|
Sergio Vera, Miguel Angel Gonzalez Ballester, & Debora Gil. (2015). A Novel Cochlear Reference Frame Based On The Laplace Equation. In 29th international Congress and Exhibition on Computer Assisted Radiology and Surgery (Vol. 10, pp. 1–312).
|
|
Arash Akbarinia, & C. Alejandro Parraga. (2015). Biologically Plausible Colour Naming Model. In European Conference on Visual Perception ECVP2015.
|
|
Fernando Alonso, Xavier Baro, Sergio Escalera, Jordi Gonzalez, Martha Mackay, & Anna Serrahima. (2016). CARE RESPITE: TAKING CARE OF THE CAREGIVERS, Theme 5 The Strategic use of Mobile and Digital Health and Care Solutions. In 16th International Conference for Integrated Care.
|
|
Dipam Goswami, Yuyang Liu, Bartlomiej Twardowski, & Joost Van de Weijer. (2023). FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning. In 37th Annual Conference on Neural Information Processing Systems.
|
|
Kai Wang, Fei Yang, Shiqi Yang, Muhammad Atif Butt, & Joost Van de Weijer. (2023). Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing. In 37th Annual Conference on Neural Information Processing Systems.
|
Laura Igual, Xavier Perez Sala, Sergio Escalera, Cecilio Angulo, & Fernando De la Torre. (2014). Continuous Generalized Procrustes Analysis. PR - Pattern Recognition, 47(2), 659–671.
Abstract: PR4883, PII: S0031-3203(13)00327-0
Two-dimensional shape models have been successfully applied to solve many problems in computer vision, such as object tracking, recognition, and segmentation. Typically, 2D shape models are learned from a discrete set of image landmarks (corresponding to projection of 3D points of an object), after applying Generalized Procustes Analysis (GPA) to remove 2D rigid transformations. However, the
standard GPA process suffers from three main limitations. Firstly, the 2D training samples do not necessarily cover a uniform sampling of all the 3D transformations of an object. This can bias the estimate of the shape model. Secondly, it can be computationally expensive to learn the shape model by sampling 3D transformations. Thirdly, standard GPA methods use only one reference shape, which can might be insufficient to capture large structural variability of some objects.
To address these drawbacks, this paper proposes continuous generalized Procrustes analysis (CGPA).
CGPA uses a continuous formulation that avoids the need to generate 2D projections from all the rigid 3D transformations. It builds an efficient (in space and time) non-biased 2D shape model from a set of 3D model of objects. A major challenge in CGPA is the need to integrate over the space of 3D rotations, especially when the rotations are parameterized with Euler angles. To address this problem, we introduce the use of the Haar measure. Finally, we extended CGPA to incorporate several reference shapes. Experimental results on synthetic and real experiments show the benefits of CGPA over GPA.
Keywords: Procrustes analysis; 2D shape model; Continuous approach
|
F.Negin, Pau Rodriguez, M.Koperski, A.Kerboua, Jordi Gonzalez, J.Bourgeois, et al. (2018). PRAXIS: Towards automatic cognitive assessment using gesture recognition. ESWA - Expert Systems with Applications, 106, 21–35.
Abstract: Praxis test is a gesture-based diagnostic test which has been accepted as diagnostically indicative of cortical pathologies such as Alzheimer’s disease. Despite being simple, this test is oftentimes skipped by the clinicians. In this paper, we propose a novel framework to investigate the potential of static and dynamic upper-body gestures based on the Praxis test and their potential in a medical framework to automatize the test procedures for computer-assisted cognitive assessment of older adults.
In order to carry out gesture recognition as well as correctness assessment of the performances we have recollected a novel challenging RGB-D gesture video dataset recorded by Kinect v2, which contains 29 specific gestures suggested by clinicians and recorded from both experts and patients performing the gesture set. Moreover, we propose a framework to learn the dynamics of upper-body gestures, considering the videos as sequences of short-term clips of gestures. Our approach first uses body part detection to extract image patches surrounding the hands and then, by means of a fine-tuned convolutional neural network (CNN) model, it learns deep hand features which are then linked to a long short-term memory to capture the temporal dependencies between video frames.
We report the results of four developed methods using different modalities. The experiments show effectiveness of our deep learning based approach in gesture recognition and performance assessment tasks. Satisfaction of clinicians from the assessment reports indicates the impact of framework corresponding to the diagnosis.
|
Maurizio Mencuccini, Jordi Martinez-Vilalta, Josep Piñol, Lasse Loepfe, Mireia Burnat, Xavier Alvarez, et al. (2010). A quantitative and statistically robust method for the determination of xylem conduit spatial distribution. AJB - American Journal of Botany, 97(8), 1247–1259.
