|
Adarsh Tiwari, Sanket Biswas, & Josep Llados. (2023). Can Pre-trained Language Models Help in Understanding Handwritten Symbols? In 17th International Conference on Document Analysis and Recognition (Vol. 14193, 199–211).
Abstract: The emergence of transformer models like BERT, GPT-2, GPT-3, RoBERTa, T5 for natural language understanding tasks has opened the floodgates towards solving a wide array of machine learning tasks in other modalities like images, audio, music, sketches and so on. These language models are domain-agnostic and as a result could be applied to 1-D sequences of any kind. However, the key challenge lies in bridging the modality gap so that they could generate strong features beneficial for out-of-domain tasks. This work focuses on leveraging the power of such pre-trained language models and discusses the challenges in predicting challenging handwritten symbols and alphabets.
|
|
|
Aniol Lidon, Marc Bolaños, Mariella Dimiccoli, Petia Radeva, Maite Garolera, & Xavier Giro. (2017). Semantic Summarization of Egocentric Photo-Stream Events. In 2nd Workshop on Lifelogging Tools and Applications.
|
|
|
Jose Manuel Alvarez, Theo Gevers, & Antonio Lopez. (2010). 3D Scene Priors for Road Detection. In 23rd IEEE Conference on Computer Vision and Pattern Recognition (57–64).
Abstract: Vision-based road detection is important in different areas of computer vision such as autonomous driving, car collision warning and pedestrian crossing detection. However, current vision-based road detection methods are usually based on low-level features and they assume structured roads, road homogeneity, and uniform lighting conditions. Therefore, in this paper, contextual 3D information is used in addition to low-level cues. Low-level photometric invariant cues are derived from the appearance of roads. Contextual cues used include horizon lines, vanishing points, 3D scene layout and 3D road stages. Moreover, temporal road cues are included. All these cues are sensitive to different imaging conditions and hence are considered as weak cues. Therefore, they are combined to improve the overall performance of the algorithm. To this end, the low-level, contextual and temporal cues are combined in a Bayesian framework to classify road sequences. Large scale experiments on road sequences show that the road detection method is robust to varying imaging conditions, road types, and scenarios (tunnels, urban and highway). Further, using the combined cues outperforms all other individual cues. Finally, the proposed method provides highest road detection accuracy when compared to state-of-the-art methods.
Keywords: road detection
|
|
|
Mohammad Rouhani, & Angel Sappa. (2010). Relaxing the 3L Algorithm for an Accurate Implicit Polynomial Fitting. In 23rd IEEE Conference on Computer Vision and Pattern Recognition (pp. 3066–3072).
Abstract: This paper presents a novel method to increase the accuracy of linear fitting of implicit polynomials. The proposed method is based on the 3L algorithm philosophy. The novelty lies on the relaxation of the additional constraints, already imposed by the 3L algorithm. Hence, the accuracy of the final solution is increased due to the proper adjustment of the expected values in the aforementioned additional constraints. Although iterative, the proposed approach solves the fitting problem within a linear framework, which is independent of the threshold tuning. Experimental results, both in 2D and 3D, showing improvements in the accuracy of the fitting are presented. Comparisons with both state of the art algorithms and a geometric based one (non-linear fitting), which is used as a ground truth, are provided.
|
|
|
Javier Marin, David Vazquez, David Geronimo, & Antonio Lopez. (2010). Learning Appearance in Virtual Scenarios for Pedestrian Detection. In 23rd IEEE Conference on Computer Vision and Pattern Recognition (137–144).
Abstract: Detecting pedestrians in images is a key functionality to avoid vehicle-to-pedestrian collisions. The most promising detectors rely on appearance-based pedestrian classifiers trained with labelled samples. This paper addresses the following question: can a pedestrian appearance model learnt in virtual scenarios work successfully for pedestrian detection in real images? (Fig. 1). Our experiments suggest a positive answer, which is a new and relevant conclusion for research in pedestrian detection. More specifically, we record training sequences in virtual scenarios and then appearance-based pedestrian classifiers are learnt using HOG and linear SVM. We test such classifiers in a publicly available dataset provided by Daimler AG for pedestrian detection benchmarking. This dataset contains real world images acquired from a moving car. The obtained result is compared with the one given by a classifier learnt using samples coming from real images. The comparison reveals that, although virtual samples were not specially selected, both virtual and real based training give rise to classifiers of similar performance.
Keywords: Pedestrian Detection; Domain Adaptation
|
|
|
Fadi Dornaika, & Bogdan Raducanu. (2010). Single Snapshot 3D Head Pose Initialization for Tracking in Human Robot Interaction Scenario. In 1st International Workshop on Computer Vision for Human-Robot Interaction (32–39).
Abstract: This paper presents an automatic 3D head pose initialization scheme for a real-time face tracker with application to human-robot interaction. It has two main contributions. First, we propose an automatic 3D head pose and person specific face shape estimation, based on a 3D deformable model. The proposed approach serves to initialize our realtime 3D face tracker. What makes this contribution very attractive is that the initialization step can cope with faces
under arbitrary pose, so it is not limited only to near-frontal views. Second, the previous framework is used to develop an application in which the orientation of an AIBO’s camera can be controlled through the imitation of user’s head pose.
