Home [1–10] << 11 12 13 >>
List View
 | 
Citations
 | 
Details
   web
Records Links
Author Ivet Rafegas; Maria Vanrell edit   pdf
openurl 
Title Color spaces emerging from deep convolutional networks Type Conference Article
Year 2016 Publication 24th Color and Imaging Conference Abbreviated Journal  
Volume Issue Pages 225-230  
Keywords  
Abstract Award for the best interactive session
Defining color spaces that provide a good encoding of spatio-chromatic properties of color surfaces is an open problem in color science [8, 22]. Related to this, in computer vision the fusion of color with local image features has been studied and evaluated [16]. In human vision research, the cells which are selective to specific color hues along the visual pathway are also a focus of attention [7, 14]. In line with these research aims, in this paper we study how color is encoded in a deep Convolutional Neural Network (CNN) that has been trained on more than one million natural images for object recognition. These convolutional nets achieve impressive performance in computer vision, and rival the representations in human brain. In this paper we explore how color is represented in a CNN architecture that can give some intuition about efficient spatio-chromatic representations. In convolutional layers the activation of a neuron is related to a spatial filter, that combines spatio-chromatic representations. We use an inverted version of it to explore the properties. Using a series of unsupervised methods we classify different type of neurons depending on the color axes they define and we propose an index of color-selectivity of a neuron. We estimate the main color axes that emerge from this trained net and we prove that colorselectivity of neurons decreases from early to deeper layers.		  
Address San Diego; USA; November 2016  
Corporate Author (up) 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 CIC  
Notes CIC Approved no  
Call Number Admin @ si @ RaV2016a Serial 2894  
Permanent link to this record
 
 
Author Ivet Rafegas; Maria Vanrell edit  openurl
Title Colour Visual Coding in trained Deep Neural Networks Type Abstract
Year 2016 Publication European Conference on Visual Perception Abbreviated Journal  
Volume Issue Pages  
Keywords  
Abstract  
Address Barcelona; Spain; August 2016  
Corporate Author (up) Thesis  
Publisher Place of Publication Editor  
Language Summary Language Original Title  
Series Editor Series Title Abbreviated Series Title  
Series Volume Series Issue Edition  
ISSN ISBN Medium  
Area Expedition Conference ECVP  
Notes CIC Approved no  
Call Number Admin @ si @ RaV2016b Serial 2895  
Permanent link to this record
 
 
Author Ivet Rafegas; Maria Vanrell edit   pdf
openurl 
Title Color representation in CNNs: parallelisms with biological vision Type Conference Article
Year 2017 Publication ICCV Workshop on Mutual Benefits ofr Cognitive and Computer Vision Abbreviated Journal  
Volume Issue Pages  
Keywords  
Abstract Convolutional Neural Networks (CNNs) trained for object recognition tasks present representational capabilities approaching to primate visual systems [1]. This provides a computational framework to explore how image features
are efficiently represented. Here, we dissect a trained CNN
[2] to study how color is represented. We use a classical methodology used in physiology that is measuring index of selectivity of individual neurons to specific features. We use ImageNet Dataset [20] images and synthetic versions
of them to quantify color tuning properties of artificial neurons to provide a classification of the network population.
We conclude three main levels of color representation showing some parallelisms with biological visual systems: (a) a decomposition in a circular hue space to represent single color regions with a wider hue sampling beyond the first
layer (V2), (b) the emergence of opponent low-dimensional spaces in early stages to represent color edges (V1); and (c) a strong entanglement between color and shape patterns representing object-parts (e.g. wheel of a car), objectshapes (e.g. faces) or object-surrounds configurations (e.g. blue sky surrounding an object) in deeper layers (V4 or IT).		  
Address Venice; Italy; October 2017  
Corporate Author (up) 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-MBCC  
Notes CIC; 600.087; 600.051 Approved no  
Call Number Admin @ si @ RaV2017 Serial 2984  
Permanent link to this record
 
 
Author Ivet Rafegas edit  isbn
openurl 
Title Color in Visual Recognition: from flat to deep representations and some biological parallelisms Type Book Whole
Year 2017 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal  
Volume Issue Pages  
Keywords  
Abstract Visual recognition is one of the main problems in computer vision that attempts to solve image understanding by deciding what objects are in images. This problem can be computationally solved by using relevant sets of visual features, such as edges, corners, color or more complex object parts. This thesis contributes to how color features have to be represented for recognition tasks.

