carefully designed semantic constraints to reduce the effects of the bias. The semantic constraint aims to enforce the preservation of desired image properties. Finally, current approaches fail to generate diverse outputs or perform scalable image transfer in a single model. To alleviate this problem, we propose a scalable and diverse image-to-image translation. We employ random noise to control the diversity. The scalabitlity is determined by conditioning the domain label.computer vision, deep learning, imitation learning, adversarial generative networks, image generation, image-to-image translation.
Address January 2020
Corporate Author Thesis Ph.D. thesis
Publisher Ediciones Graficas Rey Place of Publication Editor Joost Van de Weijer;Abel Gonzalez;Luis Herranz
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-121011-5-7 Medium
Area Expedition Conference
Notes LAMP; 600.141; 600.120 Approved no
Call Number Admin @ si @ Wan2020 Serial 3397
Permanent link to this record
 
 
Author Yaxing Wang; Chenshen Wu; Luis Herranz; Joost Van de Weijer; Abel Gonzalez-Garcia; Bogdan Raducanu
Title (up) Transferring GANs: generating images from limited data Type Conference Article
Year 2018 Publication 15th European Conference on Computer Vision Abbreviated Journal
Volume 11210 Issue Pages 220-236
Keywords Generative adversarial networks; Transfer learning; Domain adaptation; Image generation
Abstract ransferring knowledge of pre-trained networks to new domains by means of fine-tuning is a widely used practice for applications based on discriminative models. To the best of our knowledge this practice has not been studied within the context of generative deep networks. Therefore, we study domain adaptation applied to image generation with generative adversarial networks. We evaluate several aspects of domain adaptation, including the impact of target domain size, the relative distance between source and target domain, and the initialization of conditional GANs. Our results show that using knowledge from pre-trained networks can shorten the convergence time and can significantly improve the quality of the generated images, especially when target data is limited. We show that these conclusions can also be drawn for conditional GANs even when the pre-trained model was trained without conditioning. Our results also suggest that density is more important than diversity and a dataset with one or few densely sampled classes is a better source model than more diverse datasets such as ImageNet or Places.
Address Munich; September 2018
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference ECCV
Notes LAMP; 600.109; 600.106; 600.120 Approved no
Call Number Admin @ si @ WWH2018a Serial 3130
Permanent link to this record
 
 
Author Hector Laria Mantecon; Yaxing Wang; Joost Van de Weijer; Bogdan Raducanu
Title (up) Transferring Unconditional to Conditional GANs With Hyper-Modulation Type Conference Article
Year 2022 Publication IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Abbreviated Journal
Volume Issue Pages
Keywords
Abstract GANs have matured in recent years and are able to generate high-resolution, realistic images. However, the computational resources and the data required for the training of high-quality GANs are enormous, and the study of transfer learning of these models is therefore an urgent topic. Many of the available high-quality pretrained GANs are unconditional (like StyleGAN). For many applications, however, conditional GANs are preferable, because they provide more control over the generation process, despite often suffering more training difficulties. Therefore, in this paper, we focus on transferring from high-quality pretrained unconditional GANs to conditional GANs. This requires architectural adaptation of the pretrained GAN to perform the conditioning. To this end, we propose hyper-modulated generative networks that allow for shared and complementary supervision. To prevent the additional weights of the hypernetwork to overfit, with subsequent mode collapse on small target domains, we introduce a self-initialization procedure that does not require any real data to initialize the hypernetwork parameters. To further improve the sample efficiency of the transfer, we apply contrastive learning in the discriminator, which effectively works on very limited batch sizes. In extensive experiments, we validate the efficiency of the hypernetworks, self-initialization and contrastive loss for knowledge transfer on standard benchmarks.
Address New Orleans; USA; June 2022
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference CVPRW
Notes LAMP; 600.147; 602.200 Approved no
Call Number LWW2022a Serial 3785
Permanent link to this record