Raul Gomez, Jaume Gibert, Lluis Gomez, & Dimosthenis Karatzas. (2020). Location Sensitive Image Retrieval and Tagging. In 16th European Conference on Computer Vision.
Abstract: People from different parts of the globe describe objects and concepts in distinct manners. Visual appearance can thus vary across different geographic locations, which makes location a relevant contextual information when analysing visual data. In this work, we address the task of image retrieval related to a given tag conditioned on a certain location on Earth. We present LocSens, a model that learns to rank triplets of images, tags and coordinates by plausibility, and two training strategies to balance the location influence in the final ranking. LocSens learns to fuse textual and location information of multimodal queries to retrieve related images at different levels of location granularity, and successfully utilizes location information to improve image tagging.
|
Lei Kang, Pau Riba, Yaxing Wang, Marçal Rusiñol, Alicia Fornes, & Mauricio Villegas. (2020). GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images. In 16th European Conference on Computer Vision.
Abstract: Although current image generation methods have reached impressive quality levels, they are still unable to produce plausible yet diverse images of handwritten words. On the contrary, when writing by hand, a great variability is observed across different writers, and even when analyzing words scribbled by the same individual, involuntary variations are conspicuous. In this work, we take a step closer to producing realistic and varied artificially rendered handwritten words. We propose a novel method that is able to produce credible handwritten word images by conditioning the generative process with both calligraphic style features and textual content. Our generator is guided by three complementary learning objectives: to produce realistic images, to imitate a certain handwriting style and to convey a specific textual content. Our model is unconstrained to any predefined vocabulary, being able to render whatever input word. Given a sample writer, it is also able to mimic its calligraphic features in a few-shot setup. We significantly advance over prior art and demonstrate with qualitative, quantitative and human-based evaluations the realistic aspect of our synthetically produced images.
|
Hugo Bertiche, Meysam Madadi, & Sergio Escalera. (2020). CLOTH3D: Clothed 3D Humans. In 16th European Conference on Computer Vision.
Abstract: This work presents CLOTH3D, the first big scale synthetic dataset of 3D clothed human sequences. CLOTH3D contains a large variability on garment type, topology, shape, size, tightness and fabric. Clothes are simulated on top of thousands of different pose sequences and body shapes, generating realistic cloth dynamics. We provide the dataset with a generative model for cloth generation. We propose a Conditional Variational Auto-Encoder (CVAE) based on graph convolutions (GCVAE) to learn garment latent spaces. This allows for realistic generation of 3D garments on top of SMPL model for any pose and shape.
|
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.
|
Gabriel Villalonga, Sebastian Ramos, German Ros, David Vazquez, & Antonio Lopez. (2014). 3d Pedestrian Detection via Random Forest.
Abstract: Our demo focuses on showing the extraordinary performance of our novel 3D pedestrian detector along with its simplicity and real-time capabilities. This detector has been designed for autonomous driving applications, but it can also be applied in other scenarios that cover both outdoor and indoor applications.
Our pedestrian detector is based on the combination of a random forest classifier with HOG-LBP features and the inclusion of a preprocessing stage based on 3D scene information in order to precisely determinate the image regions where the detector should search for pedestrians. This approach ends up in a high accurate system that runs real-time as it is required by many computer vision and robotics applications.
Keywords: Pedestrian Detection
|
Andrea Gemelli, Sanket Biswas, Enrico Civitelli, Josep Llados, & Simone Marinai. (2022). Doc2Graph: A Task Agnostic Document Understanding Framework Based on Graph Neural Networks. In 17th European Conference on Computer Vision Workshops (Vol. 13804, 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.
|
Patricia Marquez, Debora Gil, & Aura Hernandez-Sabate. (2012). A Complete Confidence Framework for Optical Flow. In Rita Cucchiara V. M. Andrea Fusiello (Ed.), 12th European Conference on Computer Vision – Workshops and Demonstrations (Vol. 7584, pp. 124–133). LNCS. Florence, Italy, October 7-13, 2012: Springer-Verlag.
Abstract: Medial representations are powerful tools for describing and parameterizing the volumetric shape of anatomical structures. Existing methods show excellent results when applied to 2D objects, but their quality drops across dimensions. This paper contributes to the computation of medial manifolds in two aspects. First, we provide a standard scheme for the computation of medial manifolds that avoid degenerated medial axis segments; second, we introduce an energy based method which performs independently of the dimension. We evaluate quantitatively the performance of our method with respect to existing approaches, by applying them to synthetic shapes of known medial geometry. Finally, we show results on shape representation of multiple abdominal organs, exploring the use of medial manifolds for the representation of multi-organ relations.
Keywords: Optical flow, confidence measures, sparsification plots, error prediction plots
|
David Masip, Alexander Todorov, & Jordi Vitria. (2012). The Role of Facial Regions in Evaluating Social Dime. In Rita Cucchiara V. M. Andrea Fusiello (Ed.), 12th European Conference on Computer Vision – Workshops and Demonstrations (Vol. 7584, pp. 210–219). LNCS. Springer Berlin Heidelberg.