In our scenario, this application is used to build panoramic images from overlapping snapshots. Experiments on real videos confirm the robustness and usefulness of the proposed methods.
Keywords: 1st International Workshop on Computer Vision for Human-Robot Interaction, in conjunction with IEEE CVPR 2010
|
|
|
David Aldavert, Arnau Ramisa, Ramon Lopez de Mantaras, & Ricardo Toledo. (2010). Fast and Robust Object Segmentation with the Integral Linear Classifier. In 23rd IEEE Conference on Computer Vision and Pattern Recognition (1046–1053).
Abstract: We propose an efficient method, built on the popular Bag of Features approach, that obtains robust multiclass pixel-level object segmentation of an image in less than 500ms, with results comparable or better than most state of the art methods. We introduce the Integral Linear Classifier (ILC), that can readily obtain the classification score for any image sub-window with only 6 additions and 1 product by fusing the accumulation and classification steps in a single operation. In order to design a method as efficient as possible, our building blocks are carefully selected from the quickest in the state of the art. More precisely, we evaluate the performance of three popular local descriptors, that can be very efficiently computed using integral images, and two fast quantization methods: the Hierarchical K-Means, and the Extremely Randomized Forest. Finally, we explore the utility of adding spatial bins to the Bag of Features histograms and that of cascade classifiers to improve the obtained segmentation. Our method is compared to the state of the art in the difficult Graz-02 and PASCAL 2007 Segmentation Challenge datasets.
|
|
|
Michal Drozdzal, Laura Igual, Petia Radeva, Jordi Vitria, C. Malagelada, & Fernando Azpiroz. (2010). Aligning Endoluminal Scene Sequences in Wireless Capsule Endoscopy. In IEEE Computer Society Workshop on Mathematical Methods in Biomedical Image Analysis (117–124).
Abstract: Intestinal motility analysis is an important examination in detection of various intestinal malfunctions. One of the big challenges of automatic motility analysis is how to compare sequence of images and extract dynamic paterns taking into account the high deformability of the intestine wall as well as the capsule motion. From clinical point of view the ability to align endoluminal scene sequences will help to find regions of similar intestinal activity and in this way will provide a valuable information on intestinal motility problems. This work, for first time, addresses the problem of aligning endoluminal sequences taking into account motion and structure of the intestine. To describe motility in the sequence, we propose different descriptors based on the Sift Flow algorithm, namely: (1) Histograms of Sift Flow Directions to describe the flow course, (2) Sift Descriptors to represent image intestine structure and (3) Sift Flow Magnitude to quantify intestine deformation. We show that the merge of all three descriptors provides robust information on sequence description in terms of motility. Moreover, we develop a novel methodology to rank the intestinal sequences based on the expert feedback about relevance of the results. The experimental results show that the selected descriptors are useful in the alignment and similarity description and the proposed method allows the analysis of the WCE.
|
|
|
Antonio Hernandez, Miguel Reyes, Sergio Escalera, & Petia Radeva. (2010). Spatio-Temporal GrabCut human segmentation for face and pose recovery. In IEEE International Workshop on Analysis and Modeling of Faces and Gestures (33–40).
Abstract: In this paper, we present a full-automatic Spatio-Temporal GrabCut human segmentation methodology. GrabCut initialization is performed by a HOG-based subject detection, face detection, and skin color model for seed initialization. Spatial information is included by means of Mean Shift clustering whereas temporal coherence is considered by the historical of Gaussian Mixture Models. Moreover, human segmentation is combined with Shape and Active Appearance Models to perform full face and pose recovery. Results over public data sets as well as proper human action base show a robust segmentation and recovery of both face and pose using the presented methodology.
|
|
|
Petia Radeva, & M. Scoccianti. (2000). 3D Reconstruction of Abdominal Aortic Aneurysm.
|
|
|
Sandra Jimenez, Xavier Otazu, Valero Laparra, & Jesus Malo. (2013). Chromatic induction and contrast masking: similar models, different goals? In Human Vision and Electronic Imaging XVIII (Vol. 8651).
