|
Lluis Gomez, Y. Patel, Marçal Rusiñol, C.V. Jawahar and Dimosthenis Karatzas. 2017. Self‐supervised learning of visual features through embedding images into text topic spaces. 30th IEEE Conference on Computer Vision and Pattern Recognition.
Abstract: End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of freely available multi-modal content to train computer vision algorithms without human supervision. We put forward the idea of performing self-supervised learning of visual features by mining a large scale corpus of multi-modal (text and image) documents. We show that discriminative visual features can be learnt efficiently by training a CNN to predict the semantic context in which a particular image is more probable to appear as an illustration. For this we leverage the hidden semantic structures discovered in the text corpus with a well-known topic modeling technique. Our experiments demonstrate state of the art performance in image classification, object detection, and multi-modal retrieval compared to recent self-supervised or natural-supervised approaches.
|
|
|
Ruben Tito, Dimosthenis Karatzas and Ernest Valveny. 2023. Hierarchical multimodal transformers for Multipage DocVQA. PR, 144(109834).
Abstract: Existing work on DocVQA only considers single-page documents. However, in real applications documents are mostly composed of multiple pages that should be processed altogether. In this work, we propose a new multimodal hierarchical method Hi-VT5, that overcomes the limitations of current methods to process long multipage documents. In contrast to previous hierarchical methods that focus on different semantic granularity (He et al., 2021) or different subtasks (Zhou et al., 2022) used in image classification. Our method is a hierarchical transformer architecture where the encoder learns to summarize the most relevant information of every page and then, the decoder uses this summarized representation to generate the final answer, following a bottom-up approach. Moreover, due to the lack of multipage DocVQA datasets, we also introduce MP-DocVQA, an extension of SP-DocVQA where questions are posed over multipage documents instead of single pages. Through extensive experimentation, we demonstrate that Hi-VT5 is able, in a single stage, to answer the questions and provide the page that contains the answer, which can be used as a kind of explainability measure.
|
|
|
Ali Furkan Biten, Lluis Gomez and Dimosthenis Karatzas. 2022. Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning. Winter Conference on Applications of Computer Vision.1381–1390.
Abstract: Explaining an image with missing or non-existent objects is known as object bias (hallucination) in image captioning. This behaviour is quite common in the state-of-the-art captioning models which is not desirable by humans. To decrease the object hallucination in captioning, we propose three simple yet efficient training augmentation method for sentences which requires no new training data or increase
in the model size. By extensive analysis, we show that the proposed methods can significantly diminish our models’ object bias on hallucination metrics. Moreover, we experimentally demonstrate that our methods decrease the dependency on the visual features. All of our code, configuration files and model weights are available online.
Keywords: Measurement; Training; Visualization; Analytical models; Computer vision; Computational modeling; Training data
|
|
|
Andreas Fischer, Volkmar Frinken, Horst Bunke and Ching Y. Suen. 2013. Improving HMM-Based Keyword Spotting with Character Language Models. 12th International Conference on Document Analysis and Recognition.506–510.
Abstract: Facing high error rates and slow recognition speed for full text transcription of unconstrained handwriting images, keyword spotting is a promising alternative to locate specific search terms within scanned document images. We have previously proposed a learning-based method for keyword spotting using character hidden Markov models that showed a high performance when compared with traditional template image matching. In the lexicon-free approach pursued, only the text appearance was taken into account for recognition. In this paper, we integrate character n-gram language models into the spotting system in order to provide an additional language context. On the modern IAM database as well as the historical George Washington database, we demonstrate that character language models significantly improve the spotting performance.
|
|
|
Youssef El Rhabi, Simon Loic and Brun Luc. 2015. Estimation de la pose d’une caméra à partir d’un flux vidéo en s’approchant du temps réel. 15ème édition d'ORASIS, journées francophones des jeunes chercheurs en vision par ordinateur ORASIS2015.
Abstract: Finding a way to estimate quickly and robustly the pose of an image is essential in augmented reality. Here we will discuss the approach we chose in order to get closer to real time by using SIFT points [4]. We propose a method based on filtering both SIFT points and images on which to focus on. Hence we will focus on relevant data.
Keywords: Augmented Reality; SFM; SLAM; real time pose computation; 2D/3D registration
|
|
|
Pau Riba. 2020. Distilling Structure from Imagery: Graph-based Models for the Interpretation of Document Images. (Ph.D. thesis, Ediciones Graficas Rey.)
