Home [81–90] << 91 92 93 94 95 96 97 98 99 100 >> [101–110]
List View
 | 
Citations
 | 
Details
   web
Records
Author Rafael E. Rivadeneira; Angel Sappa; Boris X. Vintimilla; Riad I. Hammoud
Title A Novel Domain Transfer-Based Approach for Unsupervised Thermal Image Super-Resolution Type Journal Article
Year 2022 Publication Sensors Abbreviated Journal SENS
Volume 22 Issue 6 Pages 2254
Keywords Thermal image super-resolution; unsupervised super-resolution; thermal images; attention module; semiregistered thermal images
Abstract This paper presents a transfer domain strategy to tackle the limitations of low-resolution thermal sensors and generate higher-resolution images of reasonable quality. The proposed technique employs a CycleGAN architecture and uses a ResNet as an encoder in the generator along with an attention module and a novel loss function. The network is trained on a multi-resolution thermal image dataset acquired with three different thermal sensors. Results report better performance benchmarking results on the 2nd CVPR-PBVS-2021 thermal image super-resolution challenge than state-of-the-art methods. The code of this work is available online.
Address (up)
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 MSIAU; Approved no
Call Number Admin @ si @ RSV2022b Serial 3688
Permanent link to this record
 
 
Author David Berga; Xavier Otazu
Title A neurodynamic model of saliency prediction in v1 Type Journal Article
Year 2022 Publication Neural Computation Abbreviated Journal NEURALCOMPUT
Volume 34 Issue 2 Pages 378-414
Keywords
Abstract Lateral connections in the primary visual cortex (V1) have long been hypothesized to be responsible for several visual processing mechanisms such as brightness induction, chromatic induction, visual discomfort, and bottom-up visual attention (also named saliency). Many computational models have been developed to independently predict these and other visual processes, but no computational model has been able to reproduce all of them simultaneously. In this work, we show that a biologically plausible computational model of lateral interactions of V1 is able to simultaneously predict saliency and all the aforementioned visual processes. Our model's architecture (NSWAM) is based on Penacchio's neurodynamic model of lateral connections of V1. It is defined as a network of firing rate neurons, sensitive to visual features such as brightness, color, orientation, and scale. We tested NSWAM saliency predictions using images from several eye tracking data sets. We show that the accuracy of predictions obtained by our architecture, using shuffled metrics, is similar to other state-of-the-art computational methods, particularly with synthetic images (CAT2000-Pattern and SID4VAM) that mainly contain low-level features. Moreover, we outperform other biologically inspired saliency models that are specifically designed to exclusively reproduce saliency. We show that our biologically plausible model of lateral connections can simultaneously explain different visual processes present in V1 (without applying any type of training or optimization and keeping the same parameterization for all the visual processes). This can be useful for the definition of a unified architecture of the primary visual cortex.
Address (up)
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 NEUROBIT; 600.128; 600.120 Approved no
Call Number Admin @ si @ BeO2022 Serial 3696
Permanent link to this record
 
 
Author Razieh Rastgoo; Kourosh Kiani; Sergio Escalera; Vassilis Athitsos; Mohammad Sabokrou
Title All You Need In Sign Language Production Type Miscellaneous
Year 2022 Publication Arxiv Abbreviated Journal
Volume Issue Pages
Keywords Sign Language Production; Sign Language Recog- nition; Sign Language Translation; Deep Learning; Survey; Deaf
Abstract Sign Language is the dominant form of communication language used in the deaf and hearing-impaired community. To make an easy and mutual communication between the hearing-impaired and the hearing communities, building a robust system capable of translating the spoken language into sign language and vice versa is fundamental.
To this end, sign language recognition and production are two necessary parts for making such a two-way system. Signlanguage recognition and production need to cope with some critical challenges. In this survey, we review recent advances in
Sign Language Production (SLP) and related areas using deep learning. To have more realistic perspectives to sign language, we present an introduction to the Deaf culture, Deaf centers, psychological perspective of sign language, the main differences between spoken language and sign language. Furthermore, we present the fundamental components of a bi-directional sign language translation system, discussing the main challenges in this area. Also, the backbone architectures and methods in SLP are briefly introduced and the proposed taxonomy on SLP is presented. Finally, a general framework for SLP and performance evaluation, and also a discussion on the recent developments, advantages, and limitations in SLP, commenting on possible lines for future research are presented.
Address (up)
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; no menciona Approved no
Call Number Admin @ si @ RKE2022c Serial 3698
Permanent link to this record
 
