Automatic emotion recognition based on body movement analysis: a survey
Abstract
Humans are emotional beings, and their feelings influence how they perform and interact with computers. One of the most expressive modalities for humans is body posture and movement, which researchers have recently started exploiting for emotion recognition. This survey describes emerging techniques and modalities related to emotion recognition based on body movement, as well as recent advances in automatic emotion recognition. It also describes application areas and notation systems and explains the importance of movement segmentation. It then discusses unsolved problems and provides promising directions for future research. The Web extra (a PDF file) contains tables with additional information related to the article.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Marechal et al. (2019) show that affective state can be extracted both from the user's pose, physiological features like blood pressure, and from facial features.
“In a survey on multimodal approaches for emotion detection, Marechal et al. (2019) show that affective state can be extracted both from the user's pose (Zacharatos et al., 2014), physiological features like blood pressure (Shu et al., 2018), and from facial features (Ekman, 1993).”
From Modeling Feedback in Interaction With Conversational Agents—A Review (2022) · cites this paper as Zacharatos et al., 2014
The citation lists haven’t been fetched yet
References 31 · Cited by 77
- Authors
- Zacharatos, H., Gatzoulis, C., & Chrysanthou, Y. L.
- Affiliations
- University of Cyprus (CY)
- Bahrain Polytechnic (BH)
- Venue
- IEEE Computer Graphics and Applications
- Published
- 2014-11
- Volume
- 34
- Issue
- 6
- Pages
- 35-45
- ISSN
- 0272-1716 (ISSN-L)
- 1558-1756
- OpenAlex
- W1966424962
- Cited by
- 77
- References
- 31
- Citations by year
- 2026: 4 · 2025: 7 · 2024: 11 · 2023: 7 · 2022: 11 · 2021: 7 · 2020: 5 · 2019: 10 · 2018: 4 · 2017: 4 · 2016: 6 · 2015: 1
- FWCI
- 5.10
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Computer Graphics and Applications (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Keywords
- automatic emotion recognition, body movement analysis, posture, movement segmentation, notation systems, affective computing, human-computer interaction
- MeSH terms
- Automation, Data Collection, Emotions, Humans, Movement
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
