toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
   print
  Records Links
Author George Tom; Minesh Mathew; Sergi Garcia Bordils; Dimosthenis Karatzas; CV Jawahar edit  url
openurl 
  Title Reading Between the Lanes: Text VideoQA on the Road Type Conference Article
  Year 2023 Publication (up) 17th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume 14192 Issue Pages 137–154  
  Keywords VideoQA; scene text; driving videos  
  Abstract Text and signs around roads provide crucial information for drivers, vital for safe navigation and situational awareness. Scene text recognition in motion is a challenging problem, while textual cues typically appear for a short time span, and early detection at a distance is necessary. Systems that exploit such information to assist the driver should not only extract and incorporate visual and textual cues from the video stream but also reason over time. To address this issue, we introduce RoadTextVQA, a new dataset for the task of video question answering (VideoQA) in the context of driver assistance. RoadTextVQA consists of 3, 222 driving videos collected from multiple countries, annotated with 10, 500 questions, all based on text or road signs present in the driving videos. We assess the performance of state-of-the-art video question answering models on our RoadTextVQA dataset, highlighting the significant potential for improvement in this domain and the usefulness of the dataset in advancing research on in-vehicle support systems and text-aware multimodal question answering. The dataset is available at http://cvit.iiit.ac.in/research/projects/cvit-projects/roadtextvqa.  
  Address San Jose; CA; USA; August 2023  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICDAR  
  Notes DAG Approved no  
  Call Number Admin @ si @ TMG2023 Serial 3906  
Permanent link to this record
 

 
Author Sergi Garcia Bordils; Dimosthenis Karatzas; Marçal Rusiñol edit  url
openurl 
  Title Accelerating Transformer-Based Scene Text Detection and Recognition via Token Pruning Type Conference Article
  Year 2023 Publication (up) 17th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume 14192 Issue Pages 106-121  
  Keywords Scene Text Detection; Scene Text Recognition; Transformer Acceleration  
  Abstract Scene text detection and recognition is a crucial task in computer vision with numerous real-world applications. Transformer-based approaches are behind all current state-of-the-art models and have achieved excellent performance. However, the computational requirements of the transformer architecture makes training these methods slow and resource heavy. In this paper, we introduce a new token pruning strategy that significantly decreases training and inference times without sacrificing performance, striking a balance between accuracy and speed. We have applied this pruning technique to our own end-to-end transformer-based scene text understanding architecture. Our method uses a separate detection branch to guide the pruning of uninformative image features, which significantly reduces the number of tokens at the input of the transformer. Experimental results show how our network is able to obtain competitive results on multiple public benchmarks while running at significantly higher speeds.  
  Address San Jose; CA; USA; August 2023  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICDAR  
  Notes DAG Approved no  
  Call Number Admin @ si @ GKR2023a Serial 3907  
Permanent link to this record
 

 
Author Adarsh Tiwari; Sanket Biswas; Josep Llados edit  url
openurl 
  Title Can Pre-trained Language Models Help in Understanding Handwritten Symbols? Type Conference Article
  Year 2023 Publication (up) 17th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume 14193 Issue Pages 199–211  
  Keywords  
  Abstract The emergence of transformer models like BERT, GPT-2, GPT-3, RoBERTa, T5 for natural language understanding tasks has opened the floodgates towards solving a wide array of machine learning tasks in other modalities like images, audio, music, sketches and so on. These language models are domain-agnostic and as a result could be applied to 1-D sequences of any kind. However, the key challenge lies in bridging the modality gap so that they could generate strong features beneficial for out-of-domain tasks. This work focuses on leveraging the power of such pre-trained language models and discusses the challenges in predicting challenging handwritten symbols and alphabets.  
  Address San Jose; CA; USA; August 2023  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICDAR  
  Notes DAG Approved no  
  Call Number Admin @ si @ TBL2023 Serial 3908  
Permanent link to this record
 

 
Author Arnau Baro; Alicia Fornes; Carles Badal edit   pdf
openurl 
  Title Handwritten Historical Music Recognition by Sequence-to-Sequence with Attention Mechanism Type Conference Article
  Year 2020 Publication (up) 17th International Conference on Frontiers in Handwriting Recognition Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Despite decades of research in Optical Music Recognition (OMR), the recognition of old handwritten music scores remains a challenge because of the variabilities in the handwriting styles, paper degradation, lack of standard notation, etc. Therefore, the research in OMR systems adapted to the particularities of old manuscripts is crucial to accelerate the conversion of music scores existing in archives into digital libraries, fostering the dissemination and preservation of our music heritage. In this paper we explore the adaptation of sequence-to-sequence models with attention mechanism (used in translation and handwritten text recognition) and the generation of specific synthetic data for recognizing old music scores. The experimental validation demonstrates that our approach is promising, especially when compared with long short-term memory neural networks.  
  Address Virtual ICFHR; September 2020  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICFHR  
  Notes DAG; 600.140; 600.121 Approved no  
  Call Number Admin @ si @ BFB2020 Serial 3448  
Permanent link to this record
 

