CVC Home

Publicacions CVC

Home |  Show All |  Simple Search |  Advanced Search  | Add Record  | Import
Quick Search:
151–165 of 197 records found matching your query (RSS | history):
toggle visibility Search & Display Options
Select All    Deselect All [1–10] << 11 12 13 14 >>
List View
 | 
Citations
 | 
Details
   print
  Records Links
Author Jun Wan; Guodong Guo; Sergio Escalera; Hugo Jair Escalante; Stan Z. Li edit  openurl
  Title Multi-modal Face Presentation Attach Detection Type Book Whole
  Year (up) 2020 Publication Synthesis Lectures on Computer Vision Abbreviated Journal  
  Volume 13 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 HuPBA Approved no  
  Call Number Admin @ si @ WGE2020 Serial 3440  
Permanent link to this record
 
 
Author Pau Riba edit  isbn
openurl 
  Title Distilling Structure from Imagery: Graph-based Models for the Interpretation of Document Images Type Book Whole
  Year (up) 2020 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract From its early stages, the community of Pattern Recognition and Computer Vision has considered the importance of leveraging the structural information when understanding images. Usually, graphs have been proposed as a suitable model to represent this kind of information due to their flexibility and representational power able to codify both, the components, objects, or entities and their pairwise relationship. Even though graphs have been successfully applied to a huge variety of tasks, as a result of their symbolic and relational nature, graphs have always suffered from some limitations compared to statistical approaches. Indeed, some trivial mathematical operations do not have an equivalence in the graph domain. For instance, in the core of many pattern recognition applications, there is a need to compare two objects. This operation, which is trivial when considering feature vectors defined in \(\mathbb{R}^n\), is not properly defined for graphs.


In this thesis, we have investigated the importance of the structural information from two perspectives, the traditional graph-based methods and the new advances on Geometric Deep Learning. On the one hand, we explore the problem of defining a graph representation and how to deal with it on a large scale and noisy scenario. On the other hand, Graph Neural Networks are proposed to first redefine a Graph Edit Distance methodologies as a metric learning problem, and second, to apply them in a real use case scenario for the detection of repetitive patterns which define tables in invoice documents. As experimental framework, we have validated the different methodological contributions in the domain of Document Image Analysis and Recognition.		  
  Address  
  Corporate Author Thesis Ph.D. thesis  
  Publisher Ediciones Graficas Rey Place of Publication Editor Josep Llados;Alicia Fornes  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-84-121011-6-4 Medium  
  Area Expedition Conference  
  Notes DAG; 600.121 Approved no  
  Call Number Admin @ si @ Rib20 Serial 3478  
Permanent link to this record
 
 
Author Raul Gomez edit  isbn
openurl 
  Title Exploiting the Interplay between Visual and Textual Data for Scene Interpretation Type Book Whole
  Year (up) 2020 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Machine learning experimentation under controlled scenarios and standard datasets is necessary to compare algorithms performance by evaluating all of them in the same setup. However, experimentation on how those algorithms perform on unconstrained data and applied tasks to solve real world problems is also a must to ascertain how that research can contribute to our society.
In this dissertation we experiment with the latest computer vision and natural language processing algorithms applying them to multimodal scene interpretation. Particularly, we research on how image and text understanding can be jointly exploited to address real world problems, focusing on learning from Social Media data.
We address several tasks that involve image and textual information, discuss their characteristics and offer our experimentation conclusions. First, we work on detection of scene text in images. Then, we work with Social Media posts, exploiting the captions associated to images as supervision to learn visual features, which we apply to multimodal semantic image retrieval. Subsequently, we work with geolocated Social Media images with associated tags, experimenting on how to use the tags as supervision, on location sensitive image retrieval and on exploiting location information for image tagging. Finally, we work on a specific classification problem of Social Media publications consisting on an image and a text: Multimodal hate speech classification.		  
  Address  
  Corporate Author Thesis Ph.D. thesis  
  Publisher Ediciones Graficas Rey Place of Publication Editor Dimosthenis Karatzas;Lluis Gomez;Jaume Gibert  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-84-121011-7-1 Medium  
  Area Expedition Conference  
  Notes DAG; 600.121 Approved no  
  Call Number Admin @ si @ Gom20 Serial 3479  
Permanent link to this record
 