 
Author Y. Mori; M.Misawa; Jorge Bernal; M. Bretthauer; S.Kudo; A. Rastogi; Gloria Fernandez Esparrach
Title Artificial Intelligence for Disease Diagnosis-the Gold Standard Challenge Type Journal Article
Year 2022 Publication Gastrointestinal Endoscopy Abbreviated Journal
Volume 96 Issue 2 Pages 370-372
Keywords
Abstract
Address (up)
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 Admin @ si @ MMB2022 Serial 3701
Permanent link to this record
 
 
Author Juan Borrego-Carazo; Carles Sanchez; David Castells; Jordi Carrabina; Debora Gil
Title BronchoPose: an analysis of data and model configuration for vision-based bronchoscopy pose estimation Type Journal Article
Year 2023 Publication Computer Methods and Programs in Biomedicine Abbreviated Journal CMPB
Volume 228 Issue Pages 107241
Keywords Videobronchoscopy guiding; Deep learning; Architecture optimization; Datasets; Standardized evaluation framework; Pose estimation
Abstract Vision-based bronchoscopy (VB) models require the registration of the virtual lung model with the frames from the video bronchoscopy to provide effective guidance during the biopsy. The registration can be achieved by either tracking the position and orientation of the bronchoscopy camera or by calibrating its deviation from the pose (position and orientation) simulated in the virtual lung model. Recent advances in neural networks and temporal image processing have provided new opportunities for guided bronchoscopy. However, such progress has been hindered by the lack of comparative experimental conditions.
In the present paper, we share a novel synthetic dataset allowing for a fair comparison of methods. Moreover, this paper investigates several neural network architectures for the learning of temporal information at different levels of subject personalization. In order to improve orientation measurement, we also present a standardized comparison framework and a novel metric for camera orientation learning. Results on the dataset show that the proposed metric and architectures, as well as the standardized conditions, provide notable improvements to current state-of-the-art camera pose estimation in video bronchoscopy.
Address (up)
Corporate Author Thesis
Publisher Elsevier 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 IAM; Approved no
Call Number Admin @ si @ BSC2023 Serial 3702
Permanent link to this record
 
 
Author Jose Luis Gomez; Gabriel Villalonga; Antonio Lopez
Title Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models Type Journal Article
Year 2023 Publication Sensors – Special Issue on “Machine Learning for Autonomous Driving Perception and Prediction” Abbreviated Journal SENS
Volume 23 Issue 2 Pages 621
Keywords Domain adaptation; semi-supervised learning; Semantic segmentation; Autonomous driving
Abstract Semantic image segmentation is a central and challenging task in autonomous driving, addressed by training deep models. Since this training draws to a curse of human-based image labeling, using synthetic images with automatically generated labels together with unlabeled real-world images is a promising alternative. This implies to address an unsupervised domain adaptation (UDA) problem. In this paper, we propose a new co-training procedure for synth-to-real UDA of semantic
segmentation models. It consists of a self-training stage, which provides two domain-adapted models, and a model collaboration loop for the mutual improvement of these two models. These models are then used to provide the final semantic segmentation labels (pseudo-labels) for the real-world images. The overall
procedure treats the deep models as black boxes and drives their collaboration at the level of pseudo-labeled target images, i.e., neither modifying loss functions is required, nor explicit feature alignment. We test our proposal on standard synthetic and real-world datasets for on-board semantic segmentation. Our
procedure shows improvements ranging from ∼13 to ∼26 mIoU points over baselines, so establishing new state-of-the-art results.
Address (up)
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; no proj Approved no
Call Number Admin @ si @ GVL2023 Serial 3705
Permanent link to this record
 