Image features can be extracted following two different approaches. A first approach is defining handcrafted descriptors of images which is then followed by a learning scheme to classify the content (named flat schemes in Kruger et al. (2013). In this approach, perceptual considerations are habitually used to define efficient color features. Here we propose a new flat color descriptor based on the extension of color channels to boost the representation of spatio-chromatic contrast that surpasses state-of-the-art approaches. However, flat schemes present a lack of generality far away from the capabilities of biological systems. A second approach proposes evolving these flat schemes into a hierarchical process, like in the visual cortex. This includes an automatic process to learn optimal features. These deep schemes, and more specifically Convolutional Neural Networks (CNNs), have shown an impressive performance to solve various vision problems. However, there is a lack of understanding about the internal representation obtained, as a result of automatic learning. In this thesis we propose a new methodology to explore the internal representation of trained CNNs by defining the Neuron Feature as a visualization of the intrinsic features encoded in each individual neuron. Additionally, and inspired by physiological techniques, we propose to compute different neuron selectivity indexes (e.g., color, class, orientation or symmetry, amongst others) to label and classify the full CNN neuron population to understand learned representations.

Finally, using the proposed methodology, we show an in-depth study on how color is represented on a specific CNN, trained for object recognition, that competes with primate representational abilities (Cadieu et al (2014)). We found several parallelisms with biological visual systems: (a) a significant number of color selectivity neurons throughout all the layers; (b) an opponent and low frequency representation of color oriented edges and a higher sampling of frequency selectivity in brightness than in color in 1st layer like in V1; (c) a higher sampling of color hue in the second layer aligned to observed hue maps in V2; (d) a strong color and shape entanglement in all layers from basic features in shallower layers (V1 and V2) to object and background shapes in deeper layers (V4 and IT); and (e) a strong correlation between neuron color selectivities and color dataset bias.		  
Address November 2017  
Corporate Author (up) Thesis Ph.D. thesis  
Publisher Ediciones Graficas Rey Place of Publication Editor Maria Vanrell  
Language Summary Language Original Title  
Series Editor Series Title Abbreviated Series Title  
Series Volume Series Issue Edition  
ISSN ISBN 978-84-945373-7-0 Medium  
Area Expedition Conference  
Notes CIC Approved no  
Call Number Admin @ si @ Raf2017 Serial 3100  
Permanent link to this record
 
 
Author Ivet Rafegas; Maria Vanrell edit   pdf
url  doi
openurl 
Title Color encoding in biologically-inspired convolutional neural networks Type Journal Article
Year 2018 Publication Vision Research Abbreviated Journal VR  
Volume 151 Issue Pages 7-17  
Keywords Color coding; Computer vision; Deep learning; Convolutional neural networks  
Abstract Convolutional Neural Networks have been proposed as suitable frameworks to model biological vision. Some of these artificial networks showed representational properties that rival primate performances in object recognition. In this paper we explore how color is encoded in a trained artificial network. It is performed by estimating a color selectivity index for each neuron, which allows us to describe the neuron activity to a color input stimuli. The index allows us to classify whether they are color selective or not and if they are of a single or double color. We have determined that all five convolutional layers of the network have a large number of color selective neurons. Color opponency clearly emerges in the first layer, presenting 4 main axes (Black-White, Red-Cyan, Blue-Yellow and Magenta-Green), but this is reduced and rotated as we go deeper into the network. In layer 2 we find a denser hue sampling of color neurons and opponency is reduced almost to one new main axis, the Bluish-Orangish coinciding with the dataset bias. In layers 3, 4 and 5 color neurons are similar amongst themselves, presenting different type of neurons that detect specific colored objects (e.g., orangish faces), specific surrounds (e.g., blue sky) or specific colored or contrasted object-surround configurations (e.g. blue blob in a green surround). Overall, our work concludes that color and shape representation are successively entangled through all the layers of the studied network, revealing certain parallelisms with the reported evidences in primate brains that can provide useful insight into intermediate hierarchical spatio-chromatic representations.  
Address  
Corporate Author (up) 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 CIC; 600.051; 600.087 Approved no  
Call Number Admin @ si @RaV2018 Serial 3114  
Permanent link to this record
 