 
Author Lei Kang; Pau Riba; Marçal Rusiñol; Alicia Fornes; Mauricio Villegas edit   pdf
openurl 
  Title Distilling Content from Style for Handwritten Word Recognition Type Conference Article
  Year 2020 Publication (up) 17th International Conference on Frontiers in Handwriting Recognition Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Despite the latest transcription accuracies reached using deep neural network architectures, handwritten text recognition still remains a challenging problem, mainly because of the large inter-writer style variability. Both augmenting the training set with artificial samples using synthetic fonts, and writer adaptation techniques have been proposed to yield more generic approaches aimed at dodging style unevenness. In this work, we take a step closer to learn style independent features from handwritten word images. We propose a novel method that is able to disentangle the content and style aspects of input images by jointly optimizing a generative process and a handwritten
word recognizer. The generator is aimed at transferring writing style features from one sample to another in an image-to-image translation approach, thus leading to a learned content-centric features that shall be independent to writing style attributes.
Our proposed recognition model is able then to leverage such writer-agnostic features to reach better recognition performances. We advance over prior training strategies and demonstrate with qualitative and quantitative evaluations the performance of both
the generative process and the recognition efficiency in the IAM dataset.
 
  Address Virtual ICFHR; September 2020  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICFHR  
  Notes DAG; 600.129; 600.140; 600.121 Approved no  
  Call Number Admin @ si @ KRR2020 Serial 3425  
Permanent link to this record
 

 
Author Patricia Marquez; H. Kause; A. Fuster; Aura Hernandez-Sabate; L. Florack; Debora Gil; Hans van Assen edit   pdf
doi  isbn
openurl 
  Title Factors Affecting Optical Flow Performance in Tagging Magnetic Resonance Imaging Type Conference Article
  Year 2014 Publication (up) 17th International Conference on Medical Image Computing and Computer Assisted Intervention Abbreviated Journal  
  Volume 8896 Issue Pages 231-238  
  Keywords Optical flow; Performance Evaluation; Synthetic Database; ANOVA; Tagging Magnetic Resonance Imaging  
  Abstract Changes in cardiac deformation patterns are correlated with cardiac pathologies. Deformation can be extracted from tagging Magnetic Resonance Imaging (tMRI) using Optical Flow (OF) techniques. For applications of OF in a clinical setting it is important to assess to what extent the performance of a particular OF method is stable across di erent clinical acquisition artifacts. This paper presents a statistical validation framework, based on ANOVA, to assess the motion and appearance factors that have the largest in uence on OF accuracy drop.
In order to validate this framework, we created a database of simulated tMRI data including the most common artifacts of MRI and test three di erent OF methods, including HARP.
 
  Address Boston; USA; September 2014  
  Corporate Author Thesis  
  Publisher Springer International Publishing Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-319-14677-5 Medium  
  Area Expedition Conference STACOM  
  Notes IAM; ADAS; 600.060; 601.145; 600.076; 600.075 Approved no  
  Call Number Admin @ si @ MKF2014 Serial 2495  
Permanent link to this record
 

 
Author Georg Langs; Petia Radeva; David Rotger; Francesc Carreras edit  url
openurl 
  Title Building and Registering Parameterized 3D Models of Vessel Trees for Visualization during Intervention Type Miscellaneous
  Year 2004 Publication (up) 17th International Conference on Pattern Recognition, ICPR’04 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Cambridge, United Kingdom  
  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 BCNPCL @ bcnpcl @ LRR2004b Serial 463  
Permanent link to this record
 

 
Author Patricia Suarez; Dario Carpio; Angel Sappa edit  url
doi  openurl
  Title Depth Map Estimation from a Single 2D Image Type Conference Article
  Year 2023 Publication (up) 17th International Conference on Signal-Image Technology & Internet-Based Systems Abbreviated Journal  
  Volume Issue Pages 347-353  
  Keywords  
  Abstract This paper presents an innovative architecture based on a Cycle Generative Adversarial Network (CycleGAN) for the synthesis of high-quality depth maps from monocular images. The proposed architecture leverages a diverse set of loss functions, including cycle consistency, contrastive, identity, and least square losses, to facilitate the generation of depth maps that exhibit realism and high fidelity. A notable feature of the approach is its ability to synthesize depth maps from grayscale images without the need for paired training data. Extensive comparisons with different state-of-the-art methods show the superiority of the proposed approach in both quantitative metrics and visual quality. This work addresses the challenge of depth map synthesis and offers significant advancements in the field.  
  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 SITIS  
  Notes MSIAU Approved no  
  Call Number Admin @ si @ SCS2023b Serial 4009  
Permanent link to this record
 