 
Author Reuben Dorent; Aaron Kujawa; Marina Ivory; Spyridon Bakas; Nikola Rieke; Samuel Joutard; Ben Glocker; Jorge Cardoso; Marc Modat; Kayhan Batmanghelich; Arseniy Belkov; Maria Baldeon Calisto; Jae Won Choi; Benoit M. Dawant; Hexin Dong; Sergio Escalera; Yubo Fan; Lasse Hansen; Mattias P. Heinrich; Smriti Joshi; Victoriya Kashtanova; Hyeon Gyu Kim; Satoshi Kondo; Christian N. Kruse; Susana K. Lai-Yuen; Hao Li; Han Liu; Buntheng Ly; Ipek Oguz; Hyungseob Shin; Boris Shirokikh; Zixian Su; Guotai Wang; Jianghao Wu; Yanwu Xu; Kai Yao; Li Zhang; Sebastien Ourselin,
Title CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation Type Journal Article
Year 2023 Publication Medical Image Analysis Abbreviated Journal MIA
Volume 83 Issue Pages 102628
Keywords Domain Adaptation; Segmen tation; Vestibular Schwnannoma
Abstract Domain Adaptation (DA) has recently raised strong interests in the medical imaging community. While a large variety of DA techniques has been proposed for image segmentation, most of these techniques have been validated either on private datasets or on small publicly available datasets. Moreover, these datasets mostly addressed single-class problems. To tackle these limitations, the Cross-Modality Domain Adaptation (crossMoDA) challenge was organised in conjunction with the 24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2021). CrossMoDA is the first large and multi-class benchmark for unsupervised cross-modality DA. The challenge's goal is to segment two key brain structures involved in the follow-up and treatment planning of vestibular schwannoma (VS): the VS and the cochleas. Currently, the diagnosis and surveillance in patients with VS are performed using contrast-enhanced T1 (ceT1) MRI. However, there is growing interest in using non-contrast sequences such as high-resolution T2 (hrT2) MRI. Therefore, we created an unsupervised cross-modality segmentation benchmark. The training set provides annotated ceT1 (N=105) and unpaired non-annotated hrT2 (N=105). The aim was to automatically perform unilateral VS and bilateral cochlea segmentation on hrT2 as provided in the testing set (N=137). A total of 16 teams submitted their algorithm for the evaluation phase. The level of performance reached by the top-performing teams is strikingly high (best median Dice – VS:88.4%; Cochleas:85.7%) and close to full supervision (median Dice – VS:92.5%; Cochleas:87.7%). All top-performing methods made use of an image-to-image translation approach to transform the source-domain images into pseudo-target-domain images. A segmentation network was then trained using these generated images and the manual annotations provided for the source image.
Address (up)
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 @ DKI2023 Serial 3706
Permanent link to this record
 
 
Author Debora Gil; Aura Hernandez-Sabate; Julien Enconniere; Saryani Asmayawati; Pau Folch; Juan Borrego-Carazo; Miquel Angel Piera
Title E-Pilots: A System to Predict Hard Landing During the Approach Phase of Commercial Flights Type Journal Article
Year 2022 Publication IEEE Access Abbreviated Journal ACCESS
Volume 10 Issue Pages 7489-7503
Keywords
Abstract More than half of all commercial aircraft operation accidents could have been prevented by executing a go-around. Making timely decision to execute a go-around manoeuvre can potentially reduce overall aviation industry accident rate. In this paper, we describe a cockpit-deployable machine learning system to support flight crew go-around decision-making based on the prediction of a hard landing event.
This work presents a hybrid approach for hard landing prediction that uses features modelling temporal dependencies of aircraft variables as inputs to a neural network. Based on a large dataset of 58177 commercial flights, the results show that our approach has 85% of average sensitivity with 74% of average specificity at the go-around point. It follows that our approach is a cockpit-deployable recommendation system that outperforms existing approaches.
Address (up)
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 IAM; 600.139; 600.118; 600.145 Approved no
Call Number Admin @ si @ GHE2022 Serial 3721
Permanent link to this record
 
