MétaCan
Menu
Back to cohort

A CNN Approach to Micro-Expressions Detection

2021· article· en· W3175558462 on OpenAlexaff
Satya Chandrashekhar Ayyalasomayajula, Bogdan Ionescu, Dan Ionescu

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldPsychology
TopicEmotion and Mood Recognition
Canadian institutionsUniversity of Ottawa
Fundersnot available
KeywordsConvolutional neural networkComputer scienceFacial expressionArtificial intelligenceFace (sociological concept)Pattern recognition (psychology)Expression (computer science)Deep learningMagnificationFace detectionFacial recognition systemSpeech recognition

Abstract

fetched live from OpenAlex

Machine Learning and Convolutional Neural Networks (CNN) have significantly increased the performance in image recognition and are being widely adopted to analyze faces based on availability of very large databases of Figure and postures. A hot research interest of the the Face Recognition community is the recognition of different types of facial expressions. Among these, Facial Micro-Expressions (ME's) are of big interest due to subtle movements which can show deep or suppressed emotions of an individual. These micro-expressions are quite prominently being used in security, psychotherapy, neuroscience and other related disciplines. The major challenge encountered while detecting these expressions are their low intensity and short duration. Previous works have used Eulerian Video Magnification (EVM) in conjunction with haar-cascades for face detection which gave misleading results. In this paper, we have proposed a special Convolutional Neural Network (CNN) model for face detection on which EVM is applied for amplifying the micro-expressions to a calculated threshold. Following that, a separately trained CNN is used to classify the formerly detected micro-expression into one of the seven universal micro expressions. Results obtained during the test experiment are presented at the end of the paper.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesInsufficient payload (model declined to judge)
Consensus categoriesInsufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.788
Threshold uncertainty score0.998

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0040.002

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.048
GPT teacher head0.319
Teacher spread0.271 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; both teacher heads agree on what is shown here.

Study designBench or experimental
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations8
Published2021
Admission routes1
Has abstractyes

Explore more

Same topicEmotion and Mood RecognitionFrench-language works237,207