 
Author Sounak Dey edit  isbn
openurl 
  Title Mapping between Images and Conceptual Spaces: Sketch-based Image Retrieval Type Book Whole
  Year (up) 2020 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract This thesis presents several contributions to the literature of sketch based image retrieval (SBIR). In SBIR the first challenge we face is how to map two different domains to common space for effective retrieval of images, while tackling the different levels of abstraction people use to express their notion of objects around while sketching. To this extent we first propose a cross-modal learning framework that maps both sketches and text into a joint embedding space invariant to depictive style, while preserving semantics. Then we have also investigated different query types possible to encompass people's dilema in sketching certain world objects. For this we propose an approach for multi-modal image retrieval in multi-labelled images. A multi-modal deep network architecture is formulated to jointly model sketches and text as input query modalities into a common embedding space, which is then further aligned with the image feature space. This permits encoding the object-based features and its alignment with the query irrespective of the availability of the co-occurrence of different objects in the training set.

Finally, we explore the problem of zero-shot sketch-based image retrieval (ZS-SBIR), where human sketches are used as queries to conduct retrieval of photos from unseen categories. We importantly advance prior arts by proposing a novel ZS-SBIR scenario that represents a firm step forward in its practical application. The new setting uniquely recognises two important yet often neglected challenges of practical ZS-SBIR, (i) the large domain gap between amateur sketch and photo, and (ii) the necessity for moving towards large-scale retrieval. We first contribute to the community a novel ZS-SBIR dataset, QuickDraw-Extended. We also in this dissertation pave the path to the future direction of research in this domain.		  
  Address  
  Corporate Author Thesis Ph.D. thesis  
  Publisher Ediciones Graficas Rey Place of Publication Editor Josep Llados;Umapada Pal  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-84-121011-8-8 Medium  
  Area Expedition Conference  
  Notes DAG; 600.121 Approved no  
  Call Number Admin @ si @ Dey20 Serial 3480  
Permanent link to this record
 
 
Author Marc Masana edit  isbn
openurl 
  Title Lifelong Learning of Neural Networks: Detecting Novelty and Adapting to New Domains without Forgetting Type Book Whole
  Year (up) 2020 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Computer vision has gone through considerable changes in the last decade as neural networks have come into common use. As available computational capabilities have grown, neural networks have achieved breakthroughs in many computer vision tasks, and have even surpassed human performance in others. With accuracy being so high, focus has shifted to other issues and challenges. One research direction that saw a notable increase in interest is on lifelong learning systems. Such systems should be capable of efficiently performing tasks, identifying and learning new ones, and should moreover be able to deploy smaller versions of themselves which are experts on specific tasks. In this thesis, we contribute to research on lifelong learning and address the compression and adaptation of networks to small target domains, the incremental learning of networks faced with a variety of tasks, and finally the detection of out-of-distribution samples at inference time.

We explore how knowledge can be transferred from large pretrained models to more task-specific networks capable of running on smaller devices by extracting the most relevant information. Using a pretrained model provides more robust representations and a more stable initialization when learning a smaller task, which leads to higher performance and is known as domain adaptation. However, those models are too large for certain applications that need to be deployed on devices with limited memory and computational capacity. In this thesis we show that, after performing domain adaptation, some learned activations barely contribute to the predictions of the model. Therefore, we propose to apply network compression based on low-rank matrix decomposition using the activation statistics. This results in a significant reduction of the model size and the computational cost.

Like human intelligence, machine intelligence aims to have the ability to learn and remember knowledge. However, when a trained neural network is presented with learning a new task, it ends up forgetting previous ones. This is known as catastrophic forgetting and its avoidance is studied in continual learning. The work presented in this thesis extensively surveys continual learning techniques and presents an approach to avoid catastrophic forgetting in sequential task learning scenarios. Our technique is based on using ternary masks in order to update a network to new tasks, reusing the knowledge of previous ones while not forgetting anything about them. In contrast to earlier work, our masks are applied to the activations of each layer instead of the weights. This considerably reduces the number of parameters to be added for each new task. Furthermore, the analysis on a wide range of work on incremental learning without access to the task-ID, provides insight on current state-of-the-art approaches that focus on avoiding catastrophic forgetting by using regularization, rehearsal of previous tasks from a small memory, or compensating the task-recency bias.

