Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

A KNOWLEDGE TRANSFER AND BOOSTING APPROACH TO THE PREDICTION OF AFFECT IN MOVIES

Abstract: 

Affect prediction is a classical problem and has recently garnered special interest in multimedia applications. Affect prediction in movies is one such domain, potentially aiding the design as well as the impact analysis of movies.Given the large diversity in movies (such as different genres and languages), obtaining a comprehensive movie dataset for modeling affect is challenging while models trained on smaller datasets may not generalize. In this paper, we address the problem of continuous affect ratings with the availability of limited in-domain data resources. We initially setup several baseline models trained on in-domain data, followed by a proposal of a Knowledge Transfer (KT) + Gradient Boosting (GB) approach.KT learns models on a larger (mismatched) data which are then adapted to make predictions on the data of interest. GB further updates these predictions based on models learnt from the in-domain data.We observe that the KT + GB models provide Concordance Correlation Coefficient values of 0.13 and 0.27 for valence and affect prediction on the continuous LIRIS ACCEDE dataset against best baseline prediction values of 0.12 and 0.11. Not only the KT + GB models improve the overall performance metrics, we also observe a more consistent model performance across movies of various genres.

SigPort.zip

Package icon SigPort.zip (26 downloads)
up
0 users have voted:

Paper Details

Authors:
Sabyasachee Baruah, Rahul Gupta, Shrikanth Narayanan
Submitted On:
1 March 2017 - 9:17am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Sabyasachee Baruah
Document Year:
2017
Cite

Document Files

SigPort.zip

(26 downloads)

Subscribe

[1] Sabyasachee Baruah, Rahul Gupta, Shrikanth Narayanan, "A KNOWLEDGE TRANSFER AND BOOSTING APPROACH TO THE PREDICTION OF AFFECT IN MOVIES", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1554. Accessed: Apr. 23, 2017.
@article{1554-17,
url = {http://sigport.org/1554},
author = {Sabyasachee Baruah; Rahul Gupta; Shrikanth Narayanan },
publisher = {IEEE SigPort},
title = {A KNOWLEDGE TRANSFER AND BOOSTING APPROACH TO THE PREDICTION OF AFFECT IN MOVIES},
year = {2017} }
TY - EJOUR
T1 - A KNOWLEDGE TRANSFER AND BOOSTING APPROACH TO THE PREDICTION OF AFFECT IN MOVIES
AU - Sabyasachee Baruah; Rahul Gupta; Shrikanth Narayanan
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1554
ER -
Sabyasachee Baruah, Rahul Gupta, Shrikanth Narayanan. (2017). A KNOWLEDGE TRANSFER AND BOOSTING APPROACH TO THE PREDICTION OF AFFECT IN MOVIES. IEEE SigPort. http://sigport.org/1554
Sabyasachee Baruah, Rahul Gupta, Shrikanth Narayanan, 2017. A KNOWLEDGE TRANSFER AND BOOSTING APPROACH TO THE PREDICTION OF AFFECT IN MOVIES. Available at: http://sigport.org/1554.
Sabyasachee Baruah, Rahul Gupta, Shrikanth Narayanan. (2017). "A KNOWLEDGE TRANSFER AND BOOSTING APPROACH TO THE PREDICTION OF AFFECT IN MOVIES." Web.
1. Sabyasachee Baruah, Rahul Gupta, Shrikanth Narayanan. A KNOWLEDGE TRANSFER AND BOOSTING APPROACH TO THE PREDICTION OF AFFECT IN MOVIES [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1554