TimeConvNets: A Deep Time Windowed Convolution Neural Network Design for\n Real-time Video Facial Expression Recognition
Bibliographic record
Abstract
A core challenge faced by the majority of individuals with Autism Spectrum\nDisorder (ASD) is an impaired ability to infer other people's emotions based on\ntheir facial expressions. With significant recent advances in machine learning,\none potential approach to leveraging technology to assist such individuals to\nbetter recognize facial expressions and reduce the risk of possible loneliness\nand depression due to social isolation is the design of computer vision-driven\nfacial expression recognition systems. Motivated by this social need as well as\nthe low latency requirement of such systems, this study explores a novel deep\ntime windowed convolutional neural network design (TimeConvNets) for the\npurpose of real-time video facial expression recognition. More specifically, we\nexplore an efficient convolutional deep neural network design for\nspatiotemporal encoding of time windowed video frame sub-sequences and study\nthe respective balance between speed and accuracy. Furthermore, to evaluate the\nproposed TimeConvNet design, we introduce a more difficult dataset called\nBigFaceX, composed of a modified aggregation of the extended Cohn-Kanade (CK+),\nBAUM-1, and the eNTERFACE public datasets. Different variants of the proposed\nTimeConvNet design with different backbone network architectures were evaluated\nusing BigFaceX alongside other network designs for capturing spatiotemporal\ninformation, and experimental results demonstrate that TimeConvNets can better\ncapture the transient nuances of facial expressions and boost classification\naccuracy while maintaining a low inference time.\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 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 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
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.
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".