toggle visibility Search & Display Options
Select All    Deselect All [61–70] << 71 72 73 74 >>
List View
 | 
Citations
 | 
Details
  Records Links
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 17th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume 14192 Issue Pages 106-121  
  Keywords (up) 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 Y. Patel; Lluis Gomez; Marçal Rusiñol; Dimosthenis Karatzas edit   pdf
openurl 
  Title Dynamic Lexicon Generation for Natural Scene Images Type Conference Article
  Year 2016 Publication 14th European Conference on Computer Vision Workshops Abbreviated Journal  
  Volume Issue Pages 395-410  
  Keywords (up) scene text; photo OCR; scene understanding; lexicon generation; topic modeling; CNN  
  Abstract Many scene text understanding methods approach the endtoend recognition problem from a word-spotting perspective and take huge bene t from using small per-image lexicons. Such customized lexicons are normally assumed as given and their source is rarely discussed.
In this paper we propose a method that generates contextualized lexicons
for scene images using only visual information. For this, we exploit
the correlation between visual and textual information in a dataset consisting
of images and textual content associated with them. Using the topic modeling framework to discover a set of latent topics in such a dataset allows us to re-rank a xed dictionary in a way that prioritizes the words that are more likely to appear in a given image. Moreover, we train a CNN that is able to reproduce those word rankings but using only the image raw pixels as input. We demonstrate that the quality of the automatically obtained custom lexicons is superior to a generic frequency-based baseline.		  
  Address Amsterdam; The Netherlands; October 2016  
  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 ECCVW  
  Notes DAG; 600.084 Approved no  
  Call Number Admin @ si @ PGR2016 Serial 2825  
Permanent link to this record
 
 
Author Lluis Gomez; Dimosthenis Karatzas edit   pdf
url  openurl
  Title A fast hierarchical method for multi‐script and arbitrary oriented scene text extraction Type Journal Article
  Year 2016 Publication International Journal on Document Analysis and Recognition Abbreviated Journal IJDAR  
  Volume 19 Issue 4 Pages 335-349  
  Keywords (up) scene text; segmentation; detection; hierarchical grouping; perceptual organisation  
  Abstract Typography and layout lead to the hierarchical organisation of text in words, text lines, paragraphs. This inherent structure is a key property of text in any script and language, which has nonetheless been minimally leveraged by existing text detection methods. This paper addresses the problem of text
segmentation in natural scenes from a hierarchical perspective.
Contrary to existing methods, we make explicit use of text structure, aiming directly to the detection of region groupings corresponding to text within a hierarchy produced by an agglomerative similarity clustering process over individual regions. We propose an optimal way to construct such an hierarchy introducing a feature space designed to produce text group hypotheses with
high recall and a novel stopping rule combining a discriminative classifier and a probabilistic measure of group meaningfulness based in perceptual organization. Results obtained over four standard datasets, covering text in variable orientations and different languages, demonstrate that our algorithm, while being trained in a single mixed dataset, outperforms state of the art
methods in unconstrained scenarios.		  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes DAG; 600.056; 601.197 Approved no  
  Call Number Admin @ si @ GoK2016a Serial 2862  
Permanent link to this record
 
 
Author Josep Brugues Pujolras; Lluis Gomez; Dimosthenis Karatzas edit   pdf
doi  openurl
  Title A Multilingual Approach to Scene Text Visual Question Answering Type Conference Article
  Year 2022 Publication Document Analysis Systems.15th IAPR International Workshop, (DAS2022) Abbreviated Journal  
  Volume Issue Pages 65-79  
  Keywords (up) Scene text; Visual question answering; Multilingual word embeddings; Vision and language; Deep learning  
  Abstract Scene Text Visual Question Answering (ST-VQA) has recently emerged as a hot research topic in Computer Vision. Current ST-VQA models have a big potential for many types of applications but lack the ability to perform well on more than one language at a time due to the lack of multilingual data, as well as the use of monolingual word embeddings for training. In this work, we explore the possibility to obtain bilingual and multilingual VQA models. In that regard, we use an already established VQA model that uses monolingual word embeddings as part of its pipeline and substitute them by FastText and BPEmb multilingual word embeddings that have been aligned to English. Our experiments demonstrate that it is possible to obtain bilingual and multilingual VQA models with a minimal loss in performance in languages not used during training, as well as a multilingual model trained in multiple languages that match the performance of the respective monolingual baselines.  
  Address La Rochelle, France; May 22–25, 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 DAS  
  Notes DAG; 611.004; 600.155; 601.002 Approved no  
  Call Number Admin @ si @ BGK2022b Serial 3695  
Permanent link to this record
 
