| dc.creator | Sánchez, Jorge | |
| dc.creator | Redolfi, Javier | |
| dc.date | 2019-09-10T20:20:09Z | |
| dc.date | 2019-09-10T20:20:09Z | |
| dc.date | 2015-07-01 | |
| dc.date.accessioned | 2023-08-31T14:08:41Z | |
| dc.date.available | 2023-08-31T14:08:41Z | |
| dc.identifier | Sánchez, J., & Redolfi, J. (2015). Exponential family Fisher vector for image classification. Pattern Recognition Letters, 59, 26-32. | |
| dc.identifier | 0167-8655 | |
| dc.identifier | http://hdl.handle.net/20.500.12272/3972 | |
| dc.identifier | https://doi.org/10.1016/j.patrec.2015.03.010 | |
| dc.identifier.uri | https://repositorioslatinoamericanos.uchile.cl/handle/2250/8546172 | |
| dc.description | 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. | |
| dc.description | 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. | |
| dc.description | Peer Reviewed | |
| dc.format | application/pdf | |
| dc.language | eng | |
| dc.language | eng | |
| dc.rights | info:eu-repo/semantics/openAccess | |
| dc.rights | http://creativecommons.org/licenses/by-nc-sa/4.0/ | |
| dc.rights | Atribución-NoComercial-CompartirIgual 4.0 Internacional | |
| dc.subject | image classification | |
| dc.subject | Fisher kernel | |
| dc.subject | Fisher vectors | |
| dc.subject | exponential family | |
| dc.title | Exponential family Fisher vector for image classification | |
| dc.type | info:eu-repo/semantics/article | |
| dc.type | info:eu-repo/semantics/draft | |
| dc.type | info:ar-repo/semantics/artículo | |
| dc.coverage | Internacional | |
