Selected work

Representative Papers

The causal relation between off-street parking and electric vehicle adoption in Scotland

Apr 10, 2026

This study investigates whether the association between off-street parking availability and electric vehicle (EV) adoption among Scottish households stems from infrastructural constraints or merely reflects underlying socioeconomic disparities. Leveraging nationally representative household survey data and employing a probabilistic causal inference framework to control for confounding factors, the analysis addresses selection bias inherent in conventional observational models. Findings indicate that off-street parking significantly accelerates EV adoption only among high-income households, increasing adoption probability from 3.3% to 5.6%—a relative increase of 70%. However, income itself constitutes the primary barrier to market entry, accounting for a 23.1 percentage-point gap in participation. These results suggest that infrastructure-focused policies, if implemented without addressing income constraints, risk exacerbating inequalities in EV adoption.

0 citationsRead paper

A Survey on Sensor-based Planning and Control for Unmanned Underwater Vehicles

Apr 05, 2026

This study addresses the navigation and control challenges faced by unmanned underwater vehicles (UUVs) in complex underwater environments characterized by GNSS denial, sensor noise, and limited communication. It provides a systematic review and classification of local reactive planning and control methods that leverage real-time sensing data from sonar, inertial measurement units (IMUs), and other onboard sensors. The work innovatively proposes an architectural taxonomy that distinguishes between decoupled and coupled planning–control paradigms, emphasizing adaptive local replanning mechanisms. By integrating strategies such as PID control, model predictive control (MPC), and invariant-set-based control, the paper offers a thorough analysis of the trade-offs among path optimality, computational cost, safety, and maneuverability, thereby establishing a theoretical foundation and practical design guidance for enhancing UUV autonomy.

0 citationsRead paper

GRAD-Former: Gated Robust Attention-based Differential Transformer for Change Detection

Mar 01, 2026

This work addresses the challenges in high-resolution remote sensing change detection, where existing methods struggle to accurately delineate changed regions and conventional Transformers suffer from high computational complexity and low data efficiency. To overcome these limitations, the authors propose GRAD-Former, a lightweight and efficient framework that integrates an Adaptive Feature Embedding Amplification (SEA) module and a Global-Local Feature Refinement (GLFR) module. By incorporating gated mechanisms and differential attention, GRAD-Former effectively selects salient features while suppressing redundancy, thereby enhancing both global and local contextual awareness. Evaluated on three benchmark datasets—LEVIR-CD, CDD, and DSIFN-CD—the proposed method achieves state-of-the-art performance with fewer parameters, significantly improving detection accuracy and computational efficiency, and establishing a new benchmark for remote sensing change detection.

0 citationsRead paper

Wildlife Target Re-Identification Using Self-supervised Learning in Non-Urban Settings

Jul 03, 2025

To address the scarcity of labeled data for wildlife re-identification in non-urban environments, this paper proposes a temporal self-supervised learning framework tailored for camera-trap videos. The method leverages unlabeled consecutive video frames to model temporal consistency of individual appearance and employs contrastive learning to extract robust, view-invariant feature representations. Its key contribution is the first systematic integration of temporal self-supervision into open-world wildlife re-identification—enabling discriminative individual representation learning without manual annotations. Experiments demonstrate that the approach significantly outperforms supervised baselines across multiple species (e.g., leopard cats, wild boars), particularly excelling in few-shot and cross-domain generalization. Moreover, the learned features achieve state-of-the-art performance on downstream tasks including image retrieval, unsupervised clustering, and few-shot fine-tuning.

0 citationsRead paper

Recent publications

Latest Papers

The causal relation between off-street parking and electric vehicle adoption in Scotland

Apr 10, 2026

This study investigates whether the association between off-street parking availability and electric vehicle (EV) adoption among Scottish households stems from infrastructural constraints or merely reflects underlying socioeconomic disparities. Leveraging nationally representative household survey data and employing a probabilistic causal inference framework to control for confounding factors, the analysis addresses selection bias inherent in conventional observational models. Findings indicate that off-street parking significantly accelerates EV adoption only among high-income households, increasing adoption probability from 3.3% to 5.6%—a relative increase of 70%. However, income itself constitutes the primary barrier to market entry, accounting for a 23.1 percentage-point gap in participation. These results suggest that infrastructure-focused policies, if implemented without addressing income constraints, risk exacerbating inequalities in EV adoption.

0 citationsRead paper

A Survey on Sensor-based Planning and Control for Unmanned Underwater Vehicles

Apr 05, 2026

This study addresses the navigation and control challenges faced by unmanned underwater vehicles (UUVs) in complex underwater environments characterized by GNSS denial, sensor noise, and limited communication. It provides a systematic review and classification of local reactive planning and control methods that leverage real-time sensing data from sonar, inertial measurement units (IMUs), and other onboard sensors. The work innovatively proposes an architectural taxonomy that distinguishes between decoupled and coupled planning–control paradigms, emphasizing adaptive local replanning mechanisms. By integrating strategies such as PID control, model predictive control (MPC), and invariant-set-based control, the paper offers a thorough analysis of the trade-offs among path optimality, computational cost, safety, and maneuverability, thereby establishing a theoretical foundation and practical design guidance for enhancing UUV autonomy.

0 citationsRead paper

GRAD-Former: Gated Robust Attention-based Differential Transformer for Change Detection

Mar 01, 2026

This work addresses the challenges in high-resolution remote sensing change detection, where existing methods struggle to accurately delineate changed regions and conventional Transformers suffer from high computational complexity and low data efficiency. To overcome these limitations, the authors propose GRAD-Former, a lightweight and efficient framework that integrates an Adaptive Feature Embedding Amplification (SEA) module and a Global-Local Feature Refinement (GLFR) module. By incorporating gated mechanisms and differential attention, GRAD-Former effectively selects salient features while suppressing redundancy, thereby enhancing both global and local contextual awareness. Evaluated on three benchmark datasets—LEVIR-CD, CDD, and DSIFN-CD—the proposed method achieves state-of-the-art performance with fewer parameters, significantly improving detection accuracy and computational efficiency, and establishing a new benchmark for remote sensing change detection.

0 citationsRead paper

Wildlife Target Re-Identification Using Self-supervised Learning in Non-Urban Settings

Jul 03, 2025

To address the scarcity of labeled data for wildlife re-identification in non-urban environments, this paper proposes a temporal self-supervised learning framework tailored for camera-trap videos. The method leverages unlabeled consecutive video frames to model temporal consistency of individual appearance and employs contrastive learning to extract robust, view-invariant feature representations. Its key contribution is the first systematic integration of temporal self-supervision into open-world wildlife re-identification—enabling discriminative individual representation learning without manual annotations. Experiments demonstrate that the approach significantly outperforms supervised baselines across multiple species (e.g., leopard cats, wild boars), particularly excelling in few-shot and cross-domain generalization. Moreover, the learned features achieve state-of-the-art performance on downstream tasks including image retrieval, unsupervised clustering, and few-shot fine-tuning.

0 citationsRead paper