output
20022026
most citedFitNets: Hints for Thin Deep Nets

2k citations

Showing 2015Show all

8 papers · 1 filter

cs.AI2015★ 55 cited

SR-Clustering: Semantic Regularized Clustering for Egocentric Photo Streams Segmentation

Mariella Dimiccoli, Marc Bolaños, Estefania Talavera +3

While wearable cameras are becoming increasingly popular, locating relevant information in large unstructured collections of egocentric images is still a tedious and time consuming…

cs.CV2015★ 749 cited

Unsupervised Deep Feature Extraction for Remote Sensing Image Classification

Adriana Romero, Carlo Gatta, Gustau Camps-Valls

This paper introduces the use of single layer and deep convolutional networks for remote sensing data analysis. Direct application to multi- and hyper-spectral imagery of supervise…

cs.CV2015★ 5 cited

A Computational Model for Amodal Completion

Maria Oliver, Gloria Haro, Mariella Dimiccoli +2

This paper presents a computational model to recover the most likely interpretation of the 3D scene structure from a planar image, where some objects may occlude others. The estima…

cs.CV2015★ 2 cited

Active skeleton for bacteria modeling

Jean-Pascal Jacob, Mariella Dimiccoli, Lionel Moisan

The investigation of spatio-temporal dynamics of bacterial cells and their molecular components requires automated image analysis tools to track cell shape properties and molecular…

cs.CV2015★ 23 cited

Multi-Face Tracking by Extended Bag-of-Tracklets in Egocentric Videos

Maedeh Aghaei, Mariella Dimiccoli, Petia Radeva

Wearable cameras offer a hands-free way to record egocentric images of daily experiences, where social events are of special interest. The first step towards detection of social ev…

cs.CV2015★ 34 cited

Query by String word spotting based on character bi-gram indexing

Suman K. Ghosh, Ernest Valveny

In this paper we propose a segmentation-free query by string word spotting method. Both the documents and query strings are encoded using a recently proposed word representa- tion…