Enver Sangineto
University of Trento
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Enver Sangineto.
International Journal of Multimedia Information Retrieval | 2015
Jasper R. R. Uijlings; Ionut C. Duta; Enver Sangineto; Nicu Sebe
The current state-of-the-art in video classification is based on Bag-of-Words using local visual descriptors. Most commonly these are histogram of oriented gradients (HOG), histogram of optical flow (HOF) and motion boundary histograms (MBH) descriptors. While such approach is very powerful for classification, it is also computationally expensive. This paper addresses the problem of computational efficiency. Specifically: (1) We propose several speed-ups for densely sampled HOG, HOF and MBH descriptors and release Matlab code; (2) We investigate the trade-off between accuracy and computational efficiency of descriptors in terms of frame sampling rate and type of Optical Flow method; (3) We investigate the trade-off between accuracy and computational efficiency for computing the feature vocabulary, using and comparing most of the commonly adopted vector quantization techniques:
acm multimedia | 2014
Enver Sangineto; Gloria Zen; Elisa Ricci; Nicu Sebe
IEEE Transactions on Pattern Analysis and Machine Intelligence | 2013
Enver Sangineto
k
international conference on multimodal interfaces | 2014
Gloria Zen; Enver Sangineto; Elisa Ricci; Nicu Sebe
IEEE Transactions on Multimedia | 2016
Gloria Zen; Lorenzo Porzi; Enver Sangineto; Elisa Ricci; Nicu Sebe
k-means, hierarchical
ieee international conference on automatic face gesture recognition | 2015
Radu-Laurenţiu Vieriu; Sergey Tulyakov; Stanislau Semeniuta; Enver Sangineto; Nicu Sebe
Image and Vision Computing | 2012
Enver Sangineto; Marco Cupelli
k
Archive | 2013
R. Raghavendra; Marco Cristani; A. Del Bue; Enver Sangineto; Vittorio Murino
european conference on computer vision | 2014
Enver Sangineto
k-means, Random Forests, Fisher Vectors and VLAD.
international conference on pattern recognition | 2016
Paolo Rota; Enver Sangineto; Valentina Conotter; Christopher Pramerdorfer
Previous works on facial expression analysis have shown that person specific models are advantageous with respect to generic ones for recognizing facial expressions of new users added to the gallery set. This finding is not surprising, due to the often significant inter-individual variability: different persons have different morphological aspects and express their emotions in different ways. However, acquiring person-specific labeled data for learning models is a very time consuming process. In this work we propose a new transfer learning method to compute personalized models without labeled target data Our approach is based on learning multiple person-specific classifiers for a set of source subjects and then directly transfer knowledge about the parameters of these classifiers to the target individual. The transfer process is obtained by learning a regression function which maps the data distribution associated to each source subject to the corresponding classifiers parameters. We tested our approach on two different application domains, Action Units (AUs) detection and spontaneous pain recognition, using publicly available datasets and showing its advantages with respect to the state-of-the-art both in term of accuracy and computational cost.