Abstract: From its early stages, the community of Pattern Recognition and Computer Vision has considered the importance of leveraging the structural information when understanding images. Usually, graphs have been proposed as a suitable model to represent this kind of information due to their flexibility and representational power able to codify both, the components, objects, or entities and their pairwise relationship. Even though graphs have been successfully applied to a huge variety of tasks, as a result of their symbolic and relational nature, graphs have always suffered from some limitations compared to statistical approaches. Indeed, some trivial mathematical operations do not have an equivalence in the graph domain. For instance, in the core of many pattern recognition applications, there is a need to compare two objects. This operation, which is trivial when considering feature vectors defined in \(\mathbb{R}^n\), is not properly defined for graphs.
In this thesis, we have investigated the importance of the structural information from two perspectives, the traditional graph-based methods and the new advances on Geometric Deep Learning. On the one hand, we explore the problem of defining a graph representation and how to deal with it on a large scale and noisy scenario. On the other hand, Graph Neural Networks are proposed to first redefine a Graph Edit Distance methodologies as a metric learning problem, and second, to apply them in a real use case scenario for the detection of repetitive patterns which define tables in invoice documents. As experimental framework, we have validated the different methodological contributions in the domain of Document Image Analysis and Recognition.
|
|
|
Andrea Gemelli, Sanket Biswas, Enrico Civitelli, Josep Llados and Simone Marinai. 2022. Doc2Graph: A Task Agnostic Document Understanding Framework Based on Graph Neural Networks. 17th European Conference on Computer Vision Workshops.329–344. (LNCS.)
Abstract: Geometric Deep Learning has recently attracted significant interest in a wide range of machine learning fields, including document analysis. The application of Graph Neural Networks (GNNs) has become crucial in various document-related tasks since they can unravel important structural patterns, fundamental in key information extraction processes. Previous works in the literature propose task-driven models and do not take into account the full power of graphs. We propose Doc2Graph, a task-agnostic document understanding framework based on a GNN model, to solve different tasks given different types of documents. We evaluated our approach on two challenging datasets for key information extraction in form understanding, invoice layout analysis and table detection.
|
|
|
Miquel Ferrer, Ernest Valveny and F. Serratosa. 2009. Median Graph Computation by means of a Genetic Approach Based on Minimum Common Supergraph and Maximum Common Subraph. 4th Iberian Conference on Pattern Recognition and Image Analysis. Springer Berlin Heidelberg, 346–353. (LNCS.)
Abstract: Given a set of graphs, the median graph has been theoretically presented as a useful concept to infer a representative of the set. However, the computation of the median graph is a highly complex task and its practical application has been very limited up to now. In this work we present a new genetic algorithm for the median graph computation. A set of experiments on real data, where none of the existing algorithms for the median graph computation could be applied up to now due to their computational complexity, show that we obtain good approximations of the median graph. Finally, we use the median graph in a real nearest neighbour classification showing that it leaves the box of the only-theoretical concepts and demonstrating, from a practical point of view, that can be a useful tool to represent a set of graphs.
|
|
|
Miquel Ferrer, Ernest Valveny and F. Serratosa. 2009. Median Graphs: A Genetic Approach based on New Theoretical Properties. PR, 42(9), 2003–2012.
Abstract: Given a set of graphs, the median graph has been theoretically presented as a useful concept to infer a representative of the set. However, the computation of the median graph is a highly complex task and its practical application has been very limited up to now. In this work we present two major contributions. On one side, and from a theoretical point of view, we show new theoretical properties of the median graph. On the other side, using these new properties, we present a new approximate algorithm based on the genetic search, that improves the computation of the median graph. Finally, we perform a set of experiments on real data, where none of the existing algorithms for the median graph computation could be applied up to now due to their computational complexity. With these results, we show how the concept of the median graph can be used in real applications and leaves the box of the only-theoretical concepts, demonstrating, from a practical point of view, that can be a useful tool to represent a set of graphs.
Keywords: Median graph; Genetic search; Maximum common subgraph; Graph matching; Structural pattern recognition
|
|
|
Pau Riba, Andreas Fischer, Josep Llados and Alicia Fornes. 2018. Learning Graph Distances with Message Passing Neural Networks. 24th International Conference on Pattern Recognition.2239–2244.
Abstract: Graph representations have been widely used in pattern recognition thanks to their powerful representation formalism and rich theoretical background. A number of error-tolerant graph matching algorithms such as graph edit distance have been proposed for computing a distance between two labelled graphs. However, they typically suffer from a high
computational complexity, which makes it difficult to apply
these matching algorithms in a real scenario. In this paper, we propose an efficient graph distance based on the emerging field of geometric deep learning. Our method employs a message passing neural network to capture the graph structure and learns a metric with a siamese network approach. The performance of the proposed graph distance is validated in two application cases, graph classification and graph retrieval of handwritten words, and shows a promising performance when compared with
(approximate) graph edit distance benchmarks.
Keywords: ★Best Paper Award★
|
|