Institution profile

Technological Educational Institute of Crete

Academic institutioneurope · gr
Official website
Research library21linked papers
Opportunities0open roles
Selected work

Representative Papers

1BT: One-Block Transformer for EEG-Based Cognitive Workload Assessment

Apr 21, 2026

This work addresses the challenge of achieving both high accuracy and computational efficiency in cognitive workload assessment under resource-constrained conditions. The authors propose an extremely lightweight single-block Transformer architecture (1BT), which, for the first time, applies a single Transformer block to multi-channel EEG time-series modeling. By incorporating a latent bottleneck to compress input signals and integrating lightweight self-attention and cross-attention mechanisms, the model enables efficient discriminative learning. Requiring only 0.5 million parameters and 0.02 GFLOPs, the proposed method attains competitive cognitive workload classification performance while drastically reducing model size and computational overhead, making it well-suited for real-time, low-power deployment scenarios.

2 citationsRead paper
Recent publications

Latest Papers

FUSE: Frame-Unified Stress Estimation from Facial Video

Aug 10, 2026

This work addresses the limitations of existing video-based stress detection methods that rely on temporal windowing, which introduces additional hyperparameters and complicates unified modeling of full-length videos. To overcome this, the authors propose FUSE, a novel end-to-end framework that eliminates the need for temporal segmentation by collapsing the time dimension into the channel dimension, thereby encoding an entire video sequence into a single two-dimensional representation. Coupled with an asymmetric attention architecture, FUSE directly predicts stress states from either dense (all frames, t=1) or sparse (every 15th frame, t=15) inputs. Evaluated on a dataset of 58 participants, the method achieves accuracies of 69.03% and 69.44%, respectively, demonstrating a favorable trade-off between effectiveness and computational efficiency without requiring window-based processing.

0 citationsRead paper