 
Author Lasse Martensson; Ekta Vats; Anders Hast; Alicia Fornes edit  url
openurl 
  Title In Search of the Scribe: Letter Spotting as a Tool for Identifying Scribes in Large Handwritten Text Corpora Type Journal
  Year 2019 Publication Journal for Information Technology Studies as a Human Science Abbreviated Journal HUMAN IT  
  Volume 14 Issue 2 Pages 95-120  
  Keywords (up) Scribal attribution/ writer identification; digital palaeography; word spotting; mediaeval charters; mediaeval manuscripts  
  Abstract In this article, a form of the so-called word spotting-method is used on a large set of handwritten documents in order to identify those that contain script of similar execution. The point of departure for the investigation is the mediaeval Swedish manuscript Cod. Holm. D 3. The main scribe of this manuscript has yet not been identified in other documents. The current attempt aims at localising other documents that display a large degree of similarity in the characteristics of the script, these being possible candidates for being executed by the same hand. For this purpose, the method of word spotting has been employed, focusing on individual letters, and therefore the process is referred to as letter spotting in the article. In this process, a set of ‘g’:s, ‘h’:s and ‘k’:s have been selected as templates, and then a search has been made for close matches among the mediaeval Swedish charters. The search resulted in a number of charters that displayed great similarities with the manuscript D 3. The used letter spotting method thus proofed to be a very efficient sorting tool localising similar script samples.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes DAG; 600.097; 600.140; 600.121 Approved no  
  Call Number Admin @ si @ MVH2019 Serial 3234  
Permanent link to this record
 
 
Author Partha Pratim Roy; Umapada Pal; Josep Llados edit  doi
openurl 
  Title Document Seal Detection Using Ght and Character Proximity Graphs Type Journal Article
  Year 2011 Publication Pattern Recognition Abbreviated Journal PR  
  Volume 44 Issue 6 Pages 1282-1295  
  Keywords (up) Seal recognition; Graphical symbol spotting; Generalized Hough transform; Multi-oriented character recognition  
  Abstract This paper deals with automatic detection of seal (stamp) from documents with cluttered background. Seal detection involves a difficult challenge due to its multi-oriented nature, arbitrary shape, overlapping of its part with signature, noise, etc. Here, a seal object is characterized by scale and rotation invariant spatial feature descriptors computed from recognition result of individual connected components (characters). Scale and rotation invariant features are used in a Support Vector Machine (SVM) classifier to recognize multi-scale and multi-oriented text characters. The concept of generalized Hough transform (GHT) is used to detect the seal and a voting scheme is designed for finding possible location of the seal in a document based on the spatial feature descriptor of neighboring component pairs. The peak of votes in GHT accumulator validates the hypothesis to locate the seal in a document. Experiment is performed in an archive of historical documents of handwritten/printed English text. Experimental results show that the method is robust in locating seal instances of arbitrary shape and orientation in documents, and also efficient in indexing a collection of documents for retrieval purposes.  
  Address  
  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 Approved no  
  Call Number Admin @ si @ RPL2011 Serial 1820  
Permanent link to this record
 
 
Author Raul Gomez; Lluis Gomez; Jaume Gibert; Dimosthenis Karatzas edit   pdf
url  openurl
  Title Self-Supervised Learning from Web Data for Multimodal Retrieval Type Book Chapter
  Year 2019 Publication Multi-Modal Scene Understanding Book Abbreviated Journal  
  Volume Issue Pages 279-306  
  Keywords (up) self-supervised learning; webly supervised learning; text embeddings; multimodal retrieval; multimodal embedding  
  Abstract Self-Supervised learning from multimodal image and text data allows deep neural networks to learn powerful features with no need of human annotated data. Web and Social Media platforms provide a virtually unlimited amount of this multimodal data. In this work we propose to exploit this free available data to learn a multimodal image and text embedding, aiming to leverage the semantic knowledge learnt in the text domain and transfer it to a visual model for semantic image retrieval. We demonstrate that the proposed pipeline can learn from images with associated text without supervision and analyze the semantic structure of the learnt joint image and text embeddingspace. Weperformathoroughanalysisandperformancecomparisonoffivedifferentstateof the art text embeddings in three different benchmarks. We show that the embeddings learnt with Web and Social Media data have competitive performances over supervised methods in the text basedimageretrievaltask,andweclearlyoutperformstateoftheartintheMIRFlickrdatasetwhen training in the target data. Further, we demonstrate how semantic multimodal image retrieval can be performed using the learnt embeddings, going beyond classical instance-level retrieval problems. Finally, we present a new dataset, InstaCities1M, composed by Instagram images and their associated texts that can be used for fair comparison of image-text embeddings.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes DAG; 600.129; 601.338; 601.310 Approved no  
  Call Number Admin @ si @ GGG2019 Serial 3266  
Permanent link to this record
 
