Bibliographic record
Abstract
Safeguarding the well-being of women and children presents a challenging research endeavor. Multimodal emotion recognition poses a formidable task within this domain. The field of Human-Computer Interaction (HCI) heavily relies on multimodal data, encompassing audio, video, text, facial expressions, body motions, bio-signals, and physiological data, to predict the safety of women and children. Substantial research efforts have been dedicated to this cause. To develop an optimal multimodal model for emotion recognition, which integrates visual, textual, auditory, and video modalities, a novel deep learning framework is proposed. This framework involves a comprehensive analysis of data, feature extraction, and model-level fusion. Innovative feature extractor networks are tailored specifically for processing visual, textual, auditory, and video data. At the model level, an effective multimodal emotion recognition model is devised, synthesizing information from images, text, voice, and video. The proposed models exhibit impressive performance on three benchmark multimodal datasets, namely IEMOCAP, Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), and Surrey Audio-Visual Expressed Emotion (SAVEE), achieving high predicted accuracies of 96%, 97%, and 97%, respectively. Comparative analysis with existing emotion recognition models further validates the efficacy and optimality of the proposed approach. The application of multimodal enhanced emotion recognition holds promise in predicting women and children's safety. Index Terms: Facial Expression Recognition, Deep Learning, Multimodal, Women's Safety, Audio-Visual Media, Fusion.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".