TY - JOUR

T1 - Comparing Keyframe Summaries of Egocentric Videos: Closest-to-Centroid Baseline

AU - Kuncheva, Ludmila

AU - Yousefi, Paria

AU - Almeida, Jurandy

N1 - 978-1-5386-1842-4/17/

PY - 2018/3/12

Y1 - 2018/3/12

N2 - Evaluation of keyframe video summaries is a notoriously difficult problem. So far, there is no consensus on guidelines, protocols, benchmarks and baseline models. This study contributes in three ways: (1) We propose a new baseline model for creating a keyframe summary, called Closest-to-Centroid, and show that it is a better contestant compared to the two most popular baselines: uniform sampling and choosing the mid-event frame. (2) We also propose a method for matching the visual appearance of keyframes, suitable for comparing summaries of egocentric videos and lifelogging photostreams. (3) We examine 24 image feature spaces (different descriptors) including colour, texture, shape, motion and a feature space extracted by a pretrained convolutional neural network (CNN). Our results using the four egocentric videos in the UTE database favour low-level shape and colour feature spaces for use with CC.

AB - Evaluation of keyframe video summaries is a notoriously difficult problem. So far, there is no consensus on guidelines, protocols, benchmarks and baseline models. This study contributes in three ways: (1) We propose a new baseline model for creating a keyframe summary, called Closest-to-Centroid, and show that it is a better contestant compared to the two most popular baselines: uniform sampling and choosing the mid-event frame. (2) We also propose a method for matching the visual appearance of keyframes, suitable for comparing summaries of egocentric videos and lifelogging photostreams. (3) We examine 24 image feature spaces (different descriptors) including colour, texture, shape, motion and a feature space extracted by a pretrained convolutional neural network (CNN). Our results using the four egocentric videos in the UTE database favour low-level shape and colour feature spaces for use with CC.

M3 - Conference article

JO - International Conference on Image Processing Theory, Tools and Applications (IPTA)

JF - International Conference on Image Processing Theory, Tools and Applications (IPTA)

SN - 2154-512X

T2 - Seventh International Conference on Image Processing Theory, Tools and Applications

Y2 - 28 November 2017 through 1 December 2017

ER -