| |
Records |
Links |
|
Author |
Lei Kang; Juan Ignacio Toledo; Pau Riba; Mauricio Villegas; Alicia Fornes; Marçal Rusiñol |
|
| |
Title |
Convolve, Attend and Spell: An Attention-based Sequence-to-Sequence Model for Handwritten Word Recognition |
Type |
Conference Article |
| |
Year |
2018 |
Publication |
40th German Conference on Pattern Recognition |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
459-472 |
|
| |
Keywords |
|
|
| |
Abstract |
This paper proposes Convolve, Attend and Spell, an attention based sequence-to-sequence model for handwritten word recognition. The proposed architecture has three main parts: an encoder, consisting of a CNN and a bi-directional GRU, an attention mechanism devoted to focus on the pertinent features and a decoder formed by a one-directional GRU, able to spell the corresponding word, character by character. Compared with the recent state-of-the-art, our model achieves competitive results on the IAM dataset without needing any pre-processing step, predefined lexicon nor language model. Code and additional results are available in https://github.com/omni-us/research-seq2seq-HTR. |
|
| |
Address |
Stuttgart; Germany; October 2018 |
|
| |
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  |
GCPR |
|
| |
Notes |
DAG; 600.097; 603.057; 302.065; 601.302; 600.084; 600.121; 600.129 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ KTR2018 |
Serial |
3167 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Jaume Gibert; Ernest Valveny; Horst Bunke |
|
| |
Title |
Dimensionality Reduction for Graph of Words Embedding |
Type |
Conference Article |
| |
Year |
2011 |
Publication |
8th IAPR-TC-15 International Workshop. Graph-Based Representations in Pattern Recognition |
Abbreviated Journal |
|
|
| |
Volume |
6658 |
Issue |
|
Pages |
22-31 |
|
| |
Keywords |
|
|
| |
Abstract |
The Graph of Words Embedding consists in mapping every graph of a given dataset to a feature vector by counting unary and binary relations between node attributes of the graph. While it shows good properties in classification problems, it suffers from high dimensionality and sparsity. These two issues are addressed in this article. Two well-known techniques for dimensionality reduction, kernel principal component analysis (kPCA) and independent component analysis (ICA), are applied to the embedded graphs. We discuss their performance compared to the classification of the original vectors on three different public databases of graphs. |
|
| |
Address |
Münster, Germany |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
Xiaoyi Jiang; Miquel Ferrer; Andrea Torsello |
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
978-3-642-20843-0 |
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
GbRPR |
|
| |
Notes |
DAG |
Approved |
no |
|
| |
Call Number |
Admin @ si @ GVB2011a |
Serial |
1743 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Pau Riba; Josep Llados; Alicia Fornes; Anjan Dutta |
|
| |
Title |
Large-scale Graph Indexing using Binary Embeddings of Node Contexts |
Type |
Conference Article |
| |
Year |
2015 |
Publication |
10th IAPR-TC15 Workshop on Graph-based Representations in Pattern Recognition |
Abbreviated Journal |
|
|
| |
Volume |
9069 |
Issue |
|
Pages |
208-217 |
|
| |
Keywords |
Graph matching; Graph indexing; Application in document analysis; Word spotting; Binary embedding |
|
| |
Abstract |
Graph-based representations are experiencing a growing usage in visual recognition and retrieval due to their representational power in front of classical appearance-based representations in terms of feature vectors. Retrieving a query graph from a large dataset of graphs has the drawback of the high computational complexity required to compare the query and the target graphs. The most important property for a large-scale retrieval is the search time complexity to be sub-linear in the number of database examples. In this paper we propose a fast indexation formalism for graph retrieval. A binary embedding is defined as hashing keys for graph nodes. Given a database of labeled graphs, graph nodes are complemented with vectors of attributes representing their local context. Hence, each attribute counts the length of a walk of order k originated in a vertex with label l. Each attribute vector is converted to a binary code applying a binary-valued hash function. Therefore, graph retrieval is formulated in terms of finding target graphs in the database whose nodes have a small Hamming distance from the query nodes, easily computed with bitwise logical operators. As an application example, we validate the performance of the proposed methods in a handwritten word spotting scenario in images of historical documents. |
|
| |
Address |
Beijing; China; May 2015 |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
Springer International Publishing |
Place of Publication |
|
Editor |
C.-L.Liu; B.Luo; W.G.Kropatsch; J.Cheng |
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
0302-9743 |
ISBN |
978-3-319-18223-0 |
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
