Selected work

Representative Papers

eBIRD: Event-based Intensity Image Reconstruction Using Controllable Diffusion Models

Aug 09, 2026

Reconstructing intensity images from event streams is highly challenging due to the binary, sparse, and asynchronous nature of event data. This work proposes eBIRD, a novel framework that, for the first time, applies a ControlNet-guided denoising diffusion probabilistic model (DDPM) to event-based image reconstruction, leveraging a 33-ms event window for conditional generation. The study systematically evaluates the adaptability of general-purpose versus specialized diffusion learning strategies across domains and achieves state-of-the-art reconstruction performance on both N-MNIST (MSE: 0.0052, SSIM: 0.8982, PSNR: 23.34 dB) and RGBE-Gaze (MSE: 0.0161, SSIM: 0.7605, PSNR: 19.08 dB) benchmarks.

0 citationsRead paper

Literary Emotions in Motion: A Soft Robotics Installation for Tactile Storytelling

May 29, 2026

This work explores the translation of affective content from literary texts into tangible haptic experiences to enhance emotional resonance in artistic installations. We present an interactive soft robotic system that leverages a natural language model to identify primary and secondary emotions in textual input, actuating seven hexagonal pneumatic soft actuators—central for primary emotion and peripheral for secondary emotion—while integrating LED color and actuator stiffness modulation for multisensory affective expression. The study introduces a novel paradigm mapping textual emotional semantics to stiffness control of soft modules and develops low-cost, easily fabricable thin-film silicone actuators with a broad stiffness tuning range. User studies demonstrate that coupling stiffness variation with color significantly enhances emotional perception, underscoring the system’s potential in affective human–robot interaction and immersive narrative environments.

0 citationsRead paper

evTransFER: A Transfer Learning Framework for Event-based Facial Expression Recognition

Aug 05, 2025

To address low accuracy and challenging temporal modeling in event-camera-based facial expression recognition (FER), this paper proposes evTransFER. First, it leverages a face reconstruction pre-trained GAN encoder for cross-task transfer learning. Second, it introduces Temporal-Intensity Encoding (TIE), a novel event representation that explicitly encodes both temporal and intensity information from event streams. Third, it designs the TIE-LSTM architecture to efficiently model long-range spatiotemporal dynamics. Evaluated on the e-CK+ dataset, evTransFER achieves 93.6% accuracy—outperforming the state-of-the-art by 25.9 percentage points. Key contributions are: (i) the first application of reconstruction-pretrained encoders for transfer learning in event-based FER; (ii) the TIE representation, uniquely balancing high temporal resolution with intensity-aware encoding; and (iii) a new paradigm for high-accuracy, computationally efficient FER in the event-domain.

0 citationsRead paper

Recent publications

Latest Papers

eBIRD: Event-based Intensity Image Reconstruction Using Controllable Diffusion Models

Aug 09, 2026

Reconstructing intensity images from event streams is highly challenging due to the binary, sparse, and asynchronous nature of event data. This work proposes eBIRD, a novel framework that, for the first time, applies a ControlNet-guided denoising diffusion probabilistic model (DDPM) to event-based image reconstruction, leveraging a 33-ms event window for conditional generation. The study systematically evaluates the adaptability of general-purpose versus specialized diffusion learning strategies across domains and achieves state-of-the-art reconstruction performance on both N-MNIST (MSE: 0.0052, SSIM: 0.8982, PSNR: 23.34 dB) and RGBE-Gaze (MSE: 0.0161, SSIM: 0.7605, PSNR: 19.08 dB) benchmarks.

0 citationsRead paper

Literary Emotions in Motion: A Soft Robotics Installation for Tactile Storytelling

May 29, 2026

This work explores the translation of affective content from literary texts into tangible haptic experiences to enhance emotional resonance in artistic installations. We present an interactive soft robotic system that leverages a natural language model to identify primary and secondary emotions in textual input, actuating seven hexagonal pneumatic soft actuators—central for primary emotion and peripheral for secondary emotion—while integrating LED color and actuator stiffness modulation for multisensory affective expression. The study introduces a novel paradigm mapping textual emotional semantics to stiffness control of soft modules and develops low-cost, easily fabricable thin-film silicone actuators with a broad stiffness tuning range. User studies demonstrate that coupling stiffness variation with color significantly enhances emotional perception, underscoring the system’s potential in affective human–robot interaction and immersive narrative environments.

0 citationsRead paper

evTransFER: A Transfer Learning Framework for Event-based Facial Expression Recognition

Aug 05, 2025

To address low accuracy and challenging temporal modeling in event-camera-based facial expression recognition (FER), this paper proposes evTransFER. First, it leverages a face reconstruction pre-trained GAN encoder for cross-task transfer learning. Second, it introduces Temporal-Intensity Encoding (TIE), a novel event representation that explicitly encodes both temporal and intensity information from event streams. Third, it designs the TIE-LSTM architecture to efficiently model long-range spatiotemporal dynamics. Evaluated on the e-CK+ dataset, evTransFER achieves 93.6% accuracy—outperforming the state-of-the-art by 25.9 percentage points. Key contributions are: (i) the first application of reconstruction-pretrained encoders for transfer learning in event-based FER; (ii) the TIE representation, uniquely balancing high temporal resolution with intensity-aware encoding; and (iii) a new paradigm for high-accuracy, computationally efficient FER in the event-domain.

0 citationsRead paper