 
Author Jon Almazan; Alicia Fornes; Ernest Valveny edit   pdf
url  doi
openurl 
  Title A non-rigid appearance model for shape description and recognition Type Journal Article
  Year 2012 Publication Pattern Recognition Abbreviated Journal PR  
  Volume 45 Issue 9 Pages 3105--3113  
  Keywords (up) Shape recognition; Deformable models; Shape modeling; Hand-drawn recognition  
  Abstract In this paper we describe a framework to learn a model of shape variability in a set of patterns. The framework is based on the Active Appearance Model (AAM) and permits to combine shape deformations with appearance variability. We have used two modifications of the Blurred Shape Model (BSM) descriptor as basic shape and appearance features to learn the model. These modifications permit to overcome the rigidity of the original BSM, adapting it to the deformations of the shape to be represented. We have applied this framework to representation and classification of handwritten digits and symbols. We show that results of the proposed methodology outperform the original BSM approach.  
  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 0031-3203 ISBN Medium  
  Area Expedition Conference  
  Notes DAG Approved no  
  Call Number DAG @ dag @ AFV2012 Serial 1982  
Permanent link to this record
 
 
Author Asma Bensalah; Pau Riba; Alicia Fornes; Josep Llados edit   pdf
openurl 
  Title Shoot less and Sketch more: An Efficient Sketch Classification via Joining Graph Neural Networks and Few-shot Learning Type Conference Article
  Year 2019 Publication 13th IAPR International Workshop on Graphics Recognition Abbreviated Journal  
  Volume Issue Pages 80-85  
  Keywords (up) Sketch classification; Convolutional Neural Network; Graph Neural Network; Few-shot learning  
  Abstract With the emergence of the touchpad devices and drawing tablets, a new era of sketching started afresh. However, the recognition of sketches is still a tough task due to the variability of the drawing styles. Moreover, in some application scenarios there is few labelled data available for training,
which imposes a limitation for deep learning architectures. In addition, in many cases there is a need to generate models able to adapt to new classes. In order to cope with these limitations, we propose a method based on few-shot learning and graph neural networks for classifying sketches aiming for an efficient neural model. We test our approach with several databases of
sketches, showing promising results.		  
  Address Sydney; Australia; September 2019  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference GREC  
  Notes DAG; 600.140; 601.302; 600.121 Approved no  
  Call Number Admin @ si @ BRF2019 Serial 3354  
Permanent link to this record
 
 
Author Anjan Dutta; Hichem Sahbi edit   pdf
doi  openurl
  Title Stochastic Graphlet Embedding Type Journal Article
  Year 2018 Publication IEEE Transactions on Neural Networks and Learning Systems Abbreviated Journal TNNLS  
  Volume Issue Pages 1-14  
  Keywords (up) Stochastic graphlets; Graph embedding; Graph classification; Graph hashing; Betweenness centrality  
  Abstract Graph-based methods are known to be successful in many machine learning and pattern classification tasks. These methods consider semi-structured data as graphs where nodes correspond to primitives (parts, interest points, segments,
etc.) and edges characterize the relationships between these primitives. However, these non-vectorial graph data cannot be straightforwardly plugged into off-the-shelf machine learning algorithms without a preliminary step of – explicit/implicit –graph vectorization and embedding. This embedding process
should be resilient to intra-class graph variations while being highly discriminant. In this paper, we propose a novel high-order stochastic graphlet embedding (SGE) that maps graphs into vector spaces. Our main contribution includes a new stochastic search procedure that efficiently parses a given graph and extracts/samples unlimitedly high-order graphlets. We consider
these graphlets, with increasing orders, to model local primitives as well as their increasingly complex interactions. In order to build our graph representation, we measure the distribution of these graphlets into a given graph, using particular hash functions that efficiently assign sampled graphlets into isomorphic sets with a very low probability of collision. When
combined with maximum margin classifiers, these graphlet-based representations have positive impact on the performance of pattern comparison and recognition as corroborated through extensive experiments using standard benchmark databases.		  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes DAG; 602.167; 602.168; 600.097; 600.121 Approved no  
  Call Number Admin @ si @ DuS2018 Serial 3225  
Permanent link to this record
Select All    Deselect All [61–70] << 71 72 73 74 >>
List View
 | 
Citations
 | 
Details
toggle visibility
Save Citations:
Export Records: