Canal9: A database of political debates for analysis of social interactions

Vinciarelli, Alessandro; Dielmann, Alfred; Favre, Sarah; Salamin, Hugues

doi:10.1109/acii.2009.5349466

Cited by 76 publications

(52 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The only existing database that has been released primarily to serve research on machine analysis of conflict is the SSPNet Conflict Corpus [20], which consists of 1430 clips of 30 seconds extracted from the Canal9 Corpus [19] -a collection of audio-visual recordings from 45 political debates aired on the Swiss TV (in French) -corresponding to 138 subjects in total. Each clip of the database has been annotated in terms of a single continuous conflict score in the range [−10, +10] for the purposes of the sequence-level binary classification and regression tasks of the Conflict Sub-Challenge included in the Interspeech 2013 Computational Paralinguistics Challenge [20].…”

Section: Prior Workmentioning

confidence: 99%

The Conflict Escalation Resolution (CONFER) Database

Georgakis

Panagakis

Zafeiriou

et al. 2017

Image and Vision Computing

View full text Add to dashboard Cite

Conflict is usually defined as a high level of disagreement taking place when individuals act on incompatible goals, interests, or intentions. Research in human sciences has recognized conflict as one of the main dimensions along which an interaction is perceived and assessed. Hence, automatic estimation of conflict intensity in naturalistic conversations would be a valuable tool for the advancement of human-centered computing and the deployment of novel applications for social skills enhancement including conflict management and negotiation. However, machine analysis of conflict is still limited to just a few works, partially due to an overall lack of suitable annotated data, while it has been mostly approached as a conflict or (dis)agreement detection problem based on audio features only. In this work, we aim to overcome the aforementioned limitations by a) presenting the Conflict Escalation Resolution (CONFER) Database, a set of excerpts from audio-visual recordings of televised political debates where conflicts naturally arise, and b) reporting baseline experiments on audio-visual conflict intensity estimation. The database contains approximately 142 minutes of recordings in Greek language, split over 120 non-overlapping episodes of naturalistic conversations that involve two or three interactants. Subject-and session-independent experiments are conducted on continuous-time (frame-by-frame) estimation of real-valued conflict intensity, as opposed to binary conflict/non-conflict clas- * Corresponding author. E-mail address: christos.georgakis@imperial.ac.uk Preprint submitted to Image and Vision Computing December 20, 2016 A C C E P T E D M A N U S C R I P T ACCEPTED MANUSCRIPTsification. For the problem at hand, the efficiency of various audio and visual features and fusion of them as well as various regression frameworks is examined. Experimental results suggest that there is much room for improvement in the design and development of automated multi-modal approaches to continuous conflict analysis. The CONFER Database is publicly available for non-commercial use at http://ibug.doc.ic.ac.uk/resources/confer/.

show abstract

Section: Prior Workmentioning

confidence: 99%

The Conflict Escalation Resolution (CONFER) Database

Georgakis

Panagakis

Zafeiriou

et al. 2017

Image and Vision Computing

View full text Add to dashboard Cite

show abstract

“…Fig. 2), provided by Vinciarelli et al [14] in 2009. To the best of our knowledge, this is the only publicly available data set that can be used to test audiovisual structuring tasks.…”

Section: Resultsmentioning

confidence: 99%

Unsupervised Mining of Multiple Audiovisually Consistent Clusters for Video Structure Analysis

Gravier

2012

2012 IEEE International Conference on Multimedia and Expo

View full text Add to dashboard Cite

We address the problem of detecting multiple audiovisual events related to the edit structure of a video by incorporating an unsupervised cluster analysis technique into a cluster selection method designed to measure coherence between audio and visual segments. First, mutual information measure is used to select audio-visually consistent clusters from two dendrograms representing hierarchical clustering results respectively for the audio and visual modalities. A cluster analysis technique is then applied to define events from the audio-visual (AV) clusters with segments co-occurring frequently. Candidate events are then characterized by groups of AV clusters from which models are built by automatically selecting positive and negative examples. Experiments on the standard Canal9 data set demonstrates that our method is capable of discovering multiple audiovisual events in a totally unsupervised manner.

show abstract

“…We evaluated our approach using the Canal9 dataset [11], where the task is to recognize agreement and disagreement from nonverbal audio-visual cues during spontaneous political debates. The Canal9 dataset is a collection of 72 political debates recorded by the Canal 9 TV station in Switzerland, with a total of roughly 42 hours of recordings.…”

Section: Datasetmentioning

confidence: 99%

“…learning the complex relationship across modalities is non-trivial. Figure 1(a) shows a pair of time-aligned sequences with audio and visual features (from [11]; details can be found in Section 4.1). When learning with this type of data, it is important to consider the correlation and interaction across modalities: An underlying correlation structure between modalities may make the amplitude of the signal from one modality different in relation to the signal from another modality, e.g., loud voice with exaggerated gestures.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multimodal human behavior analysis

Song

Morency

Davis

2012

Proceedings of the 14th ACM International Conference on Multimodal Interaction

View full text Add to dashboard Cite

Multimodal human behavior analysis is a challenging task due to the presence of complex nonlinear correlations and interactions across modalities. We present a novel approach to this problem based on Kernel Canonical Correlation Analysis (KCCA) and Multi-view Hidden Conditional Random Fields (MV-HCRF). Our approach uses a nonlinear kernel to map multimodal data to a high-dimensional feature space and finds a new projection of the data that maximizes the correlation across modalities. We use a multi-chain structured graphical model with disjoint sets of latent variables, one set per modality, to jointly learn both view-shared and view-specific substructures of the projected data, capturing interaction across modalities explicitly. We evaluate our approach on a task of agreement and disagreement recognition from nonverbal audio-visual cues using the Canal 9 dataset. Experimental results show that KCCA makes capturing nonlinear hidden dynamics easier and MV-HCRF helps learning interaction across modalities.

show abstract

Canal9: A database of political debates for analysis of social interactions

Cited by 76 publications

References 6 publications

The Conflict Escalation Resolution (CONFER) Database

The Conflict Escalation Resolution (CONFER) Database

Unsupervised Mining of Multiple Audiovisually Consistent Clusters for Video Structure Analysis

Multimodal human behavior analysis

Contact Info

Product

Resources

About