 
Author Hassan Ahmed Sial; S. Sancho; Ramon Baldrich; Robert Benavente; Maria Vanrell edit   pdf
url  openurl
Title Color-based data augmentation for Reflectance Estimation Type Conference Article
Year 2018 Publication 26th Color Imaging Conference Abbreviated Journal  
Volume Issue Pages 284-289  
Keywords  
Abstract Deep convolutional architectures have shown to be successful frameworks to solve generic computer vision problems. The estimation of intrinsic reflectance from single image is not a solved problem yet. Encoder-Decoder architectures are a perfect approach for pixel-wise reflectance estimation, although it usually suffers from the lack of large datasets. Lack of data can be partially solved with data augmentation, however usual techniques focus on geometric changes which does not help for reflectance estimation. In this paper we propose a color-based data augmentation technique that extends the training data by increasing the variability of chromaticity. Rotation on the red-green blue-yellow plane of an opponent space enable to increase the training set in a coherent and sound way that improves network generalization capability for reflectance estimation. We perform some experiments on the Sintel dataset showing that our color-based augmentation increase performance and overcomes one of the state-of-the-art methods.  
Address Vancouver; November 2018  
Corporate Author (up) 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 CIC  
Notes CIC Approved no  
Call Number Admin @ si @ SSB2018a Serial 3129  
Permanent link to this record
 
 
Author Bojana Gajic; Ariel Amato; Ramon Baldrich; Carlo Gatta edit   pdf
openurl 
Title Bag of Negatives for Siamese Architectures Type Conference Article
Year 2019 Publication 30th British Machine Vision Conference Abbreviated Journal  
Volume Issue Pages  
Keywords  
Abstract Training a Siamese architecture for re-identification with a large number of identities is a challenging task due to the difficulty of finding relevant negative samples efficiently. In this work we present Bag of Negatives (BoN), a method for accelerated and improved training of Siamese networks that scales well on datasets with a very large number of identities. BoN is an efficient and loss-independent method, able to select a bag of high quality negatives, based on a novel online hashing strategy.  
Address Cardiff; United Kingdom; September 2019  
Corporate Author (up) 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 BMVC  
Notes CIC; 600.140; 600.118 Approved no  
Call Number Admin @ si @ GAB2019b Serial 3263  
Permanent link to this record
 
 
Author Ivet Rafegas; Maria Vanrell; Luis A Alexandre; G. Arias edit   pdf
url  openurl
Title Understanding trained CNNs by indexing neuron selectivity Type Journal Article
Year 2020 Publication Pattern Recognition Letters Abbreviated Journal PRL  
Volume 136 Issue Pages 318-325  
Keywords  
Abstract The impressive performance of Convolutional Neural Networks (CNNs) when solving different vision problems is shadowed by their black-box nature and our consequent lack of understanding of the representations they build and how these representations are organized. To help understanding these issues, we propose to describe the activity of individual neurons by their Neuron Feature visualization and quantify their inherent selectivity with two specific properties. We explore selectivity indexes for: an image feature (color); and an image label (class membership). Our contribution is a framework to seek or classify neurons by indexing on these selectivity properties. It helps to find color selective neurons, such as a red-mushroom neuron in layer Conv4 or class selective neurons such as dog-face neurons in layer Conv5 in VGG-M, and establishes a methodology to derive other selectivity properties. Indexing on neuron selectivity can statistically draw how features and classes are represented through layers in a moment when the size of trained nets is growing and automatic tools to index neurons can be helpful.  
Address  
Corporate Author (up) 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 CIC; 600.087; 600.140; 600.118 Approved no  
Call Number Admin @ si @ RVL2019 Serial 3310  
Permanent link to this record
 