 
Author Rafael E. Rivadeneira; Henry Velesaca; Angel Sappa edit  url
doi  openurl
  Title Object Detection in Very Low-Resolution Thermal Images through a Guided-Based Super-Resolution Approach Type Conference Article
  Year 2023 Publication (up) 17th International Conference on Signal-Image Technology & Internet-Based Systems Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract This work proposes a novel approach that integrates super-resolution techniques with off-the-shelf object detection methods to tackle the problem of handling very low-resolution thermal images. The suggested approach begins by enhancing the low-resolution (LR) thermal images through a guided super-resolution strategy, leveraging a high-resolution (HR) visible spectrum image. Subsequently, object detection is performed on the high-resolution thermal image. The experimental results demonstrate tremendous improvements in comparison with both scenarios: when object detection is performed on the LR thermal image alone, as well as when object detection is conducted on the up-sampled LR thermal image. Moreover, the proposed approach proves highly valuable in camouflaged scenarios where objects might remain undetected in visible spectrum images.  
  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 SITIS  
  Notes MSIAU Approved no  
  Call Number Admin @ si @ RVS2023 Serial 4010  
Permanent link to this record
 

 
Author Patricia Suarez; Dario Carpio; Angel Sappa edit  url
doi  openurl
  Title Boosting Guided Super-Resolution Performance with Synthesized Images Type Conference Article
  Year 2023 Publication (up) 17th International Conference on Signal-Image Technology & Internet-Based Systems Abbreviated Journal  
  Volume Issue Pages 189-195  
  Keywords  
  Abstract Guided image processing techniques are widely used for extracting information from a guiding image to aid in the processing of the guided one. These images may be sourced from different modalities, such as 2D and 3D, or different spectral bands, like visible and infrared. In the case of guided cross-spectral super-resolution, features from the two modal images are extracted and efficiently merged to migrate guidance information from one image, usually high-resolution (HR), toward the guided one, usually low-resolution (LR). Different approaches have been recently proposed focusing on the development of architectures for feature extraction and merging in the cross-spectral domains, but none of them care about the different nature of the given images. This paper focuses on the specific problem of guided thermal image super-resolution, where an LR thermal image is enhanced by an HR visible spectrum image. To improve existing guided super-resolution techniques, a novel scheme is proposed that maps the original guiding information to a thermal image-like representation that is similar to the output. Experimental results evaluating five different approaches demonstrate that the best results are achieved when the guiding and guided images share the same domain.  
  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 SITIS  
  Notes MSIAU Approved no  
  Call Number Admin @ si @ SCS2023c Serial 4011  
Permanent link to this record
 

 
Author Bhalaji Nagarajan; Ricardo Marques; Marcos Mejia; Petia Radeva edit  url
doi  openurl
  Title Class-conditional Importance Weighting for Deep Learning with Noisy Labels Type Conference Article
  Year 2022 Publication (up) 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications Abbreviated Journal  
  Volume 5 Issue Pages 679-686  
  Keywords Noisy Labeling; Loss Correction; Class-conditional Importance Weighting; Learning with Noisy Labels  
  Abstract Large-scale accurate labels are very important to the Deep Neural Networks to train them and assure high performance. However, it is very expensive to create a clean dataset since usually it relies on human interaction. To this purpose, the labelling process is made cheap with a trade-off of having noisy labels. Learning with Noisy Labels is an active area of research being at the same time very challenging. The recent advances in Self-supervised learning and robust loss functions have helped in advancing noisy label research. In this paper, we propose a loss correction method that relies on dynamic weights computed based on the model training. We extend the existing Contrast to Divide algorithm coupled with DivideMix using a new class-conditional weighted scheme. We validate the method using the standard noise experiments and achieved encouraging results.  
  Address Virtual; February 2022  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference VISAPP  
  Notes MILAB; no menciona Approved no  
  Call Number Admin @ si @ NMM2022 Serial 3798  
Permanent link to this record
 

