Publications

LiDSeg adds a lightweight guidance encoder to semantic segmentation models for adverse weather. Auxiliary image reconstruction supports training; at inference, the reconstruction decoder is removed while the guidance encoder and gated fusion remain. The framework supports multiple segmentation backbones and evaluation across fog, rain, snow, and night conditions.

A mobility-aware approach to joint service placement and task offloading in mobile edge computing. This work studies how service decisions can account for changing mobility patterns.

Research on online variational Gaussian processes for time-series data, extending probabilistic modeling to observations that arrive over time.

A shared deep learning framework for image classification, object detection, and image captioning. The work explores multitask representations and transfer learning across visual and language tasks.

An attention-based hybrid ensemble approach to breast-cancer image classification. Listed in my ORCID research record.

Application of YOLOX to face-mask detection, exploring efficient object detection in a public-health setting.

Sparse Gaussian process regression for inference and prediction on large datasets. The project investigates pseudo-inputs and kernel combinations, with experiments on weather data.

A continuous wavelet and capsule-network approach to biometric identification from electrocardiogram signals.

Research combining super-resolution convolutional processing and capsule networks for COVID-19 identification in low-quality chest X-ray images.