GbRPR |
|
| |
Notes |
DAG; 600.061; 602.006; 600.077 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ RLF2015a |
Serial |
2618 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Pau Riba; Josep Llados; Alicia Fornes |
|
| |
Title |
Error-tolerant coarse-to-fine matching model for hierarchical graphs |
Type |
Conference Article |
| |
Year |
2017 |
Publication |
11th IAPR-TC-15 International Workshop on Graph-Based Representations in Pattern Recognition |
Abbreviated Journal |
|
|
| |
Volume |
10310 |
Issue |
|
Pages |
107-117 |
|
| |
Keywords |
Graph matching; Hierarchical graph; Graph-based representation; Coarse-to-fine matching |
|
| |
Abstract |
Graph-based representations are effective tools to capture structural information from visual elements. However, retrieving a query graph from a large database of graphs implies a high computational complexity. Moreover, these representations are very sensitive to noise or small changes. In this work, a novel hierarchical graph representation is designed. Using graph clustering techniques adapted from graph-based social media analysis, we propose to generate a hierarchy able to deal with different levels of abstraction while keeping information about the topology. For the proposed representations, a coarse-to-fine matching method is defined. These approaches are validated using real scenarios such as classification of colour images and handwritten word spotting. |
|
| |
Address |
Anacapri; Italy; May 2017 |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
Springer International Publishing |
Place of Publication |
|
Editor |
Pasquale Foggia; Cheng-Lin Liu; Mario Vento |
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
GbRPR |
|
| |
Notes |
DAG; 600.097; 601.302; 600.121 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ RLF2017a |
Serial |
2951 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Miquel Ferrer; Dimosthenis Karatzas; Ernest Valveny; Horst Bunke |
|
| |
Title |
A Recursive Embedding Approach to Median Graph Computation |
Type |
Conference Article |
| |
Year |
2009 |
Publication |
7th IAPR – TC–15 Workshop on Graph–Based Representations in Pattern Recognition |
Abbreviated Journal |
|
|
| |
Volume |
5534 |
Issue |
|
Pages |
113–123 |
|
| |
Keywords |
|
|
| |
Abstract |
The median graph has been shown to be a good choice to infer a representative of a set of graphs. It has been successfully applied to graph-based classification and clustering. Nevertheless, its computation is extremely complex. Several approaches have been presented up to now based on different strategies. In this paper we present a new approximate recursive algorithm for median graph computation based on graph embedding into vector spaces. Preliminary experiments on three databases show that this new approach is able to obtain better medians than the previous existing approaches. |
|
| |
Address |
Venice, Italy |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
Springer Berlin Heidelberg |
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 |
978-3-642-02123-7 |
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
GBR |
|
| |
Notes |
DAG |
Approved |
no |
|
| |
Call Number |
DAG @ dag @ FKV2009 |
Serial |
1173 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Andreas Fischer; Ching Y. Suen; Volkmar Frinken; Kaspar Riesen; Horst Bunke |
|
| |
Title |
A Fast Matching Algorithm for Graph-Based Handwriting Recognition |
Type |
Conference Article |
| |
Year |
2013 |
Publication |
9th IAPR – TC15 Workshop on Graph-based Representation in Pattern Recognition |
Abbreviated Journal |
|
|
| |
Volume |
7877 |
Issue |
|
Pages |
194-203 |
|
| |
Keywords |
|
|
| |
Abstract |
The recognition of unconstrained handwriting images is usually based on vectorial representation and statistical classification. Despite their high representational power, graphs are rarely used in this field due to a lack of efficient graph-based recognition methods. Recently, graph similarity features have been proposed to bridge the gap between structural representation and statistical classification by means of vector space embedding. This approach has shown a high performance in terms of accuracy but had shortcomings in terms of computational speed. The time complexity of the Hungarian algorithm that is used to approximate the edit distance between two handwriting graphs is demanding for a real-world scenario. In this paper, we propose a faster graph matching algorithm which is derived from the Hausdorff distance. On the historical Parzival database it is demonstrated that the proposed method achieves a speedup factor of 12.9 without significant loss in recognition accuracy. |
|
| |
Address |
Vienna; Austria; May 2013 |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
Springer Berlin Heidelberg |
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 |
978-3-642-38220-8 |
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
GBR |
|
| |
Notes |
DAG; 600.045; 605.203 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ FSF2013 |
Serial |