 
Author Mohamed Ali Souibgui; Alicia Fornes; Yousri Kessentini; Beata Megyesi
Title Few shots are all you need: A progressive learning approach for low resource handwritten text recognition Type Journal Article
Year 2022 Publication Pattern Recognition Letters Abbreviated Journal PRL
Volume 160 Issue Pages 43-49
Keywords
Abstract Handwritten text recognition in low resource scenarios, such as manuscripts with rare alphabets, is a challenging problem. In this paper, we propose a few-shot learning-based handwriting recognition approach that significantly reduces the human annotation process, by requiring only a few images of each alphabet symbols. The method consists of detecting all the symbols of a given alphabet in a textline image and decoding the obtained similarity scores to the final sequence of transcribed symbols. Our model is first pretrained on synthetic line images generated from an alphabet, which could differ from the alphabet of the target domain. A second training step is then applied to reduce the gap between the source and the target data. Since this retraining would require annotation of thousands of handwritten symbols together with their bounding boxes, we propose to avoid such human effort through an unsupervised progressive learning approach that automatically assigns pseudo-labels to the unlabeled data. The evaluation on different datasets shows that our model can lead to competitive results with a significant reduction in human effort. The code will be publicly available in the following repository: https://github.com/dali92002/HTRbyMatching
Address (up)
Corporate Author Thesis
Publisher Elsevier 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; 600.121; 600.162; 602.230 Approved no
Call Number Admin @ si @ SFK2022 Serial 3736
Permanent link to this record
 
 
Author Penny Tarling; Mauricio Cantor; Albert Clapes; Sergio Escalera
Title Deep learning with self-supervision and uncertainty regularization to count fish in underwater images Type Journal Article
Year 2022 Publication PloS One Abbreviated Journal Plos
Volume 17 Issue 5 Pages e0267759
Keywords
Abstract Effective conservation actions require effective population monitoring. However, accurately counting animals in the wild to inform conservation decision-making is difficult. Monitoring populations through image sampling has made data collection cheaper, wide-reaching and less intrusive but created a need to process and analyse this data efficiently. Counting animals from such data is challenging, particularly when densely packed in noisy images. Attempting this manually is slow and expensive, while traditional computer vision methods are limited in their generalisability. Deep learning is the state-of-the-art method for many computer vision tasks, but it has yet to be properly explored to count animals. To this end, we employ deep learning, with a density-based regression approach, to count fish in low-resolution sonar images. We introduce a large dataset of sonar videos, deployed to record wild Lebranche mullet schools (Mugil liza), with a subset of 500 labelled images. We utilise abundant unlabelled data in a self-supervised task to improve the supervised counting task. For the first time in this context, by introducing uncertainty quantification, we improve model training and provide an accompanying measure of prediction uncertainty for more informed biological decision-making. Finally, we demonstrate the generalisability of our proposed counting framework through testing it on a recent benchmark dataset of high-resolution annotated underwater images from varying habitats (DeepFish). From experiments on both contrasting datasets, we demonstrate our network outperforms the few other deep learning models implemented for solving this task. By providing an open-source framework along with training data, our study puts forth an efficient deep learning template for crowd counting aquatic animals thereby contributing effective methods to assess natural populations from the ever-increasing visual data.
Address (up)
Corporate Author Thesis
Publisher Public Library of Science 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 @ TCC2022 Serial 3743
Permanent link to this record
 
 
Author Lu Yu; Xialei Liu; Joost Van de Weijer
Title Self-Training for Class-Incremental Semantic Segmentation Type Journal Article
Year 2022 Publication IEEE Transactions on Neural Networks and Learning Systems Abbreviated Journal TNNLS
Volume Issue Pages
Keywords Class-incremental learning; Self-training; Semantic segmentation.
Abstract In class-incremental semantic segmentation, we have no access to the labeled data of previous tasks. Therefore, when incrementally learning new classes, deep neural networks suffer from catastrophic forgetting of previously learned knowledge. To address this problem, we propose to apply a self-training approach that leverages unlabeled data, which is used for rehearsal of previous knowledge. Specifically, we first learn a temporary model for the current task, and then, pseudo labels for the unlabeled data are computed by fusing information from the old model of the previous task and the current temporary model. In addition, conflict reduction is proposed to resolve the conflicts of pseudo labels generated from both the old and temporary models. We show that maximizing self-entropy can further improve results by smoothing the overconfident predictions. Interestingly, in the experiments, we show that the auxiliary data can be different from the training data and that even general-purpose, but diverse auxiliary data can lead to large performance gains. The experiments demonstrate the state-of-the-art results: obtaining a relative gain of up to 114% on Pascal-VOC 2012 and 8.5% on the more challenging ADE20K compared to previous state-of-the-art methods.
Address (up)
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 LAMP; 600.147; 611.008; Approved no
Call Number Admin @ si @ YLW2022 Serial 3745
Permanent link to this record
 
 
Author Aura Hernandez-Sabate; Jose Elias Yauri; Pau Folch; Daniel Alvarez; Debora Gil
Title EEG Dataset Collection for Mental Workload Predictions in Flight-Deck Environment Type Journal Article
Year 2024 Publication Sensors Abbreviated Journal SENS
Volume 24 Issue 4 Pages 1174
Keywords
Abstract High mental workload reduces human performance and the ability to correctly carry out complex tasks. In particular, aircraft pilots enduring high mental workloads are at high risk of failure, even with catastrophic outcomes. Despite progress, there is still a lack of knowledge about the interrelationship between mental workload and brain functionality, and there is still limited data on flight-deck scenarios. Although recent emerging deep-learning (DL) methods using physiological data have presented new ways to find new physiological markers to detect and assess cognitive states, they demand large amounts of properly annotated datasets to achieve good performance. We present a new dataset of electroencephalogram (EEG) recordings specifically collected for the recognition of different levels of mental workload. The data were recorded from three experiments, where participants were induced to different levels of workload through tasks of increasing cognition demand. The first involved playing the N-back test, which combines memory recall with arithmetical skills. The second was playing Heat-the-Chair, a serious game specifically designed to emphasize and monitor subjects under controlled concurrent tasks. The third was flying in an Airbus320 simulator and solving several critical situations. The design of the dataset has been validated on three different levels: (1) correlation of the theoretical difficulty of each scenario to the self-perceived difficulty and performance of subjects; (2) significant difference in EEG temporal patterns across the theoretical difficulties and (3) usefulness for the training and evaluation of AI models.
Address (up)
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 IAM Approved no
Call Number Admin @ si @ HYF2024 Serial 4019
Permanent link to this record
 
 
Author Arnau Baro
Title Reading Music Systems: From Deep Optical Music Recognition to Contextual Methods Type Book Whole
Year 2022 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract The transcription of sheet music into some machine-readable format can be carried out manually. However, the complexity of music notation inevitably leads to burdensome software for music score editing, which makes the whole process
very time-consuming and prone to errors. Consequently, automatic transcription
systems for musical documents represent interesting tools.
Document analysis is the subject that deals with the extraction and processing
of documents through image and pattern recognition. It is a branch of computer
vision. Taking music scores as source, the field devoted to address this task is
known as Optical Music Recognition (OMR). Typically, an OMR system takes an
image of a music score and automatically extracts its content into some symbolic
structure such as MEI or MusicXML.
In this dissertation, we have investigated different methods for recognizing a
single staff section (e.g. scores for violin, flute, etc.), much in the same way as most text recognition research focuses on recognizing words appearing in a given line image. These methods are based in two different methodologies. On the one hand, we present two methods based on Recurrent Neural Networks, in particular, the
Long Short-Term Memory Neural Network. On the other hand, a method based on Sequence to Sequence models is detailed.
Music context is needed to improve the OMR results, just like language models
and dictionaries help in handwriting recognition. For example, syntactical rules
and grammars could be easily defined to cope with the ambiguities in the rhythm.
In music theory, for example, the time signature defines the amount of beats per
bar unit. Thus, in the second part of this dissertation, different methodologies
have been investigated to improve the OMR recognition. We have explored three
different methods: (a) a graphic tree-structure representation, Dendrograms, that
joins, at each level, its primitives following a set of rules, (b) the incorporation of Language Models to model the probability of a sequence of tokens, and (c) graph neural networks to analyze the music scores to avoid meaningless relationships between music primitives.
Finally, to train all these methodologies, and given the method-specificity of
the datasets in the literature, we have created four different music datasets. Two of them are synthetic with a modern or old handwritten appearance, whereas the
other two are real handwritten scores, being one of them modern and the other
old.
Address (up)
Corporate Author Thesis Ph.D. thesis
Publisher IMPRIMA Place of Publication Editor Alicia Fornes
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-124793-8-6 Medium
Area Expedition Conference
Notes DAG; Approved no
Call Number Admin @ si @ Bar2022 Serial 3754
Permanent link to this record
 
 
Author Ali Furkan Biten
Title A Bitter-Sweet Symphony on Vision and Language: Bias and World Knowledge Type Book Whole
Year 2022 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Vision and Language are broadly regarded as cornerstones of intelligence. Even though language and vision have different aims – language having the purpose of communication, transmission of information and vision having the purpose of constructing mental representations around us to navigate and interact with objects – they cooperate and depend on one another in many tasks we perform effortlessly. This reliance is actively being studied in various Computer Vision tasks, e.g. image captioning, visual question answering, image-sentence retrieval, phrase grounding, just to name a few. All of these tasks share the inherent difficulty of the aligning the two modalities, while being robust to language
priors and various biases existing in the datasets. One of the ultimate goal for vision and language research is to be able to inject world knowledge while getting rid of the biases that come with the datasets. In this thesis, we mainly focus on two vision and language tasks, namely Image Captioning and Scene-Text Visual Question Answering (STVQA).
In both domains, we start by defining a new task that requires the utilization of world knowledge and in both tasks, we find that the models commonly employed are prone to biases that exist in the data. Concretely, we introduce new tasks and discover several problems that impede performance at each level and provide remedies or possible solutions in each chapter: i) We define a new task to move beyond Image Captioning to Image Interpretation that can utilize Named Entities in the form of world knowledge. ii) We study the object hallucination problem in classic Image Captioning systems and develop an architecture-agnostic solution. iii) We define a sub-task of Visual Question Answering that requires reading the text in the image (STVQA), where we highlight the limitations of current models. iv) We propose an architecture for the STVQA task that can point to the answer in the image and show how to combine it with classic VQA models. v) We show how far language can get us in STVQA and discover yet another bias which causes the models to disregard the image while doing Visual Question Answering.
Address (up)
Corporate Author Thesis Ph.D. thesis
Publisher IMPRIMA Place of Publication Editor Dimosthenis Karatzas;Lluis Gomez
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-124793-5-5 Medium
Area Expedition Conference
Notes DAG Approved no
Call Number Admin @ si @ Bit2022 Serial 3755
Permanent link to this record
 
 
Author Andres Mafla
Title Leveraging Scene Text Information for Image Interpretation Type Book Whole
Year 2022 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Until recently, most computer vision models remained illiterate, largely ignoring the semantically rich and explicit information contained in scene text. Recent progress in scene text detection and recognition has recently allowed exploring its role in a diverse set of open computer vision problems, e.g. image classification, image-text retrieval, image captioning, and visual question answering to name a few. The explicit semantics of scene text closely requires specific modeling similar to language. However, scene text is a particular signal that has to be interpreted according to a comprehensive perspective that encapsulates all the visual cues in an image. Incorporating this information is a straightforward task for humans, but if we are unfamiliar with a language or scripture, achieving a complete world understanding is impossible (e.a. visiting a foreign country with a different alphabet). Despite the importance of scene text, modeling it requires considering the several ways in which scene text interacts with an image, processing and fusing an additional modality. In this thesis, we mainly focus
on two tasks, scene text-based fine-grained image classification, and cross-modal retrieval. In both studied tasks we identify existing limitations in current approaches and propose plausible solutions. Concretely, in each chapter: i) We define a compact way to embed scene text that generalizes to unseen words at training time while performing in real-time. ii) We incorporate the previously learned scene text embedding to create an image-level descriptor that overcomes optical character recognition (OCR) errors which is well-suited to the fine-grained image classification task. iii) We design a region-level reasoning network that learns the interaction through semantics among salient visual regions and scene text instances. iv) We employ scene text information in image-text matching and introduce the Scene Text Aware Cross-Modal retrieval StacMR task. We gather a dataset that incorporates scene text and design a model suited for the newly studied modality. v) We identify the drawbacks of current retrieval metrics in cross-modal retrieval. An image captioning metric is proposed as a way of better evaluating semantics in retrieved results. Ample experimentation shows that incorporating such semantics into a model yields better semantic results while
requiring significantly less data to converge.
Address (up)
Corporate Author Thesis Ph.D. thesis
Publisher IMPRIMA Place of Publication Editor Dimosthenis Karatzas;Lluis Gomez
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-124793-6-2 Medium
Area Expedition Conference
Notes DAG Approved no
Call Number Admin @ si @ Maf2022 Serial 3756
Permanent link to this record