Introducing the Geneva Multimodal Emotion Portrayal (GEMEP) corpus

By Tanja Bänziger, Klaus R. Scherer. 2010

216 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/84fbdd5923781dba16b8343b2ab3bfd418180862

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances (2022, background): “Santhoshkumar and Geetha successively proposed emotion recognition, by using both histogram of orientation gradient (HOG) and HOG-KLT features from the sequences [305], or by calculating and extracting four kinds of geometric body expressive features [306], which achieved the best recognition accura”
The Body Action and Posture Coding System (BAP): Development and Reliability (2012, methodology): “The GEMEP Corpus as Development Material This coding system was developed using the Geneva Multimodal Emotion Portrayals (GEMEP) corpus (Bänziger and Scherer 2010).”
Exploiting sparsity and co-occurrence structure for action unit recognition (2015, background): “• MATLAB code available at http://people.csail. mit.edu/yalesong/fg15”
Image based Static Facial Expression Recognition with Multiple Deep Network Learning (2015, background): “Many early facial recognition datasets [23, 36, 3, 14, 27, 4, 24, 35] were collected under “lab-controlled” environments where subjects were asked to artificially generate certain expressions [8].”
DISFA: A Spontaneous Facial Action Intensity Database (2013, background): “Recent efforts to address this need include GEMEP [14] and the Belfast-induced emotions database [16].”
CREMA-D: Crowd-sourced Emotional Multimodal Actors Dataset (2014, methodology): “The GEMEP database [31] includes ratings with 15 categories, with at least 23 raters per clip, using all three rating modalities.”
The first facial expression recognition and analysis challenge (2011, methodology): “Baenziger and Scherer [1] showed that portrayed expressions of the GEMEP are recognized by lay judges with an accuracy level that, for all emotions, largely exceeds chance level, and that inter-rater reliability for category judgements and perceived believability and intensity of the portrayal is ve”
Towards multimodal sentiment analysis: harvesting opinions from the web (2011, methodology): “Further, most sentiment analysis datasets are created by the researchers in the scientific environment with accurate precision recording and reduced noises [6, 4, 11].”
Static facial expression analysis in tough conditions: Data, evaluation protocol and benchmark (2011, unknown): “The GEMEP dataset [3] consists of actors speaking dialogues and expressing emotions.”
The Role of Perceived Voice and Speech Characteristics in Vocal Emotion Communication (2014, methodology): “The second study constitutes a replication, using the same rating scales with a different set of portrayed VEEs (the Geneva Multimodal Emotion Portrayal corpus, GEMEP; Bänziger et al. 2012; Bänziger and Scherer 2010) and a simplified rating procedure.”