Task-specific pre-training is essential when task representations diverge from generic pre-training features.

This supplementary material is divided into two main sections: Benchmarking Results and Cross-Data Results. The Benchmarking Results section reports average model performance using a Leave-OneSubject-Out (LOSO) validation strategy, calculated across all participants within each dataset. Results are reported as mean standard deviation, capturing both central tendency and variability, across all modeling paradigms for arousal, valence, and four-class classification using the EDA, PPG, and combined EDA+PPG modalities, see section 2. The Cross-Data Results section evaluates model generalizability across datasets. It begins with individual transfer experiments, where models trained on all datasets within a group (device, label, or setting) are tested on the remaining two datasets group. This is followed by a Leave-One-Dataset-Out (LODO) in-cohort analysis, in which models are trained on all but one dataset within a group and evaluated on the held-out dataset, and a zero-short analysis.

Emotion recognition from physiological signals has substantial potential for applications in mental health and emotion-aware systems.

Emotion recognition based on physiological signals plays a vital role in psychological health and human-computer interaction, particularly with the substantial advances in multimodal emotion recognition techniques. However, two key challenges remain unresolved: 1) how to effectively model the intra-modal long-range dependencies and inter-modal correlations in multimodal physiological emotion signals, and 2) how to address the performance limitations resulting from missing multimodal data. In this paper, we propose a multimodal bidirectional Mamba (BiMamba) network with test-time adaptation (TTA) for emotion recognition named BiM-TTA.

Multimodal Sentiment Analysis (MSA) aims to infer human emotions by integrating complementary signals from diverse modalities. However, in real-world scenarios, missing modalities are common due to data corruption, sensor failure, or privacy concerns, which can significantly degrade model performance. To tackle this challenge, we propose Hyper-Modality Enhancement (HME), a novel framework that avoids explicit modality reconstruction by enriching each observed modality with semantically relevant cues retrieved from other samples. This cross-sample enhancement reduces reliance on fully observed data during training, making the method better suited to scenarios with inherently incomplete inputs. In addition, we introduce an uncertainty-aware fusion mechanism that adaptively balances original and enriched representations to improve robustness. Extensive experiments on three public benchmarks show that HME consistently outperforms state-of-the-art methods under various missing modality conditions, demonstrating its practicality in real-world MSA applications.

Understanding affect is central to anticipating human behavior, yet current egocentric vision benchmarks largely ignore the person's emotional states that shape their decisions and actions.

Multimodal Emotion Recognition in Conversations (MERC) enhances emotional understanding through the fusion of multimodal signals.

Electroencephalography (EEG)-based emotion recognition suffers from severe performance degradation when models are transferred across heterogeneous datasets due to physiological variability, experimental paradigm differences, and device inconsistencies. Existing domain adversarial methods primarily enforce global marginal alignment and often overlook class-conditional mismatch and decision boundary distortion, limiting cross-corpus generalization. In this work, we propose a unified Prototype-driven Adversarial Alignment (PAA) framework for cross-corpus EEG emotion recognition. The framework is progressively instantiated in three configurations: PAA-L, which performs prototype-guided local class-conditional alignment; PAA-C, which further incorporates contrastive semantic regularization to enhance intra-class compactness and inter-class separability; and PAA-M, the full boundary-aware configuration that integrates dual relation-aware classifiers within a three-stage adversarial optimization scheme to explicitly refine controversial samples near decision boundaries. By combining prototype-guided subdomain alignment, contrastive discriminative enhancement, and boundary-aware aggregation within a coherent adversarial architecture, the proposed framework reformulates emotion recognition as a relation-driven representation learning problem, reducing sensitivity to label noise and improving cross-domain stability. Extensive experiments on SEED, SEED-IV, and SEED-V demonstrate state-of-the-art performance under four cross-corpus evaluation protocols, with average improvements of 6.72\%, 5.59\%, 6.69\%, and 4.83\%, respectively. Furthermore, the proposed framework generalizes effectively to clinical depression identification scenarios, validating its robustness in real-world heterogeneous settings. The source code is available at \textit{https://github.com/WuCB-BCI/PAA}

Accuracy is a commonly adopted performance metric in various classification tasks, which measures the proportion of correctly classified samples among all samples. It assumes equal importance for all classes, hence equal severity for misclassifications. However, in the task of emotional classification, due to the psychological similarities between emotions, misclassifying a certain emotion into one class may be more severe than another, e.g., misclassifying'excitement' as'anger' apparently is more severe than as'awe'. Albeit high meaningful for many applications, metrics capable of measuring these cases of misclassifications in visual emotion recognition tasks have yet to be explored. In this paper, based on Mikel's emotion wheel from psychology, we propose a novel approach for evaluating the performance in visual emotion recognition, which takes into account the distance on the emotion wheel between different emotions to mimic the psychological nuances of emotions. Experimental results in semi-supervised learning on emotion recognition and user study have shown that our proposed metrics is more effective than the accuracy to assess the performance and conforms to the cognitive laws of human emotions.

Understanding human emotions is fundamental to enhancing human-computer interaction, especially for embodied agents that mimic human behavior. Traditional emotion analysis often takes a third-person perspective, limiting the ability of agents to interact naturally and empathetically. To address this gap, this paper presents $E^3$ for Exploring Embodied Emotion, the first massive first-person view video dataset.