Multimodal Cross-context Recognition of Negative Interactions

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientific

1 Citation (Scopus)
28 Downloads (Pure)

Abstract

Negative emotions and stress can impact human-human interactions and eventually lead to aggression. From the perspective of surveillance systems, it is of high importance to recognize as soon as an interaction escalates and human intervention is needed. One of the limitations of deploying a system in real life is that in practice it can only be trained on a limited number of situations. In this paper we examined the generalization capabilities of a trained system given context change. For this purpose we developed scenarios and made audio-visual recordings in four different contexts in which negative interactions might occur. To obtain a quantification of cross-context performance we kept the test context fixed and performed training on itself (cross-validation) and on all the other contexts. To explore whether multiple examples in the training set are beneficial, we also trained the classifier on a merged corpus of the three contexts that were not used for testing. These experiments were done with audio features, video features and audio-visual feature level fusion to investigate which modality generalizes best. We found that context change generates a decrease in performance that is varying with within-contexts similarities. Merging multiple contexts for training in most cases results in performance just below the best predictive single context. Audio is the most robust modality and in most cases the performance of audiovisual fusion is very close to the one of audio.
Original languageEnglish
Title of host publicationProceedings of Seventh International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW) 2017
PublisherIEEE
Pages56-61
Volume7
DOIs
Publication statusPublished - 2017
EventSeventh International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW) - San Antonio, United States
Duration: 23 Oct 201726 Oct 2017
Conference number: 7
http://10.1109/ACIIW.2017.8272586

Conference

ConferenceSeventh International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)
Abbreviated title ACIIW
CountryUnited States
CitySan Antonio
Period23/10/1726/10/17
Internet address

Fingerprint Dive into the research topics of 'Multimodal Cross-context Recognition of Negative Interactions'. Together they form a unique fingerprint.

Cite this