|
V. Valev, & Petia Radeva. (1995). ECG Recognition by Non-Reducible Descriptors..
|
|
Francesco Ciompi. (2008). ECOC-based Plaque Classification using In-vivo and Exvivo Intravascular Ultrasound Data.
|
|
Sergio Escalera, Oriol Pujol, & Petia Radeva. (2006). ECOC-ONE: A novel coding and decoding strategy.
|
|
J. Mauri, E Fernandez-Nofrerias, Petia Radeva, & V. Valle. (2000). Ecografia intracoronaria, una ajuda o un mestre en lintervencionisme coronari?".
|
|
J. Mauri, E Fernandez-Nofrerias, E. Esplugas, A. Cequier, David Rotger, Ricardo Toledo, et al. (2000). Ecografia Intracoronaria: Navegacion Informatica por el cubo de datos de las imagenes..
|
|
W.Win, B.Bao, Q.Xu, Luis Herranz, & Shuqiang Jiang. (2019). Editorial Note: Efficient Multimedia Processing Methods and Applications (Vol. 78).
|
|
Angel Sappa. (2005). Efficient Closed Contour Extraction from Range Image Edge Points.
|
|
A. Pujol, Juan J. Villanueva, & Jose Luis Alba. (2001). Efficient Computation of Face Shape Similarity Using Distance Transform Eigendecomposition and Valleys..
|
|
Jordi Gonzalez, Dani Rowe, Juan Andrade, & Juan J. Villanueva. (2006). Efficient Management of Multiple Agent Tracking Through Observation Handling.
|
|
Jaume Amores, N. Sebe, & Petia Radeva. (2005). Efficient Object-Class Recognition by Boosting Contextual Information.
|
|
Eduard Vazquez, & Maria Vanrell. (2008). Eines per al desenvolupament de competencies de enginyeria en un assignatura de Intel·ligencia Artificial.
|
|
J.L.Bruguera, R.Casado, M.Martinez, I.Corral, Enric Marti, & L.A.Branda. (2009). El apoyo institucional como elemento favorecedor de la coordinación docente: experiencias en diferentes universidades.
|
|
Jaume Amores, & Petia Radeva. (2003). Elastic Matching and Retrieval of IVUS Images Using Contextual Information.
|
|
Misael Rosales. (2002). Empirical Simulation Moldel of Intravascular Ultrasound.
|
Umut Guclu, Yagmur Gucluturk, Meysam Madadi, Sergio Escalera, Xavier Baro, Jordi Gonzalez, et al. (2017). End-to-end semantic face segmentation with conditional random fields as convolutional, recurrent and adversarial networks.
Abstract: arXiv:1703.03305
Recent years have seen a sharp increase in the number of related yet distinct advances in semantic segmentation. Here, we tackle this problem by leveraging the respective strengths of these advances. That is, we formulate a conditional random field over a four-connected graph as end-to-end trainable convolutional and recurrent networks, and estimate them via an adversarial process. Importantly, our model learns not only unary potentials but also pairwise
potentials, while aggregating multi-scale contexts and controlling higher-order inconsistencies.
We evaluate our model on two standard benchmark datasets for semantic face segmentation, achieving state-of-the-art results on both of them.
|
