Selected work

Representative Papers

Feature Aggregation for Efficient Continual Learning of Complex Facial Expressions

Dec 13, 2025

To address catastrophic forgetting in continual learning for facial expression recognition (FER), this paper proposes a progressive continual learning framework tailored for multicultural dynamic affective interaction. Methodologically, it introduces the first dual-modality representation integrating deep convolutional features with Facial Action Coding System (FACS) action units (AUs), and designs a lightweight Bayesian Gaussian Mixture Model (BGMM) enabling online probabilistic inference without retraining. Experiments on the CFEE dataset demonstrate significant improvements: composite expression recognition accuracy increases notably, knowledge retention improves by 23.6%, and forgetting rate decreases by 41.2%. This work is the first to incorporate AU priors into continual FER modeling, yielding an efficient, scalable, and low-forgetting affective intelligence system. It advances cross-cultural, fine-grained affective understanding with strong practical implications.

0 citationsRead paper

Toward an Intent-Based and Ontology-Driven Autonomic Security Response in Security Orchestration Automation and Response

Jul 16, 2025

Current SOAR platforms struggle to rapidly adapt to dynamic cyberattacks due to the absence of intent-driven, ontology-supported autonomous response mechanisms. To address this, we propose an ontology-driven security intent modeling and autonomous response integration method. Leveraging the MITRE-D3FEND ontology, we establish a unified security intent definition framework and a two-tier autonomous architecture—comprising an intent parsing layer and a decision-execution layer—to ensure semantically consistent mapping from high-level security intents to executable response actions. Our approach integrates intent-driven networking, hierarchical autonomous control, and decision-theoretic modeling to enable context-aware, multi-level response orchestration. Experimental evaluation demonstrates the feasibility of the proposed mechanism within next-generation SOAR platforms, significantly improving threat handling adaptability, semantic consistency across intent and action, and sustained autonomous response capability.

0 citationsRead paper

Recent publications

Latest Papers

Feature Aggregation for Efficient Continual Learning of Complex Facial Expressions

Dec 13, 2025

To address catastrophic forgetting in continual learning for facial expression recognition (FER), this paper proposes a progressive continual learning framework tailored for multicultural dynamic affective interaction. Methodologically, it introduces the first dual-modality representation integrating deep convolutional features with Facial Action Coding System (FACS) action units (AUs), and designs a lightweight Bayesian Gaussian Mixture Model (BGMM) enabling online probabilistic inference without retraining. Experiments on the CFEE dataset demonstrate significant improvements: composite expression recognition accuracy increases notably, knowledge retention improves by 23.6%, and forgetting rate decreases by 41.2%. This work is the first to incorporate AU priors into continual FER modeling, yielding an efficient, scalable, and low-forgetting affective intelligence system. It advances cross-cultural, fine-grained affective understanding with strong practical implications.

0 citationsRead paper

Toward an Intent-Based and Ontology-Driven Autonomic Security Response in Security Orchestration Automation and Response

Jul 16, 2025

Current SOAR platforms struggle to rapidly adapt to dynamic cyberattacks due to the absence of intent-driven, ontology-supported autonomous response mechanisms. To address this, we propose an ontology-driven security intent modeling and autonomous response integration method. Leveraging the MITRE-D3FEND ontology, we establish a unified security intent definition framework and a two-tier autonomous architecture—comprising an intent parsing layer and a decision-execution layer—to ensure semantically consistent mapping from high-level security intents to executable response actions. Our approach integrates intent-driven networking, hierarchical autonomous control, and decision-theoretic modeling to enable context-aware, multi-level response orchestration. Experimental evaluation demonstrates the feasibility of the proposed mechanism within next-generation SOAR platforms, significantly improving threat handling adaptability, semantic consistency across intent and action, and sustained autonomous response capability.

0 citationsRead paper