Integrating Multimodal Data for Deep Learning-Based Facial Emotion Recognition
Bibliographic record
Abstract
With the rapid development of neural networks, emotion recognition has become a research area of great concern. It has important applications not only in marketing and human-computer interaction but also holds significant importance for improving emotional computing and user experience. This paper studies various methods for emotion recognition in images and videos, utilizing convolutional neural networks (CNN), multi-layer perceptron (MLP), and fusion models. The Facial Expression Recognition 2013 (FER2013) image dataset and the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) audio and video dataset serve as the basis for this study. The experimental results indicate that ResNet18 outperforms others in image emotion recognition, attributed to its residual block design and the incorporation of regularization techniques. In the realm of video emotion recognition, the audio model based on MLP demonstrates a superior ability to identify emotional information. Although the fusion of image and audio models theoretically could enhance accuracy, the randomness of video frames prevents the fusion model from achieving the desired effect. Future research might further explore the application of time series models in video emotion recognition to capture continuous emotional changes within videos.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".