Alvaro Peris, Marc Bolaños, Petia Radeva, & Francisco Casacuberta. (2016). Video Description Using Bidirectional Recurrent Neural Networks. In 25th International Conference on Artificial Neural Networks (Vol. 2, pp. 3–11).
Abstract: Although traditionally used in the machine translation field, the encoder-decoder framework has been recently applied for the generation of video and image descriptions. The combination of Convolutional and Recurrent Neural Networks in these models has proven to outperform the previous state of the art, obtaining more accurate video descriptions. In this work we propose pushing further this model by introducing two contributions into the encoding stage. First, producing richer image representations by combining object and location information from Convolutional Neural Networks and second, introducing Bidirectional Recurrent Neural Networks for capturing both forward and backward temporal relationships in the input frames.
Keywords: Video description; Neural Machine Translation; Birectional Recurrent Neural Networks; LSTM; Convolutional Neural Networks
|
Giuseppe De Gregorio, Sanket Biswas, Mohamed Ali Souibgui, Asma Bensalah, Josep Llados, Alicia Fornes, et al. (2022). A Few Shot Multi-representation Approach for N-Gram Spotting in Historical Manuscripts. In Frontiers in Handwriting Recognition. International Conference on Frontiers in Handwriting Recognition (ICFHR2022) (Vol. 13639, pp. 3–12). LNCS.
Abstract: Despite recent advances in automatic text recognition, the performance remains moderate when it comes to historical manuscripts. This is mainly because of the scarcity of available labelled data to train the data-hungry Handwritten Text Recognition (HTR) models. The Keyword Spotting System (KWS) provides a valid alternative to HTR due to the reduction in error rate, but it is usually limited to a closed reference vocabulary. In this paper, we propose a few-shot learning paradigm for spotting sequences of a few characters (N-gram) that requires a small amount of labelled training data. We exhibit that recognition of important n-grams could reduce the system’s dependency on vocabulary. In this case, an out-of-vocabulary (OOV) word in an input handwritten line image could be a sequence of n-grams that belong to the lexicon. An extensive experimental evaluation of our proposed multi-representation approach was carried out on a subset of Bentham’s historical manuscript collections to obtain some really promising results in this direction.
Keywords: N-gram spotting; Few-shot learning; Multimodal understanding; Historical handwritten collections
|
Francesc Net, Marc Folia, Pep Casals, & Lluis Gomez. (2023). Transductive Learning for Near-Duplicate Image Detection in Scanned Photo Collections. In 17th International Conference on Document Analysis and Recognition (Vol. 14191, pp. 3–17). LNCS.
Abstract: This paper presents a comparative study of near-duplicate image detection techniques in a real-world use case scenario, where a document management company is commissioned to manually annotate a collection of scanned photographs. Detecting duplicate and near-duplicate photographs can reduce the time spent on manual annotation by archivists. This real use case differs from laboratory settings as the deployment dataset is available in advance, allowing the use of transductive learning. We propose a transductive learning approach that leverages state-of-the-art deep learning architectures such as convolutional neural networks (CNNs) and Vision Transformers (ViTs). Our approach involves pre-training a deep neural network on a large dataset and then fine-tuning the network on the unlabeled target collection with self-supervised learning. The results show that the proposed approach outperforms the baseline methods in the task of near-duplicate image detection in the UKBench and an in-house private dataset.
Keywords: Image deduplication; Near-duplicate images detection; Transductive Learning; Photographic Archives; Deep Learning
|
Albert Tatjer, Bhalaji Nagarajan, Ricardo Marques, & Petia Radeva. (2023). CCLM: Class-Conditional Label Noise Modelling. In 11th Iberian Conference on Pattern Recognition and Image Analysis (Vol. 14062, pp. 3–14). LNCS.
Abstract: The performance of deep neural networks highly depends on the quality and volume of the training data. However, cost-effective labelling processes such as crowdsourcing and web crawling often lead to data with noisy (i.e., wrong) labels. Making models robust to this label noise is thus of prime importance. A common approach is using loss distributions to model the label noise. However, the robustness of these methods highly depends on the accuracy of the division of training set into clean and noisy samples. In this work, we dive in this research direction highlighting the existing problem of treating this distribution globally and propose a class-conditional approach to split the clean and noisy samples. We apply our approach to the popular DivideMix algorithm and show how the local treatment fares better with respect to the global treatment of loss distribution. We validate our hypothesis on two popular benchmark datasets and show substantial improvements over the baseline experiments. We further analyze the effectiveness of the proposal using two different metrics – Noise Division Accuracy and Classiness.
|
Angel Sappa, Niki Aifanti, N. Grammalidis, & Sotiris Malassiotis. (2004). Advances in Vision-Based Human Body Modeling. In N. Sarris and M. Strintzis. (Ed.), 3D Modeling & Animation: Systhesis and Analysis Techniques for the Human Body (pp. 1–26).
|
Josep Llados, & Dorothea Blostein. (2007). Special Issue on Graphics Recognition. IJDAR - International Journal on Document Analysis and Recognition, 1–2.