 
Author Hassan Ahmed Sial; Ramon Baldrich; Maria Vanrell edit   pdf
url  openurl
Title Deep intrinsic decomposition trained on surreal scenes yet with realistic light effects Type Journal Article
Year 2020 Publication Journal of the Optical Society of America A Abbreviated Journal JOSA A  
Volume 37 Issue 1 Pages 1-15  
Keywords  
Abstract Estimation of intrinsic images still remains a challenging task due to weaknesses of ground-truth datasets, which either are too small or present non-realistic issues. On the other hand, end-to-end deep learning architectures start to achieve interesting results that we believe could be improved if important physical hints were not ignored. In this work, we present a twofold framework: (a) a flexible generation of images overcoming some classical dataset problems such as larger size jointly with coherent lighting appearance; and (b) a flexible architecture tying physical properties through intrinsic losses. Our proposal is versatile, presents low computation time, and achieves state-of-the-art results.  
Address  
Corporate Author (up) 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 CIC; 600.140; 600.12; 600.118 Approved no  
Call Number Admin @ si @ SBV2019 Serial 3311  
Permanent link to this record
 
 
Author Hassan Ahmed Sial; Ramon Baldrich; Maria Vanrell; Dimitris Samaras edit   pdf
openurl 
Title Light Direction and Color Estimation from Single Image with Deep Regression Type Conference Article
Year 2020 Publication London Imaging Conference Abbreviated Journal  
Volume Issue Pages  
Keywords  
Abstract We present a method to estimate the direction and color of the scene light source from a single image. Our method is based on two main ideas: (a) we use a new synthetic dataset with strong shadow effects with similar constraints to the SID dataset; (b) we define a deep architecture trained on the mentioned dataset to estimate the direction and color of the scene light source. Apart from showing good performance on synthetic images, we additionally propose a preliminary procedure to obtain light positions of the Multi-Illumination dataset, and, in this way, we also prove that our trained model achieves good performance when it is applied to real scenes.  
Address Virtual; September 2020  
Corporate Author (up) 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 LIM  
Notes CIC; 600.118; 600.140; Approved no  
Call Number Admin @ si @ SBV2020 Serial 3460  
Permanent link to this record
 
 
Author Sagnik Das; Hassan Ahmed Sial; Ke Ma; Ramon Baldrich; Maria Vanrell; Dimitris Samaras edit   pdf
openurl 
Title Intrinsic Decomposition of Document Images In-the-Wild Type Conference Article
Year 2020 Publication 31st British Machine Vision Conference Abbreviated Journal  
Volume Issue Pages  
Keywords  
Abstract Automatic document content processing is affected by artifacts caused by the shape
of the paper, non-uniform and diverse color of lighting conditions. Fully-supervised
methods on real data are impossible due to the large amount of data needed. Hence, the
current state of the art deep learning models are trained on fully or partially synthetic images. However, document shadow or shading removal results still suffer because: (a) prior methods rely on uniformity of local color statistics, which limit their application on real-scenarios with complex document shapes and textures and; (b) synthetic or hybrid datasets with non-realistic, simulated lighting conditions are used to train the models. In this paper we tackle these problems with our two main contributions. First, a physically constrained learning-based method that directly estimates document reflectance based on intrinsic image formation which generalizes to challenging illumination conditions. Second, a new dataset that clearly improves previous synthetic ones, by adding a large range of realistic shading and diverse multi-illuminant conditions, uniquely customized to deal with documents in-the-wild. The proposed architecture works in two steps. First, a white balancing module neutralizes the color of the illumination on the input image. Based on the proposed multi-illuminant dataset we achieve a good white-balancing in really difficult conditions. Second, the shading separation module accurately disentangles the shading and paper material in a self-supervised manner where only the synthetic texture is used as a weak training signal (obviating the need for very costly ground truth with disentangled versions of shading and reflectance). The proposed approach leads to significant generalization of document reflectance estimation in real scenes with challenging illumination. We extensively evaluate on the real benchmark datasets available for intrinsic image decomposition and document shadow removal tasks. Our reflectance estimation scheme, when used as a pre-processing step of an OCR pipeline, shows a 21% improvement of character error rate (CER), thus, proving the practical applicability. The data and code will be available at: https://github.com/cvlab-stonybrook/DocIIW.		  
Address Virtual; September 2020  
Corporate Author (up) 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 BMVC  
Notes CIC; 600.087; 600.140; 600.118 Approved no  
Call Number Admin @ si @ DSM2020 Serial 3461  
Permanent link to this record
 
