The paper introduces a disagreement‑aware dynamic facial expression recognition framework that directly learns from raw annotator vote vectors using a Dirichlet‑Multinomial likelihood, preserving both predictive mean and scale‑sensitive supervision. It adds an ambiguity head to estimate annotation entropy for unseen clips and employs a Chow‑style reject rule that integrates ambiguity, vacuity, temporal instability, and input quality for selective prediction. On the DFEW benchmark, the method maintains recognition accuracy while cutting expected calibration error by 30 % and area‑under‑risk‑curve by 15 %, with predicted ambiguity correlating 0.52 (Spearman) with true annotation entropy, and these gains transfer to FERV39k and hold under identity‑ and movie‑disjoint splits.
Dynamic facial expression recognition (DFER) benchmarks such as DFEW provide multiple annotator votes per clip, yet most models collapse them to a majority label and cannot represent human disagreemen...
arXiv:2409. 00240v2 Announce Type: replace-cross Abstract: Automatic facial action unit (AU) recognition is used widely in facial expression analysis.
arXiv:2607. 12774v1 Announce Type: cross Abstract: This article presents our results for the 11th Affective Behavior Analysis in-the-Wild (ABAW) competition.
arXiv:2604. 15280v2 Announce Type: replace-cross Abstract: Understanding emotions is a fundamental ability for intelligent systems to be able to interact with humans.
arXiv:2606. 27536v1 Announce Type: cross Abstract: Speech emotion recognition (SER) often relies on hard consensus labels that collapse annotator disagreement.
Chehre is an emoji‑prompted video dataset designed to study perceptual flexibility in video language models. It contains 2,111 videos of 203 participants expressing 40 facial emojis, with each video annotated by about 30 perceivers, yielding 1,242 annotators in total. The dataset introduces a new task—distributional expression recognition—that evaluates a model’s ability to reproduce the variation seen in human annotations, and shows that persona prompting can shift model perception to better match human variability.
The paper introduces Evidential Multimodal Transformers with Dempster-Shafer Fusion (EMT-DS) for emotion recognition, which models predictions as Dirichlet distributions to separate epistemic and aleatoric uncertainty. EMT-DS fuses modality-specific belief masses using Dempster's Rule, explicitly quantifying conflict and producing more diffuse predictions when evidence is contradictory. Across four benchmarks, EMT-DS outperforms baselines, reduces calibration error, remains robust to noise, and its conflict metric can flag misclassifications for selective prediction.
Conventional face recognition relies on static appearance cues and degrades in unconstrained settings with expression variation, occlusion, and poor lighting. We hypothesize that audiovisual expression dynamics carry identity-discriminative information complementary to static appearance, and that extracting this signal requires multimodal representations robust to the variable input quality of in-the-wild video.
arXiv:2606. 02679v1 Announce Type: new Abstract: Multimodal systems often benefit from combining information across language, sound, and visual streams, but this benefit is not guaranteed.
The paper examines whether model uncertainty aligns with human disagreement on vision tasks. Using multi‑annotator datasets (FER+ and CIFAR‑10H), the authors find that pretrained models rarely reflect the ambiguity humans perceive, with weak correlations between model confidence and human disagreement. Predictive multiplicity offers only modest improvement, indicating that common uncertainty metrics fail to flag ambiguous cases.
DisFace3DNet is a facial attractiveness prediction model that disentangles 3D facial components—identity, skin, hair, light, background, expression, and pose—to learn seven component reference scores from overall ratings using weak semantic supervision. The model combines five static and two signed dynamic scores to produce an overall rating, revealing each component’s numerical contribution and enabling component‑specific comparisons across images. On the SCUT‑FBP5500 dataset, it achieves a Pearson correlation of 0.8904±0.0063 with human ratings, with skin, hair, and facial shape contributing most to prediction variation.
The paper tackles the challenge of predicting student engagement from online tutoring videos, noting that engagement is a complex, multidimensional construct influenced by behavioral, emotional, and cognitive states. By analyzing the CASED dataset, the authors highlight the difficulty posed by high inter‑person variability and subjective annotations. They propose a multimodal framework that fuses implicit spatiotemporal features from pretrained video, audio, and image encoders with structured behavioral cues such as head pose, gaze, facial action units, emotion, and wavelet‑based audio features, integrating them via a Perceiver IO bottleneck and modeling participant personalities with variational posteriors. The system employs evidential regression and spectral‑normalized Gaussian process classification heads to provide uncertainty‑aware predictions, achieving competitive performance on the CASED challenge test set while offering well‑calibrated uncertainty metrics.