Abstract: Premise of the study: Because of their limited length, xylem conduits need to connect to each other to maintain water transport from roots to leaves. Conduit spatial distribution in a cross section plays an important role in aiding this connectivity. While indices of conduit spatial distribution already exist, they are not well defined statistically. * Methods: We used point pattern analysis to derive new spatial indices. One hundred and five cross-sectional images from different species were transformed into binary images. The resulting point patterns, based on the locations of the conduit centers-of-area, were analyzed to determine whether they departed from randomness. Conduit distribution was then modeled using a spatially explicit stochastic model. * Key results: The presence of conduit randomness, uniformity, or aggregation depended on the spatial scale of the analysis. The large majority of the images showed patterns significantly different from randomness at least at one spatial scale. A strong phylogenetic signal was detected in the spatial variables. * Conclusions: Conduit spatial arrangement has been largely conserved during evolution, especially at small spatial scales. Species in which conduits were aggregated in clusters had a lower conduit density compared to those with uniform distribution. Statistically sound spatial indices must be employed as an aid in the characterization of distributional patterns across species and in models of xylem water transport. Point pattern analysis is a very useful tool in identifying spatial patterns.
Keywords: Geyer; hydraulic conductivity; point pattern analysis; Ripley; Spatstat; vessel clusters; xylem anatomy; xylem network
|
Enric Marti, Jaume Rocarias, Debora Gil, Aura Hernandez-Sabate, Jaume Garcia, Carme Julia, et al. (2009). Uso de recursos virtuales en Aprendizaje Basado en Proyectos. Una experiencia en la asignatura de Gráficos por Computador. Vigo (Spain).
Abstract: Presentamos una experiencia en Aprendizaje Basado en Proyectos (ABP) realizada los últimos cuatro años en Gráficos por Computador 2, asignatura de Ingeniería Informática, de la Escuela Técnica Superior de Ingeniería (ETSE) de la Universidad Autónoma de Barcelona (UAB). Utilizamos un entorno Moodle adaptado por nosotros llamado Caronte para poder gestionar la documentación generada en ABP. Primero se presenta la asignatura, basada en dos itinerarios para cursarla: ABP y TPPE (Teoría, Problemas, Prácticas, Examen). El alumno debe escoger uno de ellos. Ambos itinerarios generan una cantidad importante de documentación (entregas de trabajos y prácticas, correcciones, ejercicios, etc.) a gestionar. En la comunicación presentamos los espacios electrónicos Moodle de ambos itinerarios. Finalmente, mostramos los resultados de encuestas realizadas a los alumnos para finalmente exponer las conclusiones de la experiencia en ABP y el uso de Moodle, así como plantear mejoras y temas de discusión.
Keywords: Aprendizaje Basado en Proyectos; Project Based Learning; Aprendizaje Cooperativo; Recursos Virtuales para el Aprendizaje Cooperativo; Moodle
|
Josep Llados, Jaime Lopez-Krahe, & Enric Marti. (1997). A system to understand hand-drawn floor plans using subgraph isomorphism and Hough transform. In Machine Vision and Applications (Vol. 10, pp. 150–158).
Abstract: Presently, man-machine interface development is a widespread research activity. A system to understand hand drawn architectural drawings in a CAD environment is presented in this paper. To understand a document, we have to identify its building elements and their structural properties. An attributed graph structure is chosen as a symbolic representation of the input document and the patterns to recognize in it. An inexact subgraph isomorphism procedure using relaxation labeling techniques is performed. In this paper we focus on how to speed up the matching. There is a building element, the walls, characterized by a hatching pattern. Using a straight line Hough transform (SLHT)-based method, we recognize this pattern, characterized by parallel straight lines, and remove from the input graph the edges belonging to this pattern. The isomorphism is then applied to the remainder of the input graph. When all the building elements have been recognized, the document is redrawn, correcting the inaccurate strokes obtained from a hand-drawn input.
Keywords: Line drawings – Hough transform – Graph matching – CAD systems – Graphics recognition
|
Ali Furkan Biten, Ruben Tito, Lluis Gomez, Ernest Valveny, & Dimosthenis Karatzas. (2022). OCR-IDL: OCR Annotations for Industry Document Library Dataset. In ECCV Workshop on Text in Everything.
Abstract: Pretraining has proven successful in Document Intelligence tasks where deluge of documents are used to pretrain the models only later to be finetuned on downstream tasks. One of the problems of the pretraining approaches is the inconsistent usage of pretraining data with different OCR engines leading to incomparable results between models. In other words, it is not obvious whether the performance gain is coming from diverse usage of amount of data and distinct OCR engines or from the proposed models. To remedy the problem, we make public the OCR annotations for IDL documents using commercial OCR engine given their superior performance over open source OCR models. The contributed dataset (OCR-IDL) has an estimated monetary value over 20K US$. It is our hope that OCR-IDL can be a starting point for future works on Document Intelligence. All of our data and its collection process with the annotations can be found in this https URL.
|
David Berga, & Xavier Otazu. (2020). Modeling Bottom-Up and Top-Down Attention with a Neurodynamic Model of V1. NEUCOM - Neurocomputing, 417, 270–289.
