Abstract

There is an increasing demand for applications that can detect changes in human affect or behavior especially in the fields of health care and crime detection. Detection of changes in continuous human affect dimensions from multimedia data precedes the exact prediction of an emotion as a continuum. With the growth in the dimensions of emotion space there is a need to discover latent descriptors (topics) that can explain these complex states. Considering that at every time step the audio/video frames constitute a set of such latent topics, the presence and absence of changes in emotion should effect the topics in those frames. Based on this assumption an Adaptive Temporal Topic model (ATTM) based change detection algorithm is presented that, at each time step, detects whether a significant change in human affect has occurred. ATTM is a probabilistic topic model that extends Latent Dirichlet Allocation model by incorporating the temporal dependencies between human audio/video 'documents' and generates refined topics. The topics assigned to a document by ATTM are adapted to the presence or absence of a change in the affect dimension at that time step. ATTM along with different regression models has been tested on the multimodal Audio Visual Emotion Challenge (AVEC 2012) data and has shown promising results in comparison to existing temporal and non-temporal topic models.

Original languageEnglish (US)
Title of host publication2013 IEEE International Conference on Multimedia and Expo, ICME 2013
DOIs
StatePublished - 2013
Event2013 IEEE International Conference on Multimedia and Expo, ICME 2013 - San Jose, CA, United States
Duration: Jul 15 2013Jul 19 2013

Other

Other2013 IEEE International Conference on Multimedia and Expo, ICME 2013
CountryUnited States
CitySan Jose, CA
Period7/15/137/19/13

Fingerprint

Crime
Health care
Statistical Models

Keywords

  • Change Detection
  • Human Emotion Recognition algorithm
  • Topic Models
  • Video Audio data

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Lade, P., Balasubramanian, V. N., Demakethepalli Venkateswara, H., & Panchanathan, S. (2013). Detection of changes in human affect dimensions using an Adaptive Temporal Topic model. In 2013 IEEE International Conference on Multimedia and Expo, ICME 2013 [6607627] https://doi.org/10.1109/ICME.2013.6607627

Detection of changes in human affect dimensions using an Adaptive Temporal Topic model. / Lade, Prasanth; Balasubramanian, Vineeth N.; Demakethepalli Venkateswara, Hemanth; Panchanathan, Sethuraman.

2013 IEEE International Conference on Multimedia and Expo, ICME 2013. 2013. 6607627.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lade, P, Balasubramanian, VN, Demakethepalli Venkateswara, H & Panchanathan, S 2013, Detection of changes in human affect dimensions using an Adaptive Temporal Topic model. in 2013 IEEE International Conference on Multimedia and Expo, ICME 2013., 6607627, 2013 IEEE International Conference on Multimedia and Expo, ICME 2013, San Jose, CA, United States, 7/15/13. https://doi.org/10.1109/ICME.2013.6607627
Lade P, Balasubramanian VN, Demakethepalli Venkateswara H, Panchanathan S. Detection of changes in human affect dimensions using an Adaptive Temporal Topic model. In 2013 IEEE International Conference on Multimedia and Expo, ICME 2013. 2013. 6607627 https://doi.org/10.1109/ICME.2013.6607627
Lade, Prasanth ; Balasubramanian, Vineeth N. ; Demakethepalli Venkateswara, Hemanth ; Panchanathan, Sethuraman. / Detection of changes in human affect dimensions using an Adaptive Temporal Topic model. 2013 IEEE International Conference on Multimedia and Expo, ICME 2013. 2013.
@inproceedings{c3d5185746da42c58f4397a521afaa64,
title = "Detection of changes in human affect dimensions using an Adaptive Temporal Topic model",
abstract = "There is an increasing demand for applications that can detect changes in human affect or behavior especially in the fields of health care and crime detection. Detection of changes in continuous human affect dimensions from multimedia data precedes the exact prediction of an emotion as a continuum. With the growth in the dimensions of emotion space there is a need to discover latent descriptors (topics) that can explain these complex states. Considering that at every time step the audio/video frames constitute a set of such latent topics, the presence and absence of changes in emotion should effect the topics in those frames. Based on this assumption an Adaptive Temporal Topic model (ATTM) based change detection algorithm is presented that, at each time step, detects whether a significant change in human affect has occurred. ATTM is a probabilistic topic model that extends Latent Dirichlet Allocation model by incorporating the temporal dependencies between human audio/video 'documents' and generates refined topics. The topics assigned to a document by ATTM are adapted to the presence or absence of a change in the affect dimension at that time step. ATTM along with different regression models has been tested on the multimodal Audio Visual Emotion Challenge (AVEC 2012) data and has shown promising results in comparison to existing temporal and non-temporal topic models.",
keywords = "Change Detection, Human Emotion Recognition algorithm, Topic Models, Video Audio data",
author = "Prasanth Lade and Balasubramanian, {Vineeth N.} and {Demakethepalli Venkateswara}, Hemanth and Sethuraman Panchanathan",
year = "2013",
doi = "10.1109/ICME.2013.6607627",
language = "English (US)",
isbn = "9781479900152",
booktitle = "2013 IEEE International Conference on Multimedia and Expo, ICME 2013",