Neural networks trained with a cross-entropy loss force the outputs of the model to tend toward a one-hot encoded vector. This leads to models being too overly confident when presented with images or classes that were not present in the training distribution. The capacity of a system to be aware of the boundaries of the learned tasks and identify anomalies or classes which have not been learned yet is key to lifelong learning and autonomous systems. In this thesis, we present a metric learning approach to out-of-distribution detection that learns the task at hand on an embedding space.		  
  Address  
  Corporate Author Thesis Ph.D. thesis  
  Publisher Ediciones Graficas Rey Place of Publication Editor Joost Van de Weijer;Andrew Bagdanov  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-84-121011-9-5 Medium  
  Area Expedition Conference  
  Notes LAMP; 600.120 Approved no  
  Call Number Admin @ si @ Mas20 Serial 3481  
Permanent link to this record
 
 
Author Lei Kang edit  isbn
openurl 
  Title Robust Handwritten Text Recognition in Scarce Labeling Scenarios: Disentanglement, Adaptation and Generation Type Book Whole
  Year (up) 2020 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Handwritten documents are not only preserved in historical archives but also widely used in administrative documents such as cheques and claims. With the rise of the deep learning era, many state-of-the-art approaches have achieved good performance on specific datasets for Handwritten Text Recognition (HTR). However, it is still challenging to solve real use cases because of the varied handwriting styles across different writers and the limited labeled data. Thus, both explorin a more robust handwriting recognition architectures and proposing methods to diminish the gap between the source and target data in an unsupervised way are
demanded.
In this thesis, firstly, we explore novel architectures for HTR, from Sequence-to-Sequence (Seq2Seq) method with attention mechanism to non-recurrent Transformer-based method. Secondly, we focus on diminishing the performance gap between source and target data in an unsupervised way. Finally, we propose a group of generative methods for handwritten text images, which could be utilized to increase the training set to obtain a more robust recognizer. In addition, by simply modifying the generative method and joining it with a recognizer, we end up with an effective disentanglement method to distill textual content from handwriting styles so as to achieve a generalized recognition performance.
We outperform state-of-the-art HTR performances in the experimental results among different scientific and industrial datasets, which prove the effectiveness of the proposed methods. To the best of our knowledge, the non-recurrent recognizer and the disentanglement method are the first contributions in the handwriting recognition field. Furthermore, we have outlined the potential research lines, which would be interesting to explore in the future.		  
  Address  
  Corporate Author Thesis Ph.D. thesis  
  Publisher Ediciones Graficas Rey Place of Publication Editor Alicia Fornes;Marçal Rusiñol;Mauricio Villegas  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-84-122714-0-9 Medium  
  Area Expedition Conference  
  Notes DAG; 600.121 Approved no  
  Call Number Admin @ si @ Kan20 Serial 3482  
Permanent link to this record
 
 
Author Manuel Carbonell edit  isbn
openurl 
  Title Neural Information Extraction from Semi-structured Documents A Type Book Whole
  Year (up) 2020 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Sectors as fintech, legaltech or insurance process an inflow of millions of forms, invoices, id documents, claims or similar every day. Together with these, historical archives provide gigantic amounts of digitized documents containing useful information that needs to be stored in machine encoded text with a meaningful structure. This procedure, known as information extraction (IE) comprises the steps of localizing and recognizing text, identifying named entities contained in it and optionally finding relationships among its elements. In this work we explore multi-task neural models at image and graph level to solve all steps in a unified way. While doing so we find benefits and limitations of these end-to-end approaches in comparison with sequential separate methods. More specifically, we first propose a method to produce textual as well as semantic labels with a unified model from handwritten text line images. We do so with the use of a convolutional recurrent neural model trained with connectionist temporal classification to predict the textual as well as semantic information encoded in the images. Secondly, motivated by the success of this approach we investigate the unification of the localization and recognition tasks of handwritten text in full pages with an end-to-end model, observing benefits in doing so. Having two models that tackle information extraction subsequent task pairs in an end-to-end to end manner, we lastly contribute with a method to put them all together in a single neural network to solve the whole information extraction pipeline in a unified way. Doing so we observe some benefits and some limitations in the approach, suggesting that in certain cases it is beneficial to train specialized models that excel at a single challenging task of the information extraction process, as it can be the recognition of named entities or the extraction of relationships between them. For this reason we lastly study the use of the recently arrived graph neural network architectures for the semantic tasks of the information extraction process, which are recognition of named entities and relation extraction, achieving promising results on the relation extraction part.  
  Address  
  Corporate Author Thesis Ph.D. thesis  
  Publisher Ediciones Graficas Rey Place of Publication Editor Alicia Fornes;Mauricio Villegas;Josep Llados  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-84-122714-1-6 Medium  
  Area Expedition Conference  
  Notes DAG; 600.121 Approved no  
  Call Number Admin @ si @ Car20 Serial 3483  
Permanent link to this record
 
