2016 IEEE International Conference on Image Processing (ICIP)

Visit the conference page.


Thanks to the low operational cost and large storage capacity of smartphones and wearable devices, people are recording many hours of daily activities, sport actions and home videos. These videos, also known as egocentric videos, are generally long-running streams with unedited content, which make them boring and visually unpalatable, bringing up the challenge to make egocentric videos more appealing. In this work, we propose a novel methodology to compose the new fast-forward video by selecting frames based on semantic information extracted from images. The experiments show that our approach outperforms the state-of-the-art as far as semantic information is concerned and that it is also able to produce videos that are more pleasant to be watched.

Keywords: Semantic Information, First-person Video, Fast-Forward, Video Sampling, Video Segmentation


Offical Publication

Source code



Conference Poster

Methodology and Results.


author = {W. L. S. Ramos and M. M. Silva and M. F. M. Campos and E. R. Nascimento},
booktitle = {IEEE International Conference on Image Processing (ICIP)},
title = {Fast-forward video based on semantic extraction},
year = {2016},
month = {Sep.},
address = {Phoenix, USA},
pages = {3334-3338},
doi = {10.1109/ICIP.2016.7532977}


We compare this proposed methodology against the following methods:


We conducted the experimental evaluation using the datasets:


Back to the project page.