QuMinS: fast and scalable querying, mining and summarizing multi-modal databases

Given a large image set, in which very few images have labels, how to guess labels for the remaining majority? How to spot images that need brand new labels different from the predefined ones? How to summarize these data to route the user’s attention to what really matters? Here we answer all these questions. Specifically, we propose QuMinS, a fast, scalable solution to two problems: (i) Low-labor labeling (LLL) – given an image set, very few images have labels, find the most appropriate labels for the rest; and (ii) Mining and attention routing – in the same setting, find clusters, the top-'N IND.O' outlier images, and the 'N IND.R' images that best represent the data. Experiments on satellite images spanning up to 2.25 GB show that, contrasting to the state-of-the-art labeling techniques, QuMinS scales linearly on the data size, being up to 40 times faster than top competitors (GCap), still achieving better or equal accuracy, it spots images that potentially require unpredicted labels, and it works even with tiny initial label sets, i.e., nearly five examples. We also report a case study of our method’s practical usage to show that QuMinS is a viable tool for automatic coffee crop detection from remote sensing images.

Underwater towed video: a useful tool to rapidly assess elasmobranch populations in large marine protected areas

Elasmobranch stock assessment studies are usually made through fisheries surveys data. However, in large marine protected areas (MPAs) the use of destructive techniques must be dismissed in order to avoid population impacts. In 2005, while conducting a marine habitat survey in two marine Special Areas of Conservation (Sebadales de Playa de Inglés and Franja Marina de Mogán) in south Gran Canary Island (Canary Islands, Spain) with underwater towed video (UTV) and underwater visual census (UVC) transects, we recognized the opportunity rose to assess elasmobranch populations through UTV. Number of observed species and specimens, overall field work effort and total surveyed area were determined and compared between methods. Mean observations per day per unit of time (MOPUT) and mean observations per day per unit of surveyed area (MOPUA) were also compared through Mann–Whitney rank sum statistical test (α=0.05). Data analysis demonstrated that UTV is a very useful tool to rapidly assess elasmobranch populations in large MPAs in good visibility underwater environments. It can assess larger areas than UVC with the same effort (statistically significant difference found for the MOPUT; p=<0.001), leading to more observed species (5 vs 2) and specimens (46 vs 3) per day of work, with no loss in resolution power (MOPUA values were not significantly different between UTV and UVC; p=0.104).

Video promocional de la Biblioteca de la Universidad de Las Palmas de Gran Canaria, 2010

Video de promoción de la Biblioteca Universitaria realizado por Ginés Cedrés con música de Los Coquillos. Se recogen los distintos servicios que ofrece la Biblioteca universitaria

Video promocional del acceso abierto en la Biblioteca de la ULPGC

El Grupo de Trabajo Open Access y Derechos de Autor de la Biblioteca Universitaria pretende con este video promocionar el movimiento de Acceso Abierto (Open Access) con el fin de concienciar a la comunidad universitaria de la importancia de dar mayor visibilidad a la producción científica y académica generada por la misma.

Video promocional de la Biblioteca de la Universidad de Las Palmas de Gran Canaria, 2013

Vídeo de promoción de la Biblioteca Universitaria con música de Mariano Pávez, canción Portal de Luz, ExplendorMix por Ginés Cedrés y Mariano Pávez, de su Álbum: 13 Lunas RMX (2013). Se recogen los distintos servicios que ofrece la Biblioteca Universitaria de Las Palmas de Gran Canaria, así como las distintas bibliotecas temáticas de la misma.

Digital Video Broadcasting: Introduction

Versione preliminare per la lezione del 28/02/2008

A video database for facial behavior understanding

[EN]The use of new technologies in order to step up the inter- action between humans and machines is the main proof that faces are important in videos. Therefore we suggest a novel Face Video Database for development, testing and veri cation of algorithms related to face- based applications and to facial recognition applications. In addition of facial expression videos, the database includes body videos. The videos are taken by three di erent cameras, working in real time, without vary- ing illumination conditions.

An evolutive approach for smile recognition in video sequences

Facial expression recognition is one of the most challenging research areas in the image recognition ¯eld and has been actively studied since the 70's. For instance, smile recognition has been studied due to the fact that it is considered an important facial expression in human communication, it is therefore likely useful for human–machine interaction. Moreover, if a smile can be detected and also its intensity estimated, it will raise the possibility of new applications in the future