 
Author Giovanni Maria Farinella; Petia Radeva; Jose Braz edit  openurl
  Title Proceedings of the 15th International Joint Conference on Computer Vision; Imaging and Computer Graphics Theory and Applications Type Book Whole
  Year (up) 2020 Publication Proceedings of the 15th International Joint Conference on Computer Vision; Imaging and Computer Graphics Theory and Applications; VISIGRAPP 2020 Abbreviated Journal  
  Volume 4 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 MILAB Approved no  
  Call Number Admin @ si @ FRB2020a Serial 3546  
Permanent link to this record
 
 
Author Giovanni Maria Farinella; Petia Radeva; Jose Braz edit  openurl
  Title Proceedings of the 15th International Joint Conference on Computer Vision; Imaging and Computer Graphics Theory and Applications Type Book Whole
  Year (up) 2020 Publication Proceedings of the 15th International Joint Conference on Computer Vision; Imaging and Computer Graphics Theory and Applications; VISIGRAPP 2020 Abbreviated Journal  
  Volume 5 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 MILAB Approved no  
  Call Number Admin @ si @ FRB2020b Serial 3547  
Permanent link to this record
 
 
Author David Aldavert edit  isbn
openurl 
  Title Efficient and Scalable Handwritten Word Spotting on Historical Documents using Bag of Visual Words Type Book Whole
  Year (up) 2021 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Word spotting can be defined as the pattern recognition tasked aimed at locating and retrieving a specific keyword within a document image collection without explicitly transcribing the whole corpus. Its use is particularly interesting when applied in scenarios where Optical Character Recognition performs poorly or can not be used at all. This thesis focuses on such a scenario, word spotting on historical handwritten documents that have been written by a single author or by multiple authors with a similar calligraphy.
This problem requires a visual signature that is robust to image artifacts, flexible to accommodate script variations and efficient to retrieve information in a rapid manner. For this, we have developed a set of word spotting methods that on their foundation use the well known Bag-of-Visual-Words (BoVW) representation. This representation has gained popularity among the document image analysis community to characterize handwritten words
in an unsupervised manner. However, most approaches on this field rely on a basic BoVW configuration and disregard complex encoding and spatial representations. We determine which BoVW configurations provide the best performance boost to a spotting system.
Then, we extend the segmentation-based word spotting, where word candidates are given a priori, to segmentation-free spotting. The proposed approach seeds the document images with overlapping word location candidates and characterizes them with a BoVW signature. Retrieval is achieved comparing the query and candidate signatures and returning the locations that provide a higher consensus. This is a simple but powerful approach that requires a more compact signature than in a segmentation-based scenario. We first
project the BoVW signature into a reduced semantic topics space and then compress it further using Product Quantizers. The resulting signature only requires a few dozen bytes, allowing us to index thousands of pages on a common desktop computer. The final system still yields a performance comparable to the state-of-the-art despite all the information loss during the compression phases.
Afterwards, we also study how to combine different modalities of information in order to create a query-by-X spotting system where, words are indexed using an information modality and queries are retrieved using another. We consider three different information modalities: visual, textual and audio. Our proposal is to create a latent feature space where features which are semantically related are projected onto the same topics. Creating thus a new feature space where information from different modalities can be compared. Later, we consider the codebook generation and descriptor encoding problem. The codebooks used to encode the BoVW signatures are usually created using an unsupervised clustering algorithm and, they require to test multiple parameters to determine which configuration is best for a certain document collection. We propose a semantic clustering algorithm which allows to estimate the best parameter from data. Since gather annotated data is costly, we use synthetically generated word images. The resulting codebook is database agnostic, i. e. a codebook that yields a good performance on document collections that use the same script. We also propose the use of an additional codebook to approximate descriptors and reduce the descriptor encoding
complexity to sub-linear.
Finally, we focus on the problem of signatures dimensionality. We propose a new symbol probability signature where each bin represents the probability that a certain symbol is present a certain location of the word image. This signature is extremely compact and combined with compression techniques can represent word images with just a few bytes per signature.		  
  Address April 2021  
  Corporate Author Thesis Ph.D. thesis  
  Publisher Ediciones Graficas Rey Place of Publication Editor Marçal Rusiñol;Josep Llados  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-84-122714-5-4 Medium  
  Area Expedition Conference  
  Notes DAG; 600.121 Approved no  
  Call Number Admin @ si @ Ald2021 Serial 3601  
Permanent link to this record
 