Abstract: Normalization of signals coming from linear sensors is an ubiquitous mechanism of neural adaptation.1 Local interaction between sensors tuned to a particular feature at certain spatial position and neighbor sensors explains a wide range of psychophysical facts including (1) masking of spatial patterns, (2) non-linearities of motion sensors, (3) adaptation of color perception, (4) brightness and chromatic induction, and (5) image quality assessment. Although the above models have formal and qualitative similarities, it does not necessarily mean that the mechanisms involved are pursuing the same statistical goal. For instance, in the case of chromatic mechanisms (disregarding spatial information), different parameters in the normalization give rise to optimal discrimination or adaptation, and different non-linearities may give rise to error minimization or component independence. In the case of spatial sensors (disregarding color information), a number of studies have pointed out the benefits of masking in statistical independence terms. However, such statistical analysis has not been performed for spatio-chromatic induction models where chromatic perception depends on spatial configuration. In this work we investigate whether successful spatio-chromatic induction models,6 increase component independence similarly as previously reported for masking models. Mutual information analysis suggests that seeking an efficient chromatic representation may explain the prevalence of induction effects in spatially simple images. © (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
|
|
|
Xinhang Song, Luis Herranz, & Shuqiang Jiang. (2017). Depth CNNs for RGB-D Scene Recognition: Learning from Scratch Better than Transferring from RGB-CNNs. In 31st AAAI Conference on Artificial Intelligence.
Abstract: Scene recognition with RGB images has been extensively studied and has reached very remarkable recognition levels, thanks to convolutional neural networks (CNN) and large scene datasets. In contrast, current RGB-D scene data is much more limited, so often leverages RGB large datasets, by transferring pretrained RGB CNN models and fine-tuning with the target RGB-D dataset. However, we show that this approach has the limitation of hardly reaching bottom layers, which is key to learn modality-specific features. In contrast, we focus on the bottom layers, and propose an alternative strategy to learn depth features combining local weakly supervised training from patches followed by global fine tuning with images. This strategy is capable of learning very discriminative depth-specific features with limited depth images, without resorting to Places-CNN. In addition we propose a modified CNN architecture to further match the complexity of the model and the amount of data available. For RGB-D scene recognition, depth and RGB features are combined by projecting them in a common space and further leaning a multilayer classifier, which is jointly optimized in an end-to-end network. Our framework achieves state-of-the-art accuracy on NYU2 and SUN RGB-D in both depth only and combined RGB-D data.
Keywords: RGB-D scene recognition; weakly supervised; fine tune; CNN
|
|
|
Mario Rojas, David Masip, A. Todorov, & Jordi Vitria. (2010). Automatic Point-based Facial Trait Judgments Evaluation. In 23rd IEEE Conference on Computer Vision and Pattern Recognition (2715–2720).
Abstract: Humans constantly evaluate the personalities of other people using their faces. Facial trait judgments have been studied in the psychological field, and have been determined to influence important social outcomes of our lives, such as elections outcomes and social relationships. Recent work on textual descriptions of faces has shown that trait judgments are highly correlated. Further, behavioral studies suggest that two orthogonal dimensions, valence and dominance, can describe the basis of the human judgments from faces. In this paper, we used a corpus of behavioral data of judgments on different trait dimensions to automatically learn a trait predictor from facial pixel images. We study whether trait evaluations performed by humans can be learned using machine learning classifiers, and used later in automatic evaluations of new facial images. The experiments performed using local point-based descriptors show promising results in the evaluation of the main traits.
|
|
|
Josep M. Gonfaus, Xavier Boix, Joost Van de Weijer, Andrew Bagdanov, Joan Serrat, & Jordi Gonzalez. (2010). Harmony Potentials for Joint Classification and Segmentation. In 23rd IEEE Conference on Computer Vision and Pattern Recognition (3280–3287).
Abstract: Hierarchical conditional random fields have been successfully applied to object segmentation. One reason is their ability to incorporate contextual information at different scales. However, these models do not allow multiple labels to be assigned to a single node. At higher scales in the image, this yields an oversimplified model, since multiple classes can be reasonable expected to appear within one region. This simplified model especially limits the impact that observations at larger scales may have on the CRF model. Neglecting the information at larger scales is undesirable since class-label estimates based on these scales are more reliable than at smaller, noisier scales. To address this problem, we propose a new potential, called harmony potential, which can encode any possible combination of class labels. We propose an effective sampling strategy that renders tractable the underlying optimization problem. Results show that our approach obtains state-of-the-art results on two challenging datasets: Pascal VOC 2009 and MSRC-21.
|
|
|
Petia Radeva, A.Amini, J.Huang, & Enric Marti. (1996). Deformable B-Solids and Implicit Snakes for Localization and Tracking of SPAMM MRI-Data. In Workshop on Mathematical Methods in Biomedical Image Analysis (pp. 192–201). IEEE Computer Society.
Abstract: To date, MRI-SPAMM data from different image slices have been analyzed independently. In this paper, we propose an approach for 3D tag localization and tracking of SPAMM data by a novel deformable B-solid. The solid is defined in terms of a 3D tensor product B-spline. The isoparametric curves of the B-spline solid have special importance. These are termed implicit snakes as they deform under image forces from tag lines in different image slices. The localization and tracking of tag lines is performed under constraints of continuity and smoothness of the B-solid. The framework unifies the problems of localization, and displacement fitting and interpolation into the same procedure utilizing B-spline bases for interpolation. To track motion from boundaries and restrict image forces to the myocardium, a volumetric model is employed as a pair of coupled endocardial and epicardial B-spline surfaces. To recover deformations in the LV an energy-minimization problem is posed where both tag and ...
|
|