BibTeX
@MISC{Fiss_meanhuman,
author = {Juliet Fiss and Aseem Agarwala and Brian Curless},
title = {Mean Human Score},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Frame Number Figure 1: A plot of the ratings assigned by humans in our psychology study (mean shown in dark gray, per-frame standard deviation shown in light gray), and the ratings assigned by our predictive model (cyan) across the frames of a short video sequence. Both series of ratings have been normalized by their mean and standard deviation. We also show several automatically-selected video frames at peaks (green, top) and valleys (red, bottom) of our predicted rating. In this paper, we train a computer to select still frames from video that work well as candid portraits. Because of the subjective nature of this task, we conduct a human subjects study to collect ratings of video frames across multiple videos. Then, we compute a number of features and train a model to predict the average rating of a video frame. We evaluate our model with cross-validation, and show that it is better able to select quality still frames than previous techniques, such as simply omitting frames that contain blinking or motion blur, or selecting only smiles. We also evaluate our technique qualitatively on videos that were not part of our validation set, and were taken outdoors and under different lighting conditions. Links: DL PDF WEB VIDEO DATA 1
Keyphrases
mean human score video frame psychology study predicted rating multiple video per-frame standard deviation motion blur frame number figure dl pdf web video data average rating previous technique predictive model different lighting condition several automatically-selected video frame subjective nature candid portrait standard deviation light gray short video sequence human subject