 
Author Domicele Jonauskaite; Lucia Camenzind; C. Alejandro Parraga; Cecile N Diouf; Mathieu Mercapide Ducommun; Lauriane Müller; Melanie Norberg; Christine Mohr edit  url
doi  openurl
Title Colour-emotion associations in individuals with red-green colour blindness Type Journal Article
Year 2021 Publication PeerJ Abbreviated Journal  
Volume 9 Issue Pages e11180  
Keywords Affect; Chromotherapy; Colour cognition; Colour vision deficiency; Cross-modal correspondences; Daltonism; Deuteranopia; Dichromatic; Emotion; Protanopia.  
Abstract Colours and emotions are associated in languages and traditions. Some of us may convey sadness by saying feeling blue or by wearing black clothes at funerals. The first example is a conceptual experience of colour and the second example is an immediate perceptual experience of colour. To investigate whether one or the other type of experience more strongly drives colour-emotion associations, we tested 64 congenitally red-green colour-blind men and 66 non-colour-blind men. All participants associated 12 colours, presented as terms or patches, with 20 emotion concepts, and rated intensities of the associated emotions. We found that colour-blind and non-colour-blind men associated similar emotions with colours, irrespective of whether colours were conveyed via terms (r = .82) or patches (r = .80). The colour-emotion associations and the emotion intensities were not modulated by participants' severity of colour blindness. Hinting at some additional, although minor, role of actual colour perception, the consistencies in associations for colour terms and patches were higher in non-colour-blind than colour-blind men. Together, these results suggest that colour-emotion associations in adults do not require immediate perceptual colour experiences, as conceptual experiences are sufficient.  
Address  
Corporate Author (up) 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 CIC; LAMP; 600.120; 600.128 Approved no  
Call Number Admin @ si @ JCP2021 Serial 3564  
Permanent link to this record
 
 
Author Trevor Canham; Javier Vazquez; Elise Mathieu; Marcelo Bertalmío edit   pdf
url  doi
openurl 
Title Matching visual induction effects on screens of different size Type Journal Article
Year 2021 Publication Journal of Vision Abbreviated Journal JOV  
Volume 21 Issue 6(10) Pages 1-22  
Keywords  
Abstract In the film industry, the same movie is expected to be watched on displays of vastly different sizes, from cinema screens to mobile phones. But visual induction, the perceptual phenomenon by which the appearance of a scene region is affected by its surroundings, will be different for the same image shown on two displays of different dimensions. This phenomenon presents a practical challenge for the preservation of the artistic intentions of filmmakers, because it can lead to shifts in image appearance between viewing destinations. In this work, we show that a neural field model based on the efficient representation principle is able to predict induction effects and how, by regularizing its associated energy functional, the model is still able to represent induction but is now invertible. From this finding, we propose a method to preprocess an image in a screen–size dependent way so that its perception, in terms of visual induction, may remain constant across displays of different size. The potential of the method is demonstrated through psychophysical experiments on synthetic images and qualitative examples on natural images.  
Address  
Corporate Author (up) 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 CIC Approved no  
Call Number Admin @ si @ CVM2021 Serial 3595  
Permanent link to this record
 
