Facial Expression Recognition using Encoded Dynamic Features
Open accessAbstract
In this paper, we propose a new approach of facial expression recognition. In order to capture the temporal characteristic of facial expressions, we design dynamic haar-like features to represent the facial images, and code them into binary patterns for the further analysis. Based on the encoded features, Adaboost is employed to learn the combination of optimal discriminant features to construct the classifier. The experiments carried on the CMU database show the promising performance of the proposed method.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Previous FER methods treat the texture or landmark modality independently, using only one modality for FER.
“Mostly, all previous work treats the texture or landmark modality independently, where only the texture or landmark modality is employed for FER.”
From Multimodal learning for facial expression recognition (2015) · cites this paper as [6]
The Introduction (page unavailable) describes earlier facial-expression methods using appearance features and another using key-point tracking. These examples support the distinction between appearance and landmark approaches, but the paper does not establish that mostly all previous methods used only one modality or treated the two independently. (LLM, conf=0.78)
Experimental — accuracy not yet measuredPrevious FER methods are two-step: handcrafted features are extracted from texture or landmark, then classifiers such as SVM or Adaboost are trained on the extracted features.
“As aforementioned, the previous FER methods can be regarded as a type of two-step methods.”
From Multimodal learning for facial expression recognition (2015) · cites this paper as [6]
The Introduction describes earlier image-based methods as recognizing expressions from appearance features and discusses earlier methods using motion parameters or tracked key points. It also describes the paper’s own feature-extraction and boosting-classifier stages. These passages support the broad two-step characterization, but do not establish the claim that previous methods generally extracted texture or landmark features and then trained SVM or AdaBoost classifiers. No page numbers are available in our copy. (LLM, conf=0.82)
Experimental — accuracy not yet measuredROC curves are more general and reliable than recognition accuracy for evaluating FER systems.
“The receiver operating characteristic (ROC) curves are employed as the criterion to evaluate the performance, which is more general and reliable than recognition accuracy [6] for evaluating the FER system.”
From Multimodal learning for facial expression recognition (2015) · cites this paper as [6]
The Introduction (page not provided) discusses facial-expression recognition methods, but does not compare evaluation criteria. Searches for ROC curves, recognition accuracy, and evaluation performance found no passage in our copy saying ROC curves are more general or reliable than recognition accuracy. (LLM, conf=0.72)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Automatic analysis of facial expressions: the state of the art
Pantie, M., & Rothkrantz, L. J. M. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.895976 · Cited by 1,778 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Multimodal learning for facial expression recognition
Zhang, W., Zhang, Y., Ma, L., Guan, J., & Gong, S. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.04.012 · Cited by 100 · see citing works
- Authors
- Yang, P., Liu, Q., & Metaxas, D. N.
- Affiliations
- Rutgers, The State University of New Jersey (US)
- Venue
- Multimedia and Expo, 2007 IEEE International Conference on
- Publisher
- IEEE
- Published
- 2007-07
- Pages
- 1107-1110
- OpenAlex
- W2092946680
- Cited by
- 33
- References
- 1
- Citations by year
- 2024: 1 · 2022: 2 · 2021: 1 · 2020: 2 · 2019: 1 · 2018: 1 · 2017: 3 · 2016: 3 · 2015: 2 · 2014: 3 · 2013: 1 · 2012: 3
- FWCI
- 1.37
- Type
- conference paper
- Language
- en
- Open access
- green
- zenodo.org
- Licence
- public-domain
- Locations
- IEEE International Conference on Multimedia and Expo (ICME) (publishedVersion)
- Zenodo (CERN European Organization for Nuclear Research) (submittedVersion, public-domain)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face and Expression Recognition
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Keywords
- facial expression recognition, temporal features, AdaBoost
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
