Exploració per autor "Simó Serra, Edgar"
Ara es mostren els items 1-20 de 21
-
3D human pose tracking priors using geodesic mixture models
(2017-04-01)
Article
Accés obertWe present a novel approach for learning a finite mixture model on a Riemannian manifold in which Euclidean metrics are not applicable and one needs to resort to geodesic distances consistent with the manifold geometry. ... -
A high performance CRF model for clothes parsing
(Springer, 2014)
Text en actes de congrés
Accés obertIn this paper we tackle the problem of clothing parsing: Our goal is to segment and classify different garments a person is wearing. We frame the problem as the one of inference in a pose-aware Conditional Random Field ... -
A joint model for 2D and 3D pose estimation from a single image
(Institute of Electrical and Electronics Engineers (IEEE), 2013)
Text en actes de congrés
Accés restringit per política de l'editorialWe introduce a novel approach to automatically recover 3D human pose from a single image. Most previous work follows a pipelined approach: initially, a set of 2D features such as edges, joints or silhouettes are detected ... -
BASS: boundary-aware superpixel segmentation
(IEEE Press, 2016)
Text en actes de congrés
Accés obertWe propose a new superpixel algorithm based on exploiting the boundary information of an image, as objects in images can generally be described by their boundaries. Our proposed approach initially estimates the boundaries ... -
DaLI: deformation and light invariant descriptor
(2015-11-01)
Article
Accés obertRecent advances in 3D shape analysis and recognition have shown that heat diffusion theory can be effectively used to describe local features of deforming and scaling surfaces. In this paper, we show how this description ... -
Design of non-anthropomorphic robotic hands for anthropomorphic tasks
(2011)
Text en actes de congrés
Accés obertIn this paper, we explore the idea of designing non- anthropomorphic multi-fingered robotic hands for tasks tha t replicate the motion of the human hand. Taking as input data a finite set of rigid-body positions for the ... -
Discriminative learning of deep convolutional feature point descriptors
(Institute of Electrical and Electronics Engineers (IEEE), 2015)
Text en actes de congrés
Accés obertDeep learning has revolutionalized image-level tasks such as classification, but patch-level tasks, such as correspondence, still rely on hand-crafted features, e.g. SIFT. In this paper we use Convolutional Neural Networks ... -
Efficient monocular pose estimation for complex 3D models
(Institute of Electrical and Electronics Engineers (IEEE), 2015)
Text en actes de congrés
Accés obertWe propose a robust and efficient method to estimate the pose of a camera with respect to complex 3D textured models of the environment that can potentially contain more than 100, 000 points. To tackle this problem we ... -
Geodesic finite mixture models
(2014)
Text en actes de congrés
Accés obertWe present a novel approach for learning a finite mixture model on a Riemannian manifold in which Euclidean metrics are not applicable and one needs to resort to geodesic distances consistent with the manifold geometry. ... -
Kinematic Model of the Hand using Computer Vision
(Universitat Politècnica de Catalunya, 2011-04)
Projecte/Treball Final de Carrera
Accés obertLa biotecnología es una ciencia en auge y en especial el diseño de interfaces humano-máquina. El objetivo de este proyecto es avanzar en dicho campo y en concreto explorar el diseño de exoesqueletos y prótesis de la mano ... -
Kinematic synthesis of multi-fingered robotic hands for finite and infinitesimal tasks
(Springer, 2012)
Text en actes de congrés
Accés obertIn this paper we present a novel method of designing multi-fingered robotic hands using tasks composed of both finite and infinitesimal motion. The method is based on representing the robotic hands as a kinematic chain ... -
Lie algebra-based kinematic prior for 3D human pose tracking
(2015)
Text en actes de congrés
Accés obertWe propose a novel kinematic prior for 3D human pose tracking that allows predicting the position in subsequent frames given the current position. We first define a Riemannian manifold that models the pose and extend it ... -
Multi-modal embedding for main product detection in fashion
(2017)
Text en actes de congrés
Accés obertWe present an approach to detect the main product in fashion images by exploiting the textual metadata associated with each image. Our approach is based on a Convolutional Neural Network and learns a joint embedding of ... -
Multi-modal fashion product retrieval
(2017)
Text en actes de congrés
Accés obertFinding a product in the fashion world can be a daunting task. Everyday, e-commerce sites are updating with thousands of images and their associated metadata (textual information), deepening the problem. In this paper, we ... -
Multi-modal joint embedding for fashion product retrieval
(Institute of Electrical and Electronics Engineers (IEEE), 2017)
Text en actes de congrés
Accés obertFinding a product in the fashion world can be a daunting task. Everyday, e-commerce sites are updating with thousands of images and their associated metadata (textual information), deepening the problem, akin to finding a ... -
Neuroaesthetics in fashion: modeling the perception of fashionability
(2015)
Text en actes de congrés
Accés obertIn this paper, we analyze the fashion of clothing of a large social website. Our goal is to learn and predict how fashionable a person looks on a photograph and suggest subtle improvements the user could make to improve ... -
Quadern de treball CEABOT 2009 - Twiki
(2010)
Report de recerca
Accés obertResum de l'experiència en la participació del concurs CEABOT 2009. -
Single image 3D human pose estimation from noisy observations
(2012)
Text en actes de congrés
Accés obertMarkerless 3D human pose detection from a single image is a severely underconstrained problem because different 3D poses can have similar image projections. In order to handle this ambiguity, current approaches rely on ... -
Slave architecture for the Robonova MR-C3024 using the HMI protocol
(2010)
Report de recerca
Accés obertThe goal of the project is to develop a new rmware for the servo control board Hitec MR- C3024 [8] to improve its speci cations. This board will be used to control the movement of a humanoid robot, driven by digital ... -
Structured prediction with output embeddings for semantic image annotation
(2016)
Text en actes de congrés
Accés obertWe address the task of annotating images with semantic tuples. Solving this problem requires an algorithm able to deal with hundreds of classes for each argument of the tuple. In such contexts, data sparsity becomes a key ...