|
Maya Dimitrova, Ch. Roumenin, Siya Lozanova, David Rotger, & Petia Radeva. (2007). An Interface System Based on Multimodal Principle for Cardiological Diagnosis Assistance. In International Conference On Computer Systems And Technologies (Vol. IIIB.4, 1–6).
|
Eduard Vazquez, Joost Van de Weijer, & Ramon Baldrich. (2008). Image Segmentation in the Presence of Shadows and Highligts. In 10th European Conference on Computer Vision (Vol. 5305, 1–14). LNCS.
|
Agata Lapedriza, David Masip, & Jordi Vitria. (2008). On the Use of Independent Tasks for Face Recognition. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (1–6).
|
Ariel Amato, Mikhail Mozerov, Ivan Huerta, Jordi Gonzalez, & Juan J. Villanueva. (2008). ackground Subtraction Technique Based on Chromaticity and Intensity Patterns. In 19th International Conference on Pattern Recognition, (1–4).
|
Murad Al Haj, Francisco Javier Orozco, Jordi Gonzalez, & Juan J. Villanueva. (2008). Automatic Face and Facial Features Initialization for Robust and Accurate Tracking. In 19th International Conference on Pattern Recognition. (1– 4).
|
Santiago Segui, Laura Igual, & Jordi Vitria. (2010). Weighted Bagging for Graph based One-Class Classifiers. In 9th International Workshop on Multiple Classifier Systems (Vol. 5997, pp. 1–10). LNCS. Springer Berlin Heidelberg.
Abstract: Most conventional learning algorithms require both positive and negative training data for achieving accurate classification results. However, the problem of learning classifiers from only positive data arises in many applications where negative data are too costly, difficult to obtain, or not available at all. Minimum Spanning Tree Class Descriptor (MSTCD) was presented as a method that achieves better accuracies than other one-class classifiers in high dimensional data. However, the presence of outliers in the target class severely harms the performance of this classifier. In this paper we propose two bagging strategies for MSTCD that reduce the influence of outliers in training data. We show the improved performance on both real and artificially contaminated data.
|
Jose Seabra, F. Javier Sanchez, Francesco Ciompi, & Petia Radeva. (2010). Ultrasonographic Plaque Characterization using a Rayleigh Mixture Model. In 7th IEEE International Symposium on Biomedical Imaging (1–4).
Abstract: From Nano to Macro
A correct modelling of tissue morphology is determinant for the identification of vulnerable plaques. This paper aims at describing the plaque composition by means of a Rayleigh Mixture Model applied to ultrasonic data. The effectiveness of using a mixture of distributions is established through synthetic and real ultrasonic data samples. Furthermore, the proposed mixture model is used in a plaque classification problem in Intravascular Ultrasound (IVUS) images of coronary plaques. A classifier tested on a set of 67 in-vitro plaques, yields an overall accuracy of 86% and sensitivity of 92%, 94% and 82%, for fibrotic, calcified and lipidic tissues, respectively. These results strongly suggest that different plaques types can be distinguished by means of the coefficients and Rayleigh parameters of the mixture distribution.
|
Herve Locteau, Sebastien Mace, Ernest Valveny, & Salvatore Tabbone. (2010). Extraction des pieces de un plan de habitation. In Colloque Internacional Francophone de l´Ecrit et le Document (1–12).
Abstract: In this article, a method to extract the rooms of an architectural floor plan image is described. We first present a line detection algorithm to extract long lines in the image. Those lines are analyzed to identify the existing walls. From this point, room extraction can be seen as a classical segmentation task for which each region corresponds to a room. The chosen resolution strategy consists in recursively decomposing the image until getting nearly convex regions. The notion of convexity is difficult to quantify, and the selection of separation lines can also be rough. Thus, we take advantage of knowledge associated to architectural floor plans in order to obtain mainly rectangular rooms. Preliminary tests on a set of real documents show promising results.
|
Xavier Otazu, C. Alejandro Parraga, & Maria Vanrell. (2010). Towards a unified chromatic inducction model. VSS - Journal of Vision, 10(12:5), 1–24.
Abstract: In a previous work (X. Otazu, M. Vanrell, & C. A. Párraga, 2008b), we showed how several brightness induction effects can be predicted using a simple multiresolution wavelet model (BIWaM). Here we present a new model for chromatic induction processes (termed Chromatic Induction Wavelet Model or CIWaM), which is also implemented on a multiresolution framework and based on similar assumptions related to the spatial frequency and the contrast surround energy of the stimulus. The CIWaM can be interpreted as a very simple extension of the BIWaM to the chromatic channels, which in our case are defined in the MacLeod-Boynton (lsY) color space. This new model allows us to unify both chromatic assimilation and chromatic contrast effects in a single mathematical formulation. The predictions of the CIWaM were tested by means of several color and brightness induction experiments, which showed an acceptable agreement between model predictions and psychophysical data.
Keywords: Visual system; Color induction; Wavelet transform
|