Abstract: Previous studies suggested that lateral interactions of V1 cells are responsible, among other visual effects, of bottom-up visual attention (alternatively named visual salience or saliency). Our objective is to mimic these connections with a neurodynamic network of firing-rate neurons in order to predict visual attention. Early visual subcortical processes (i.e. retinal and thalamic) are functionally simulated. An implementation of the cortical magnification function is included to define the retinotopical projections towards V1, processing neuronal activity for each distinct view during scene observation. Novel computational definitions of top-down inhibition (in terms of inhibition of return, oculomotor and selection mechanisms), are also proposed to predict attention in Free-Viewing and Visual Search tasks. Results show that our model outpeforms other biologically inspired models of saliency prediction while predicting visual saccade sequences with the same model. We also show how temporal and spatial characteristics of saccade amplitude and inhibition of return can improve prediction of saccades, as well as how distinct search strategies (in terms of feature-selective or category-specific inhibition) can predict attention at distinct image contexts.
|
David Berga, C. Wloka, & JK. Tsotsos. (2019). Modeling task influences for saccade sequence and visual relevance prediction. JV - Journal of Vision, 19(10), 106c.
Abstract: Previous work from Wloka et al. (2017) presented the Selective Tuning Attentive Reference model Fixation Controller (STAR-FC), an active vision model for saccade prediction. Although the model is able to efficiently predict saccades during free-viewing, it is well known that stimulus and task instructions can strongly affect eye movement patterns (Yarbus, 1967). These factors are considered in previous Selective Tuning architectures (Tsotsos and Kruijne, 2014)(Tsotsos, Kotseruba and Wloka, 2016)(Rosenfeld, Biparva & Tsotsos 2017), proposing a way to combine bottom-up and top-down contributions to fixation and saccade programming. In particular, task priming has been shown to be crucial to the deployment of eye movements, involving interactions between brain areas related to goal-directed behavior, working and long-term memory in combination with stimulus-driven eye movement neuronal correlates. Initial theories and models of these influences include (Rao, Zelinsky, Hayhoe and Ballard, 2002)(Navalpakkam and Itti, 2005)(Huang and Pashler, 2007) and show distinct ways to process the task requirements in combination with bottom-up attention. In this study we extend the STAR-FC with novel computational definitions of Long-Term Memory, Visual Task Executive and a Task Relevance Map. With these modules we are able to use textual instructions in order to guide the model to attend to specific categories of objects and/or places in the scene. We have designed our memory model by processing a hierarchy of visual features learned from salient object detection datasets. The relationship between the executive task instructions and the memory representations has been specified using a tree of semantic similarities between the learned features and the object category labels. Results reveal that by using this model, the resulting relevance maps and predicted saccades have a higher probability to fall inside the salient regions depending on the distinct task instructions.
|
Chenshen Wu, Luis Herranz, Xialei Liu, Joost Van de Weijer, & Bogdan Raducanu. (2018). Memory Replay GANs: Learning to Generate New Categories without Forgetting. In 32nd Annual Conference on Neural Information Processing Systems (pp. 5966–5976).
Abstract: Previous works on sequential learning address the problem of forgetting in discriminative models. In this paper we consider the case of generative models. In particular, we investigate generative adversarial networks (GANs) in the task of learning new categories in a sequential fashion. We first show that sequential fine tuning renders the network unable to properly generate images from previous categories (ie forgetting). Addressing this problem, we propose Memory Replay GANs (MeRGANs), a conditional GAN framework that integrates a memory replay generator. We study two methods to prevent forgetting by leveraging these replays, namely joint training with replay and replay alignment. Qualitative and quantitative experimental results in MNIST, SVHN and LSUN datasets show that our memory replay approach can generate competitive images while significantly mitigating the forgetting of previous categories.
|
Carlos David Martinez Hinarejos, Josep Llados, Alicia Fornes, Francisco Casacuberta, Lluis de Las Heras, Joan Mas, et al. (2016). Context, multimodality, and user collaboration in handwritten text processing: the CoMUN-HaT project. In 3rd IberSPEECH.
Abstract: Processing of handwritten documents is a task that is of wide interest for many
purposes, such as those related to preserve cultural heritage. Handwritten text recognition techniques have been successfully applied during the last decade to obtain transcriptions of handwritten documents, and keyword spotting techniques have been applied for searching specific terms in image collections of handwritten documents. However, results on transcription and indexing are far from perfect. In this framework, the use of new data sources arises as a new paradigm that will allow for a better transcription and indexing of handwritten documents. Three main different data sources could be considered: context of the document (style, writer, historical time, topics,. . . ), multimodal data (representations of the document in a different modality, such as the speech signal of the dictation of the text), and user feedback (corrections, amendments,. . . ). The CoMUN-HaT project aims at the integration of these different data sources into the transcription and indexing task for handwritten documents: the use of context derived from the analysis of the documents, how multimodality can aid the recognition process to obtain more accurate transcriptions (including transcription in a modern version of the language), and integration into a userin-the-loop assisted text transcription framework. This will be reflected in the construction of a transcription and indexing platform that can be used by both professional and nonprofessional users, contributing to crowd-sourcing activities to preserve cultural heritage and to obtain an accessible version of the involved corpus.
|
