MétaCan
Menu
Back to cohort
Record W4298054249 · doi:10.48550/arxiv.1503.01800

EmoNets: Multimodal deep learning approaches for emotion recognition in\n video

2015· preprint· en· W4298054249 on OpenAlexfundno aff
Samira Ebrahimi Kahou, Xavier Bouthillier, Pascal Lamblin, Çağlar Gülçehre, Vincent Michalski, Kishore Konda, Sébastien Jean, Pierre Froumenty, Yann Dauphin, Nicolas Boulanger-Lewandowski, Raul Chandias Ferrari, Mehdi Mirza, David Warde-Farley, Aaron Courville, P. Vincent, Roland Memisevic, Christopher Pal, Yoshua Bengio

Bibliographic record

VenuearXiv (Cornell University) · 2015
Typepreprint
Languageen
FieldPsychology
TopicEmotion and Mood Recognition
Canadian institutionsnot available
FundersBundesministerium für Bildung und ForschungNatural Sciences and Engineering Research Council of CanadaCanadian Institute for Advanced Research
KeywordsComputer scienceArtificial intelligenceAutoencoderConvolutional neural networkDeep learningClassifier (UML)ModalitiesModality (human–computer interaction)Pattern recognition (psychology)Test setFeature learningMachine learning

Abstract

fetched live from OpenAlex

The task of the emotion recognition in the wild (EmotiW) Challenge is to\nassign one of seven emotions to short video clips extracted from Hollywood\nstyle movies. The videos depict acted-out emotions under realistic conditions\nwith a large degree of variation in attributes such as pose and illumination,\nmaking it worthwhile to explore approaches which consider combinations of\nfeatures from multiple modalities for label assignment. In this paper we\npresent our approach to learning several specialist models using deep learning\ntechniques, each focusing on one modality. Among these are a convolutional\nneural network, focusing on capturing visual information in detected faces, a\ndeep belief net focusing on the representation of the audio stream, a K-Means\nbased "bag-of-mouths" model, which extracts visual features around the mouth\nregion and a relational autoencoder, which addresses spatio-temporal aspects of\nvideos. We explore multiple methods for the combination of cues from these\nmodalities into one common classifier. This achieves a considerably greater\naccuracy than predictions from our strongest single-modality classifier. Our\nmethod was the winning submission in the 2013 EmotiW challenge and achieved a\ntest set accuracy of 47.67% on the 2014 dataset.\n

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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.378
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0000.000

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 head0.232
GPT teacher head0.247
Teacher spread0.015 · 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; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
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

Citations1
Published2015
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicEmotion and Mood RecognitionFrench-language works237,207