 
Author Josep Llados; Daniel Lopresti; Seiichi Uchida (eds) edit  doi
isbn  openurl
  Title 16th International Conference, 2021, Proceedings, Part III Type Book Whole
  Year (up) 2021 Publication Document Analysis and Recognition – ICDAR 2021 Abbreviated Journal  
  Volume 12823 Issue Pages  
  Keywords  
  Abstract This four-volume set of LNCS 12821, LNCS 12822, LNCS 12823 and LNCS 12824, constitutes the refereed proceedings of the 16th International Conference on Document Analysis and Recognition, ICDAR 2021, held in Lausanne, Switzerland in September 2021. The 182 full papers were carefully reviewed and selected from 340 submissions, and are presented with 13 competition reports.

The papers are organized into the following topical sections: document analysis for literature search, document summarization and translation, multimedia document analysis, mobile text recognition, document analysis for social good, indexing and retrieval of documents, physical and logical layout analysis, recognition of tables and formulas, and natural language processing (NLP) for document understanding.		  
  Address Lausanne, Switzerland, September 5-10, 2021  
  Corporate Author Thesis  
  Publisher Springer Cham Place of Publication Editor Josep Llados; Daniel Lopresti; Seiichi Uchida  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-3-030-86333-3 Medium  
  Area Expedition Conference ICDAR  
  Notes DAG Approved no  
  Call Number Admin @ si @ Serial 3727  
Permanent link to this record
 
 
Author Josep Llados; Daniel Lopresti; Seiichi Uchida (eds) edit  doi
isbn  openurl
  Title 16th International Conference, 2021, Proceedings, Part IV Type Book Whole
  Year (up) 2021 Publication Document Analysis and Recognition – ICDAR 2021 Abbreviated Journal  
  Volume 12824 Issue Pages  
  Keywords  
  Abstract This four-volume set of LNCS 12821, LNCS 12822, LNCS 12823 and LNCS 12824, constitutes the refereed proceedings of the 16th International Conference on Document Analysis and Recognition, ICDAR 2021, held in Lausanne, Switzerland in September 2021. The 182 full papers were carefully reviewed and selected from 340 submissions, and are presented with 13 competition reports.

The papers are organized into the following topical sections: document analysis for literature search, document summarization and translation, multimedia document analysis, mobile text recognition, document analysis for social good, indexing and retrieval of documents, physical and logical layout analysis, recognition of tables and formulas, and natural language processing (NLP) for document understanding.		  
  Address Lausanne, Switzerland, September 5-10, 2021  
  Corporate Author Thesis  
  Publisher Springer Cham Place of Publication Editor Josep Llados; Daniel Lopresti; Seiichi Uchida  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-3-030-86336-4 Medium  
  Area Expedition Conference ICDAR  
  Notes DAG Approved no  
  Call Number Admin @ si @ Serial 3728  
Permanent link to this record
 