 
Author Graham D. Finlayson; Javier Vazquez; Fufu Fang edit   pdf
doi  openurl
Title The Discrete Cosine Maximum Ignorance Assumption Type Conference Article
Year 2021 Publication 29th Color and Imaging Conference Abbreviated Journal  
Volume Issue Pages 13-18  
Keywords  
Abstract the performance of colour correction algorithms are dependent on the reflectance sets used. Sometimes, when the testing reflectance set is changed the ranking of colour correction algorithms also changes. To remove dependence on dataset we can
make assumptions about the set of all possible reflectances. In the Maximum Ignorance with Positivity (MIP) assumption we assume that all reflectances with per wavelength values between 0 and 1 are equally likely. A weakness in the MIP is that it fails to take into account the correlation of reflectance functions between
wavelengths (many of the assumed reflectances are, in reality, not possible).
In this paper, we take the view that the maximum ignorance assumption has merit but, hitherto it has been calculated with respect to the wrong coordinate basis. Here, we propose the Discrete Cosine Maximum Ignorance assumption (DCMI), where
all reflectances that have coordinates between max and min bounds in the Discrete Cosine Basis coordinate system are equally likely.
Here, the correlation between wavelengths is encoded and this results in the set of all plausible reflectances ’looking like’ typical reflectances that occur in nature. This said the DCMI model is also a superset of all measured reflectance sets.
Experiments show that, in colour correction, adopting the DCMI results in similar colour correction performance as using a particular reflectance set.		  
Address Virtual; November 2021  
Corporate Author (up) 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 CIC  
Notes CIC Approved no  
Call Number FVF2021 Serial 3596  
Permanent link to this record
 
 
Author Hassan Ahmed Sial edit  isbn
openurl 
Title Estimating Light Effects from a Single Image: Deep Architectures and Ground-Truth Generation Type Book Whole
Year 2021 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal  
Volume Issue Pages  
Keywords  
Abstract In this thesis, we explore how to estimate the effects of the light interacting with the scene objects from a single image. To achieve this goal, we focus on recovering intrinsic components like reflectance, shading, or light properties such as color and position using deep architectures. The success of these approaches relies on training on large and diversified image datasets. Therefore, we present several contributions on this such as: (a) a data-augmentation technique; (b) a ground-truth for an existing multi-illuminant dataset; (c) a family of synthetic datasets, SID for Surreal Intrinsic Datasets, with diversified backgrounds and coherent light conditions; and (d) a practical pipeline to create hybrid ground-truths to overcome the complexity of acquiring realistic light conditions in a massive way. In parallel with the creation of datasets, we trained different flexible encoder-decoder deep architectures incorporating physical constraints from the image formation models.

In the last part of the thesis, we apply all the previous experience to two different problems. Firstly, we create a large hybrid Doc3DShade dataset with real shading and synthetic reflectance under complex illumination conditions, that is used to train a two-stage architecture that improves the character recognition task in complex lighting conditions of unwrapped documents. Secondly, we tackle the problem of single image scene relighting by extending both, the SID dataset to present stronger shading and shadows effects, and the deep architectures to use intrinsic components to estimate new relit images.		  
Address September 2021  
Corporate Author (up) Thesis Ph.D. thesis  
Publisher IMPRIMA Place of Publication Editor Maria Vanrell;Ramon Baldrich  
Language Summary Language Original Title  
Series Editor Series Title Abbreviated Series Title  
Series Volume Series Issue Edition  
ISSN ISBN 978-84-122714-8-5 Medium  
Area Expedition Conference  
Notes CIC; Approved no  
Call Number Admin @ si @ Sia2021 Serial 3607  
Permanent link to this record
 