Abstract: Facial trait judgments are an important information cue for people. Recent works in the Psychology field have stated the basis of face evaluation, defining a set of traits that we evaluate from faces (e.g. dominance, trustworthiness, aggressiveness, attractiveness, threatening or intelligence among others). We rapidly infer information from others faces, usually after a short period of time (< 1000ms) we perceive a certain degree of dominance or trustworthiness of another person from the face. Although these perceptions are not necessarily accurate, they influence many important social outcomes (such as the results of the elections or the court decisions). This topic has also attracted the attention of Computer Vision scientists, and recently a computational model to automatically predict trait evaluations from faces has been proposed. These systems try to mimic the human perception by means of applying machine learning classifiers to a set of labeled data. In this paper we perform an experimental study on the specific facial features that trigger the social inferences. Using previous results from the literature, we propose to use simple similarity maps to evaluate which regions of the face influence the most the trait inferences. The correlation analysis is performed using only appearance, and the results from the experiments suggest that each trait is correlated with specific facial characteristics.
Keywords: Workshops and Demonstrations
|
Bogdan Raducanu, & Fadi Dornaika. (2012). Pose-Invariant Face Recognition in Videos for Human-Machine Interaction. In 12th European Conference on Computer Vision (Vol. 7584, 566.575). LNCS. Springer Berlin Heidelberg.
Abstract: Human-machine interaction is a hot topic nowadays in the communities of computer vision and robotics. In this context, face recognition algorithms (used as primary cue for a person’s identity assessment) work well under controlled conditions but degrade significantly when tested in real-world environments. This is mostly due to the difficulty of simultaneously handling variations in illumination, pose, and occlusions. In this paper, we propose a novel approach for robust pose-invariant face recognition for human-robot interaction based on the real-time fitting of a 3D deformable model to input images taken from video sequences. More concrete, our approach generates a rectified face image irrespective with the actual head-pose orientation. Experimental results performed on Honda video database, using several manifold learning techniques, show a distinct advantage of the proposed method over the standard 2D appearance-based snapshot approach.
|
Jose Manuel Alvarez, Y. LeCun, Theo Gevers, & Antonio Lopez. (2012). Semantic Road Segmentation via Multi-Scale Ensembles of Learned Features. In 12th European Conference on Computer Vision – Workshops and Demonstrations (Vol. 7584, pp. 586–595). LNCS. Springer Berlin Heidelberg.
Abstract: Semantic segmentation refers to the process of assigning an object label (e.g., building, road, sidewalk, car, pedestrian) to every pixel in an image. Common approaches formulate the task as a random field labeling problem modeling the interactions between labels by combining local and contextual features such as color, depth, edges, SIFT or HoG. These models are trained to maximize the likelihood of the correct classification given a training set. However, these approaches rely on hand–designed features (e.g., texture, SIFT or HoG) and a higher computational time required in the inference process.
Therefore, in this paper, we focus on estimating the unary potentials of a conditional random field via ensembles of learned features. We propose an algorithm based on convolutional neural networks to learn local features from training data at different scales and resolutions. Then, diversification between these features is exploited using a weighted linear combination. Experiments on a publicly available database show the effectiveness of the proposed method to perform semantic road scene segmentation in still images. The algorithm outperforms appearance based methods and its performance is similar compared to state–of–the–art methods using other sources of information such as depth, motion or stereo.
Keywords: road detection
|
Sergio Escalera, Xavier Baro, Jordi Gonzalez, Miguel Angel Bautista, Meysam Madadi, Miguel Reyes, et al. (2014). ChaLearn Looking at People Challenge 2014: Dataset and Results. In ECCV Workshop on ChaLearn Looking at People (Vol. 8925, pp. 459–473). LNCS.
Abstract: This paper summarizes the ChaLearn Looking at People 2014 challenge data and the results obtained by the participants. The competition was split into three independent tracks: human pose recovery from RGB data, action and interaction recognition from RGB data sequences, and multi-modal gesture recognition from RGB-Depth sequences. For all the tracks, the goal was to perform user-independent recognition in sequences of continuous images using the overlapping Jaccard index as the evaluation measure. In this edition of the ChaLearn challenge, two large novel data sets were made publicly available and the Microsoft Codalab platform were used to manage the competition. Outstanding results were achieved in the three challenge tracks, with accuracy results of 0.20, 0.50, and 0.85 for pose recovery, action/interaction recognition, and multi-modal gesture recognition, respectively.
Keywords: Human Pose Recovery; Behavior Analysis; Action and in- teractions; Multi-modal gestures; recognition
|
Xavier Perez Sala, Fernando De la Torre, Laura Igual, Sergio Escalera, & Cecilio Angulo. (2014). Subspace Procrustes Analysis. In ECCV Workshop on ChaLearn Looking at People (Vol. 8925, pp. 654–668). LNCS.
Abstract: Procrustes Analysis (PA) has been a popular technique to align and build 2-D statistical models of shapes. Given a set of 2-D shapes PA is applied to remove rigid transformations. Then, a non-rigid 2-D model is computed by modeling (e.g., PCA) the residual. Although PA has been widely used, it has several limitations for modeling 2-D shapes: occluded landmarks and missing data can result in local minima solutions, and there is no guarantee that the 2-D shapes provide a uniform sampling of the 3-D space of rotations for the object. To address previous issues, this paper proposes Subspace PA (SPA). Given several instances of a 3-D object, SPA computes the mean and a 2-D subspace that can simultaneously model all rigid and non-rigid deformations of the 3-D object. We propose a discrete (DSPA) and continuous (CSPA) formulation for SPA, assuming that 3-D samples of an object are provided. DSPA extends the traditional PA, and produces unbiased 2-D models by uniformly sampling dierent views of the 3-D object. CSPA provides a continuous approach to uniformly sample the space of 3-D rotations, being more ecient in space and time. Experiments using SPA to learn 2-D models of bodies from motion capture data illustrate the benets of our approach.
|
Eloi Puertas, Miguel Angel Bautista, Daniel Sanchez, Sergio Escalera, & Oriol Pujol. (2014). Learning to Segment Humans by Stacking their Body Parts,. In ECCV Workshop on ChaLearn Looking at People (Vol. 8925, pp. 685–697). LNCS.
Abstract: Human segmentation in still images is a complex task due to the wide range of body poses and drastic changes in environmental conditions. Usually, human body segmentation is treated in a two-stage fashion. First, a human body part detection step is performed, and then, human part detections are used as prior knowledge to be optimized by segmentation strategies. In this paper, we present a two-stage scheme based on Multi-Scale Stacked Sequential Learning (MSSL). We define an extended feature set by stacking a multi-scale decomposition of body
part likelihood maps. These likelihood maps are obtained in a first stage
by means of a ECOC ensemble of soft body part detectors. In a second stage, contextual relations of part predictions are learnt by a binary classifier, obtaining an accurate body confidence map. The obtained confidence map is fed to a graph cut optimization procedure to obtain the final segmentation. Results show improved segmentation when MSSL is included in the human segmentation pipeline.
Keywords: Human body segmentation; Stacked Sequential Learning
|
Y. Patel, Lluis Gomez, Marçal Rusiñol, & Dimosthenis Karatzas. (2016). Dynamic Lexicon Generation for Natural Scene Images. In 14th European Conference on Computer Vision Workshops (pp. 395–410).
Abstract: Many scene text understanding methods approach the endtoend recognition problem from a word-spotting perspective and take huge benet from using small per-image lexicons. Such customized lexicons are normally assumed as given and their source is rarely discussed.
In this paper we propose a method that generates contextualized lexicons
for scene images using only visual information. For this, we exploit
the correlation between visual and textual information in a dataset consisting
of images and textual content associated with them. Using the topic modeling framework to discover a set of latent topics in such a dataset allows us to re-rank a xed dictionary in a way that prioritizes the words that are more likely to appear in a given image. Moreover, we train a CNN that is able to reproduce those word rankings but using only the image raw pixels as input. We demonstrate that the quality of the automatically obtained custom lexicons is superior to a generic frequency-based baseline.
Keywords: scene text; photo OCR; scene understanding; lexicon generation; topic modeling; CNN
|
Victor Ponce, Baiyu Chen, Marc Oliu, Ciprian Corneanu, Albert Clapes, Isabelle Guyon, et al. (2016). ChaLearn LAP 2016: First Round Challenge on First Impressions – Dataset and Results. In 14th European Conference on Computer Vision Workshops.
Abstract: This paper summarizes the ChaLearn Looking at People 2016 First Impressions challenge data and results obtained by the teams in the rst round of the competition. The goal of the competition was to automatically evaluate ve \apparent“ personality traits (the so-called \Big Five”) from videos of subjects speaking in front of a camera, by using human judgment. In this edition of the ChaLearn challenge, a novel data set consisting of 10,000 shorts clips from YouTube videos has been made publicly available. The ground truth for personality traits was obtained from workers of Amazon Mechanical Turk (AMT). To alleviate calibration problems between workers, we used pairwise comparisons between videos, and variable levels were reconstructed by tting a Bradley-Terry-Luce model with maximum likelihood. The CodaLab open source
platform was used for submission of predictions and scoring. The competition attracted, over a period of 2 months, 84 participants who are grouped in several teams. Nine teams entered the nal phase. Despite the diculty of the task, the teams made great advances in this round of the challenge.
Keywords: Behavior Analysis; Personality Traits; First Impressions
|