}

TY - GEN

T1 - Detection of changes in human affect dimensions using an Adaptive Temporal Topic model

AU - Lade, Prasanth

AU - Balasubramanian, Vineeth N.

AU - Demakethepalli Venkateswara, Hemanth

AU - Panchanathan, Sethuraman

PY - 2013

Y1 - 2013

N2 - There is an increasing demand for applications that can detect changes in human affect or behavior especially in the fields of health care and crime detection. Detection of changes in continuous human affect dimensions from multimedia data precedes the exact prediction of an emotion as a continuum. With the growth in the dimensions of emotion space there is a need to discover latent descriptors (topics) that can explain these complex states. Considering that at every time step the audio/video frames constitute a set of such latent topics, the presence and absence of changes in emotion should effect the topics in those frames. Based on this assumption an Adaptive Temporal Topic model (ATTM) based change detection algorithm is presented that, at each time step, detects whether a significant change in human affect has occurred. ATTM is a probabilistic topic model that extends Latent Dirichlet Allocation model by incorporating the temporal dependencies between human audio/video 'documents' and generates refined topics. The topics assigned to a document by ATTM are adapted to the presence or absence of a change in the affect dimension at that time step. ATTM along with different regression models has been tested on the multimodal Audio Visual Emotion Challenge (AVEC 2012) data and has shown promising results in comparison to existing temporal and non-temporal topic models.

AB - There is an increasing demand for applications that can detect changes in human affect or behavior especially in the fields of health care and crime detection. Detection of changes in continuous human affect dimensions from multimedia data precedes the exact prediction of an emotion as a continuum. With the growth in the dimensions of emotion space there is a need to discover latent descriptors (topics) that can explain these complex states. Considering that at every time step the audio/video frames constitute a set of such latent topics, the presence and absence of changes in emotion should effect the topics in those frames. Based on this assumption an Adaptive Temporal Topic model (ATTM) based change detection algorithm is presented that, at each time step, detects whether a significant change in human affect has occurred. ATTM is a probabilistic topic model that extends Latent Dirichlet Allocation model by incorporating the temporal dependencies between human audio/video 'documents' and generates refined topics. The topics assigned to a document by ATTM are adapted to the presence or absence of a change in the affect dimension at that time step. ATTM along with different regression models has been tested on the multimodal Audio Visual Emotion Challenge (AVEC 2012) data and has shown promising results in comparison to existing temporal and non-temporal topic models.

KW - Change Detection

KW - Human Emotion Recognition algorithm

KW - Topic Models

KW - Video Audio data

UR - http://www.scopus.com/inward/record.url?scp=84885571161&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885571161&partnerID=8YFLogxK

U2 - 10.1109/ICME.2013.6607627

DO - 10.1109/ICME.2013.6607627

M3 - Conference contribution

AN - SCOPUS:84885571161

SN - 9781479900152

BT - 2013 IEEE International Conference on Multimedia and Expo, ICME 2013

ER -