arXiv:2607. 20820v1 Announce Type: new Abstract: Body-based emotion recognition is important for real-time affective systems, but graph-based skeleton models can be computationally expensive.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
The study compares temporal deep learning models—Bidirectional LSTM, Temporal Convolutional Network, and Transformer—for physiological emotion recognition using two multimodal wearable datasets, WESAD and EmoWear. Experiments evaluate wrist-only, chest-only, and multimodal sensor configurations with participant-independent leave-one-subject-out cross-validation, and also explore ensembles, sensor ablation, sampling frequency, and saliency analysis. Results show that the best architecture varies by dataset, multimodal sensing consistently outperforms single-site configurations, and a 4 Hz sampling rate offers a cost-effective operating point.
The paper introduces SV-GCN, a single-stream multi-feature fusion framework for 3D skeleton-based gait emotion recognition that incorporates temporal invariance. It uses intra-frame relative motion features to remove frame-rate sensitivity and embeds heterogeneous cues at shallow layers for early fusion, avoiding multi-stream complexity. A global mask-guided valid-frame spatio-temporal graph convolution module further enhances robustness to variable-length sequences and differing frame rates, achieving state‑of‑the‑art performance on the E‑Gait dataset and strong generalization across sequence lengths.
arXiv:2606. 28769v1 Announce Type: new Abstract: Emotional body motion expressions are an essential element of non-verbal communication.
arXiv:2609.13854v1 Announce Type: new Abstract: Facial emotion recognition (FER) in real-world environments remains challenging due to unconstrained imaging conditions, including multiple faces, occl...
The paper evaluates deep learning models for electrocardiogram‑based emotion recognition, focusing on generalization across datasets rather than dataset‑specific performance. It introduces two open‑source tools—ARRC for standardized benchmarking and ARDT for inter‑dataset training—to merge three public AER datasets (CUADS, ASCERTAIN, DREAMER) into a more variable benchmark. Using these tools, the authors compare three prominent deep learning architectures and two CNN baselines with hyperparameter tuning and 10‑fold cross‑validation, revealing trade‑offs between accuracy and model complexity and providing a reproducible benchmark for future research.
In this paper, we present the solution developed by our team, XInsight Lab, which achieved first place in Track 3 of the 4th EI-MIGA-IJCAI Challenge with a test accuracy of 0. 76923.