 
Author Patricia Suarez; Angel Sappa; Dario Carpio; Henry Velesaca; Francisca Burgos; Patricia Urdiales edit   pdf
url  doi
openurl 
  Title Deep Learning Based Shrimp Classification Type Conference Article
  Year 2022 Publication (up) 17th International Symposium on Visual Computing Abbreviated Journal  
  Volume 13598 Issue Pages 36–45  
  Keywords Pigmentation; Color space; Light weight network  
  Abstract This work proposes a novel approach based on deep learning to address the classification of shrimp (Pennaeus vannamei) into two classes, according to their level of pigmentation accepted by shrimp commerce. The main goal of this actual study is to support the shrimp industry in terms of price and process. An efficient CNN architecture is proposed to perform image classification through a program that could be set other in mobile devices or in fixed support in the shrimp supply chain. The proposed approach is a lightweight model that uses HSV color space shrimp images. A simple pipeline shows the most important stages performed to determine a pattern that identifies the class to which they belong based on their pigmentation. For the experiments, a database acquired with mobile devices of various brands and models has been used to capture images of shrimp. The results obtained with the images in the RGB and HSV color space allow for testing the effectiveness of the proposed model.  
  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 ISVC  
  Notes MSIAU; no proj Approved no  
  Call Number Admin @ si @ SAC2022 Serial 3772  
Permanent link to this record
 

 
Author P. Andreeva; Maya Dimitrova; Petia Radeva edit  openurl
  Title Data Mining Learning Models and Algorithms for Medical Applications Type Book Chapter
  Year 2004 Publication (up) 18 Conference Systems for Automation of Engineering and Research (SEAR 2004) Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Varna (Bulgaria)  
  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 BCNPCL @ bcnpcl @ ADR2004 Serial 474  
Permanent link to this record
 

 
Author Lichao Zhang; Abel Gonzalez-Garcia; Joost Van de Weijer; Martin Danelljan; Fahad Shahbaz Khan edit   pdf
url  doi
openurl 
  Title Learning the Model Update for Siamese Trackers Type Conference Article
  Year 2019 Publication (up) 18th IEEE International Conference on Computer Vision Abbreviated Journal  
  Volume Issue Pages 4009-4018  
  Keywords  
  Abstract Siamese approaches address the visual tracking problem by extracting an appearance template from the current frame, which is used to localize the target in the next frame. In general, this template is linearly combined with the accumulated template from the previous frame, resulting in an exponential decay of information over time. While such an approach to updating has led to improved results, its simplicity limits the potential gain likely to be obtained by learning to update. Therefore, we propose to replace the handcrafted update function with a method which learns to update. We use a convolutional neural network, called UpdateNet, which given the initial template, the accumulated template and the template of the current frame aims to estimate the optimal template for the next frame. The UpdateNet is compact and can easily be integrated into existing Siamese trackers. We demonstrate the generality of the proposed approach by applying it to two Siamese trackers, SiamFC and DaSiamRPN. Extensive experiments on VOT2016, VOT2018, LaSOT, and TrackingNet datasets demonstrate that our UpdateNet effectively predicts the new target template, outperforming the standard linear update. On the large-scale TrackingNet dataset, our UpdateNet improves the results of DaSiamRPN with an absolute gain of 3.9% in terms of success score.  
  Address Seul; Corea; October 2019  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICCV  
  Notes LAMP; 600.109; 600.141; 600.120 Approved no  
  Call Number Admin @ si @ ZGW2019 Serial 3295  
Permanent link to this record
 

 
Author Ali Furkan Biten; R. Tito; Andres Mafla; Lluis Gomez; Marçal Rusiñol; C.V. Jawahar; Ernest Valveny; Dimosthenis Karatzas edit   pdf
url  doi
openurl 
  Title Scene Text Visual Question Answering Type Conference Article
  Year 2019 Publication (up) 18th IEEE International Conference on Computer Vision Abbreviated Journal  
  Volume Issue Pages 4291-4301  
  Keywords  
  Abstract Current visual question answering datasets do not consider the rich semantic information conveyed by text within an image. In this work, we present a new dataset, ST-VQA, that aims to highlight the importance of exploiting highlevel semantic information present in images as textual cues in the Visual Question Answering process. We use this dataset to define a series of tasks of increasing difficulty for which reading the scene text in the context provided by the visual information is necessary to reason and generate an appropriate answer. We propose a new evaluation metric for these tasks to account both for reasoning errors as well as shortcomings of the text recognition module. In addition we put forward a series of baseline methods, which provide further insight to the newly released dataset, and set the scene for further research.  
  Address Seul; Corea; October 2019  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICCV  
  Notes DAG; 600.129; 600.135; 601.338; 600.121 Approved no  
  Call Number Admin @ si @ BTM2019b Serial 3285  
Permanent link to this record
Select All    Deselect All
 |   | 
Details
   print

Save Citations:
Export Records: