Mostrar el registro sencillo del ítem
Exponential family Fisher vector for image classification
dc.coverage.spatial | Internacional | es_ES |
dc.creator | Sánchez, Jorge | |
dc.creator | Redolfi, Javier | |
dc.date.accessioned | 2019-09-10T20:20:09Z | |
dc.date.available | 2019-09-10T20:20:09Z | |
dc.date.issued | 2015-07-01 | |
dc.identifier.citation | Sánchez, J., & Redolfi, J. (2015). Exponential family Fisher vector for image classification. Pattern Recognition Letters, 59, 26-32. | es_ES |
dc.identifier.issn | 0167-8655 | |
dc.identifier.uri | http://hdl.handle.net/20.500.12272/3972 | |
dc.description.abstract | One of the fundamental problems in image classification is to devise models that allow us to relate the images to higher-level semantic concepts in an efficient and reliable way. A widely used approach consists on extracting local descriptors from the images and to summarize them into an image-level representation. Within this framework, the Fisher vector (FV) is one of the most robust signatures to date. In the FV, local descriptors are modeled as samples drawn from a mixture of Gaussian pdfs. An image is represented by a gradient vector characterizing the distributions of samples w.r.t. the model. Equipped with robust features like SIFT, the FV has shown state-of-the-art performance on different recognition problems. However, it is not clear how it should be applied when the feature space is clearly non-Euclidean, leading to heuristics that ignore the underlying structure of the space. In this paper we generalize the Gaussian FV to a broader family of distributions known as the exponential family. The model, termed exponential family Fisher vectors (eFV), provides a unified framework from which rich and powerful representations can be derived. Experimental results show the generality and flexibility of our approach. | es_ES |
dc.format | application/pdf | es_ES |
dc.language.iso | eng | es_ES |
dc.language.iso | eng | es_ES |
dc.rights | info:eu-repo/semantics/openAccess | es_ES |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-sa/4.0/ | * |
dc.subject | image classification | es_ES |
dc.subject | Fisher kernel | es_ES |
dc.subject | Fisher vectors | es_ES |
dc.subject | exponential family | es_ES |
dc.title | Exponential family Fisher vector for image classification | es_ES |
dc.type | info:eu-repo/semantics/article | es_ES |
dc.description.affiliation | Fil: Sánchez, Jorge (1,2); Redolfi, Javier Andrés (3) (1) CONICET, Haya de la Torre S/N, Ciudad Universitaria, Córdoba, X5016ZAA, Argentina. (2) Universidad Nacional de Córdoba, Córdoba, X5000HUA, Argentina. (3) CIII, UTN Facultad Regional Córdoba, Córdoba, X5016ZAA, Argentina. | es_ES |
dc.description.peerreviewed | Peer Reviewed | es_ES |
dc.type.version | info:eu-repo/semantics/draft | es_ES |
dc.type.snrd | info:ar-repo/semantics/artículo | es_ES |
dc.rights.use | Atribución-NoComercial-CompartirIgual 4.0 Internacional | * |
dc.identifier.doi | https://doi.org/10.1016/j.patrec.2015.03.010 |