 
Author Yasuko Sugito; Trevor Canham; Javier Vazquez; Marcelo Bertalmio edit  url
doi  openurl
Title A Study of Objective Quality Metrics for HLG-Based HDR/WCG Image Coding Type Journal
Year 2021 Publication SMPTE Motion Imaging Journal Abbreviated Journal SMPTE  
Volume 130 Issue 4 Pages 53 - 65  
Keywords  
Abstract In this work, we study the suitability of high dynamic range, wide color gamut (HDR/WCG) objective quality metrics to assess the perceived deterioration of compressed images encoded using the hybrid log-gamma (HLG) method, which is the standard for HDR television. Several image quality metrics have been developed to deal specifically with HDR content, although in previous work we showed that the best results (i.e., better matches to the opinion of human expert observers) are obtained by an HDR metric that consists simply in applying a given standard dynamic range metric, called visual information fidelity (VIF), directly to HLG-encoded images. However, all these HDR metrics ignore the chroma components for their calculations, that is, they consider only the luminance channel. For this reason, in the current work, we conduct subjective evaluation experiments in a professional setting using compressed HDR/WCG images encoded with HLG and analyze the ability of the best HDR metric to detect perceivable distortions in the chroma components, as well as the suitability of popular color metrics (including ΔITPR , which supports parameters for HLG) to correlate with the opinion scores. Our first contribution is to show that there is a need to consider the chroma components in HDR metrics, as there are color distortions that subjects perceive but that the best HDR metric fails to detect. Our second contribution is the surprising result that VIF, which utilizes only the luminance channel, correlates much better with the subjective evaluation scores than the metrics investigated that do consider the color components.  
Address  
Corporate Author (up) 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 CIC Approved no  
Call Number SCV2021 Serial 3671  
Permanent link to this record
 
 
Author Bojana Gajic; Ariel Amato; Ramon Baldrich; Joost Van de Weijer; Carlo Gatta edit   pdf
doi  openurl
Title Area Under the ROC Curve Maximization for Metric Learning Type Conference Article
Year 2022 Publication CVPR 2022 Workshop on Efficien Deep Learning for Computer Vision (ECV 2022, 5th Edition) Abbreviated Journal  
Volume Issue Pages  
Keywords Training; Computer vision; Conferences; Area measurement; Benchmark testing; Pattern recognition  
Abstract Most popular metric learning losses have no direct relation with the evaluation metrics that are subsequently applied to evaluate their performance. We hypothesize that training a metric learning model by maximizing the area under the ROC curve (which is a typical performance measure of recognition systems) can induce an implicit ranking suitable for retrieval problems. This hypothesis is supported by previous work that proved that a curve dominates in ROC space if and only if it dominates in Precision-Recall space. To test this hypothesis, we design and maximize an approximated, derivable relaxation of the area under the ROC curve. The proposed AUC loss achieves state-of-the-art results on two large scale retrieval benchmark datasets (Stanford Online Products and DeepFashion In-Shop). Moreover, the AUC loss achieves comparable performance to more complex, domain specific, state-of-the-art methods for vehicle re-identification.  
Address New Orleans, USA; 20 June 2022  
Corporate Author (up) 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 CIC; LAMP; Approved no  
Call Number Admin @ si @ GAB2022 Serial 3700  
Permanent link to this record
 
 
Author Bojana Gajic; Ramon Baldrich edit  doi
openurl 
Title Cross-domain fashion image retrieval Type Conference Article
Year 2018 Publication CVPR 2018 Workshop on Women in Computer Vision (WiCV 2018, 4th Edition) Abbreviated Journal  
Volume Issue Pages 19500-19502  
Keywords  
Abstract Cross domain image retrieval is a challenging task that implies matching images from one domain to their pairs from another domain. In this paper we focus on fashion image retrieval, which involves matching an image of a fashion item taken by users, to the images of the same item taken in controlled condition, usually by professional photographer. When facing this problem, we have different products
in train and test time, and we use triplet loss to train the network. We stress the importance of proper training of simple architecture, as well as adapting general models to the specific task.		  
Address Salt Lake City, USA; 22 June 2018  
Corporate Author (up) 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 CIC; 600.087 Approved no  
Call Number Admin @ si @ Serial 3709  
Permanent link to this record