 
Author Carola Figueroa Flores edit  isbn
openurl 
  Title Visual Saliency for Object Recognition, and Object Recognition for Visual Saliency Type Book Whole
  Year (up) 2021 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal  
  Volume Issue Pages  
  Keywords computer vision; visual saliency; fine-grained object recognition; convolutional neural networks; images classification  
  Abstract For humans, the recognition of objects is an almost instantaneous, precise and
extremely adaptable process. Furthermore, we have the innate capability to learn
new object classes from only few examples. The human brain lowers the complexity
of the incoming data by filtering out part of the information and only processing
those things that capture our attention. This, mixed with our biological predisposition to respond to certain shapes or colors, allows us to recognize in a simple
glance the most important or salient regions from an image. This mechanism can
be observed by analyzing on which parts of images subjects place attention; where
they fix their eyes when an image is shown to them. The most accurate way to
record this behavior is to track eye movements while displaying images.
Computational saliency estimation aims to identify to what extent regions or
objects stand out with respect to their surroundings to human observers. Saliency
maps can be used in a wide range of applications including object detection, image
and video compression, and visual tracking. The majority of research in the field has
focused on automatically estimating saliency maps given an input image. Instead, in
this thesis, we set out to incorporate saliency maps in an object recognition pipeline:
we want to investigate whether saliency maps can improve object recognition
results.
In this thesis, we identify several problems related to visual saliency estimation.
First, to what extent the estimation of saliency can be exploited to improve the
training of an object recognition model when scarce training data is available. To
solve this problem, we design an image classification network that incorporates
saliency information as input. This network processes the saliency map through a
dedicated network branch and uses the resulting characteristics to modulate the
standard bottom-up visual characteristics of the original image input. We will refer to this technique as saliency-modulated image classification (SMIC). In extensive
experiments on standard benchmark datasets for fine-grained object recognition,
we show that our proposed architecture can significantly improve performance,
especially on dataset with scarce training data.
Next, we address the main drawback of the above pipeline: SMIC requires an
explicit saliency algorithm that must be trained on a saliency dataset. To solve this,
we implement a hallucination mechanism that allows us to incorporate the saliency
estimation branch in an end-to-end trained neural network architecture that only
needs the RGB image as an input. A side-effect of this architecture is the estimation
of saliency maps. In experiments, we show that this architecture can obtain similar
results on object recognition as SMIC but without the requirement of ground truth
saliency maps to train the system.
Finally, we evaluated the accuracy of the saliency maps that occur as a sideeffect of object recognition. For this purpose, we use a set of benchmark datasets
for saliency evaluation based on eye-tracking experiments. Surprisingly, the estimated saliency maps are very similar to the maps that are computed from human
eye-tracking experiments. Our results show that these saliency maps can obtain
competitive results on benchmark saliency maps. On one synthetic saliency dataset
this method even obtains the state-of-the-art without the need of ever having seen
an actual saliency image for training.		  
  Address March 2021  
  Corporate Author Thesis Ph.D. thesis  
  Publisher Ediciones Graficas Rey Place of Publication Editor Joost Van de Weijer;Bogdan Raducanu  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-84-122714-4-7 Medium  
  Area Expedition Conference  
  Notes LAMP; 600.120 Approved no  
  Call Number Admin @ si @ Fig2021 Serial 3600  
Permanent link to this record
 
 
Author Gabriel Villalonga edit  isbn
openurl 
  Title Leveraging Synthetic Data to Create Autonomous Driving Perception Systems Type Book Whole
  Year (up) 2021 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Manually annotating images to develop vision models has been a major bottleneck
since computer vision and machine learning started to walk together. This has
been more evident since computer vision falls on the shoulders of data-hungry
deep learning techniques. When addressing on-board perception for autonomous
driving, the curse of data annotation is exacerbated due to the use of additional
sensors such as LiDAR. Therefore, any approach aiming at reducing such a timeconsuming and costly work is of high interest for addressing autonomous driving
and, in fact, for any application requiring some sort of artificial perception. In the
last decade, it has been shown that leveraging from synthetic data is a paradigm
worth to pursue in order to minimizing manual data annotation. The reason is
that the automatic process of generating synthetic data can also produce different
types of associated annotations (e.g. object bounding boxes for synthetic images
and LiDAR pointclouds, pixel/point-wise semantic information, etc.). Directly
using synthetic data for training deep perception models may not be the definitive
solution in all circumstances since it can appear a synth-to-real domain shift. In
this context, this work focuses on leveraging synthetic data to alleviate manual
annotation for three perception tasks related to driving assistance and autonomous
driving. In all cases, we assume the use of deep convolutional neural networks
(CNNs) to develop our perception models.
The first task addresses traffic sign recognition (TSR), a kind of multi-class
classification problem. We assume that the number of sign classes to be recognized
must be suddenly increased without having annotated samples to perform the
corresponding TSR CNN re-training. We show that leveraging synthetic samples of
such new classes and transforming them by a generative adversarial network (GAN)
trained on the known classes (i.e. without using samples from the new classes), it is
possible to re-train the TSR CNN to properly classify all the signs for a ∼ 1/4 ratio of
new/known sign classes. The second task addresses on-board 2D object detection,
focusing on vehicles and pedestrians. In this case, we assume that we receive a set
of images without the annotations required to train an object detector, i.e. without
object bounding boxes. Therefore, our goal is to self-annotate these images so
that they can later be used to train the desired object detector. In order to reach
this goal, we leverage from synthetic data and propose a semi-supervised learning
approach based on the co-training idea. In fact, we use a GAN to reduce the synthto-real domain shift before applying co-training. Our quantitative results show
that co-training and GAN-based image-to-image translation complement each
other up to allow the training of object detectors without manual annotation, and still almost reaching the upper-bound performances of the detectors trained from
human annotations. While in previous tasks we focus on vision-based perception,
the third task we address focuses on LiDAR pointclouds. Our initial goal was to
develop a 3D object detector trained on synthetic LiDAR-style pointclouds. While
for images we may expect synth/real-to-real domain shift due to differences in
their appearance (e.g. when source and target images come from different camera
sensors), we did not expect so for LiDAR pointclouds since these active sensors
factor out appearance and provide sampled shapes. However, in practice, we have
seen that it can be domain shift even among real-world LiDAR pointclouds. Factors
such as the sampling parameters of the LiDARs, the sensor suite configuration onboard the ego-vehicle, and the human annotation of 3D bounding boxes, do induce
a domain shift. We show it through comprehensive experiments with different
publicly available datasets and 3D detectors. This redirected our goal towards the
design of a GAN for pointcloud-to-pointcloud translation, a relatively unexplored
topic.
Finally, it is worth to mention that all the synthetic datasets used for these three
tasks, have been designed and generated in the context of this PhD work and will
be publicly released. Overall, we think this PhD presents several steps forward to
encourage leveraging synthetic data for developing deep perception models in the
field of driving assistance and autonomous driving.		  
  Address February 2021  
  Corporate Author Thesis Ph.D. thesis  
  Publisher Ediciones Graficas Rey Place of Publication Editor Antonio Lopez;German Ros  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-84-122714-2-3 Medium  
  Area Expedition Conference  
  Notes ADAS; 600.118 Approved no  
  Call Number Admin @ si @ Vil2021 Serial 3599  
Permanent link to this record
 