2294 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Josep Llados |
|
| |
Title |
The 5G of Document Intelligence |
Type |
Conference Article |
| |
Year |
2021 |
Publication |
3rd Workshop on Future of Document Analysis and Recognition |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
|
|
| |
Keywords |
|
|
| |
Abstract |
|
|
| |
Address |
Lausanne; Suissa; September 2021 |
|
| |
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 |
FDAR |
|
| |
Notes |
DAG |
Approved |
no |
|
| |
Call Number |
Admin @ si @ |
Serial |
3677 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Fernando Vilariño; Dimosthenis Karatzas |
|
| |
Title |
A Living Lab approach for Citizen Science in Libraries |
Type |
Conference Article |
| |
Year |
2016 |
Publication |
1st International ECSA Conference |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
|
|
| |
Keywords |
|
|
| |
Abstract |
|
|
| |
Address |
Berlin; Germany; May 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 |
ECSA |
|
| |
Notes |
MV; DAG; 600.084; 600.097;SIAI |
Approved |
no |
|
| |
Call Number |
Admin @ si @ViK2016 |
Serial |
2804 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Mohammed Al Rawi; Dimosthenis Karatzas |
|
| |
Title |
On the Labeling Correctness in Computer Vision Datasets |
Type |
Conference Article |
| |
Year |
2018 |
Publication |
Proceedings of the Workshop on Interactive Adaptive Learning, co-located with European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
|
|
| |
Keywords |
|
|
| |
Abstract |
Image datasets have heavily been used to build computer vision systems.
These datasets are either manually or automatically labeled, which is a
problem as both labeling methods are prone to errors. To investigate this problem, we use a majority voting ensemble that combines the results from several Convolutional Neural Networks (CNNs). Majority voting ensembles not only enhance the overall performance, but can also be used to estimate the confidence level of each sample. We also examined Softmax as another form to estimate posterior probability. We have designed various experiments with a range of different ensembles built from one or different, or temporal/snapshot CNNs, which have been trained multiple times stochastically. We analyzed CIFAR10, CIFAR100, EMNIST, and SVHN datasets and we found quite a few incorrect
labels, both in the training and testing sets. We also present detailed confidence analysis on these datasets and we found that the ensemble is better than the Softmax when used estimate the per-sample confidence. This work thus proposes an approach that can be used to scrutinize and verify the labeling of computer vision datasets, which can later be applied to weakly/semi-supervised learning. We propose a measure, based on the Odds-Ratio, to quantify how many of these incorrectly classified labels are actually incorrectly labeled and how many of these are confusing. The proposed methods are easily scalable to larger datasets, like ImageNet, LSUN and SUN, as each CNN instance is trained for 60 epochs; or even faster, by implementing a temporal (snapshot) ensemble. |
|
| |
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 |
ECML-PKDDW |
|
| |
Notes |
DAG; 600.121; 600.129 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ RaK2018 |
Serial |
3144 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Marçal Rusiñol; David Aldavert; Dimosthenis Karatzas; Ricardo Toledo; Josep Llados |
|
| |
Title |
Interactive Trademark Image Retrieval by Fusing Semantic and Visual Content. Advances in Information Retrieval |
Type |
Conference Article |
| |
Year |
2011 |
Publication |
33rd European Conference on Information Retrieval |
Abbreviated Journal |
|
|
| |
Volume |
6611 |
Issue |
|
Pages |
314-325 |
|
| |
Keywords |
|
|
| |
Abstract |
In this paper we propose an efficient queried-by-example retrieval system which is able to retrieve trademark images by similarity from patent and trademark offices' digital libraries. Logo images are described by both their semantic content, by means of the Vienna codes, and their visual contents, by using shape and color as visual cues. The trademark descriptors are then indexed by a locality-sensitive hashing data structure aiming to perform approximate k-NN search in high dimensional spaces in sub-linear time. The resulting ranked lists are combined by using the Condorcet method and a relevance feedback step helps to iteratively revise the query and refine the obtained results. The experiments demonstrate the effectiveness and efficiency of this system on a realistic and large dataset. |
|
| |
Address |
Dublin, Ireland |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
Springer |
Place of Publication |
Berlin |
Editor |
P. Clough; C. Foley; C. Gurrin; G.J.F. Jones; W. Kraaij; H. Lee; V. Murdoch |
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
978-3-642-20160-8 |
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
ECIR |
|
| |
Notes |
DAG; RV;ADAS |
Approved |
no |
|
| |
Call Number |
Admin @ si @ RAK2011 |
Serial |
1737 |
|
| Permanent link to this record |