 
Author Gemma Rotger edit  isbn
openurl 
  Title Lifelike Humans: Detailed Reconstruction of Expressive Human Faces Type Book Whole
  Year (up) 2021 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Developing human-like digital characters is a challenging task since humans are used to recognizing our fellows, and find the computed generated characters inadequately humanized. To fulfill the standards of the videogame and digital film productions it is necessary to model and animate these characters the most closely to human beings. However, it is an arduous and expensive task, since many artists and specialists are required to work on a single character. Therefore, to fulfill these requirements we found an interesting option to study the automatic creation of detailed characters through inexpensive setups. In this work, we develop novel techniques to bring detailed characters by combining different aspects that stand out when developing realistic characters, skin detail, facial hairs, expressions, and microexpressions. We examine each of the mentioned areas with the aim of automatically recover each of the parts without user interaction nor training data. We study the problems for their robustness but also for the simplicity of the setup, preferring single-image with uncontrolled illumination and methods that can be easily computed with the commodity of a standard laptop. A detailed face with wrinkles and skin details is vital to develop a realistic character. In this work, we introduce our method to automatically describe facial wrinkles on the image and transfer to the recovered base face. Then we advance to facial hair recovery by resolving a fitting problem with a novel parametrization model. As of last, we develop a mapping function that allows transfer expressions and microexpressions between different meshes, which provides realistic animations to our detailed mesh. We cover all the mentioned points with the focus on key aspects as (i) how to describe skin wrinkles in a simple and straightforward manner, (ii) how to recover 3D from 2D detections, (iii) how to recover and model facial hair from 2D to 3D, (iv) how to transfer expressions between models holding both skin detail and facial hair, (v) how to perform all the described actions without training data nor user interaction. In this work, we present our proposals to solve these aspects with an efficient and simple setup. We validate our work with several datasets both synthetic and real data, prooving remarkable results even in challenging cases as occlusions as glasses, thick beards, and indeed working with different face topologies like single-eyed cyclops.  
  Address  
  Corporate Author Thesis Ph.D. thesis  
  Publisher Ediciones Graficas Rey Place of Publication Editor Felipe Lumbreras;Antonio Agudo  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-84-122714-3-0 Medium  
  Area Expedition Conference  
  Notes ADAS Approved no  
  Call Number Admin @ si @ Rot2021 Serial 3513  
Permanent link to this record
Select All    Deselect All [1–10] << 11 12 13 14 >>
List View
 | 
Citations
 | 
Details
   print
toggle visibility
Save Citations:
Export Records:
Home SQL Search  |  Library Search  |  Show Record  |  Extract Citations Help