arXiv subjects

Jiayuan Tian

Publications and source records attributed to Jiayuan Tian.

6 recordsLinked to original sources

arXiv2026

PhaseAware: Interpretable Human-in-the-Loop Rehabilitation Scoring with Boundary Monitoring

Rehabilitation scoring systems are most useful when their outputs can be reviewed and interpreted within clinical workflows. This study presents PhaseAware, a compact framework for continuous rehabilitation quality assessment that combines a temporal backbone with phase- and body-group descriptors through a backbone-conditioned gated residual pathway. The model was evaluated on the UI-PRMD deep-squat protocol and further tested on the KIMORE squatting subset. On UI-PRMD, PhaseAware achieved an RMSE of 0.0230, corresponding to an 88.9% reduction relative to the accepted baseline. It also maintained favorable performance on KIMORE, suggesting that the phase-aware design transfers across related squatting protocols. In addition to score prediction, PhaseAware generates structured review cues based on phase- and body-level sensitivity, highlighting the movement stages and body regions most relevant to each prediction. The architecture employs a backbone-conditioned gated residual mechanism to stabilize feature representation, supporting use in resource-constrained settings. These cues are intended to support clinician review, boundary-case monitoring, and human-in-the-loop triage rather than autonomous decision-making. Overall, PhaseAware offers a practical and interpretable approach to rehabilitation scoring that may help integrate automated assessment into information systems while preserving clinician oversight.

cs.LG↗

arXiv2024

Spin Polarized Quasi-particle in Off-equilibrium Medium

It is usually believed that physics in off-equilibrium state characterized by hydrodynamic gradient can be equivalently studied using equilibrium state with suitable metric perturbation. We scrutinize this assumption using chiral kinetic theory in curved space, focusing on spin response to hydrodynamic gradient. Two effects of metric perturbation have been identified: one is to change particle motion by scattering it off the metric fields, which does capture spin response to hydrodynamic gradient, but is limited by kinematic condition in the scattering picture. The other is the genuine effect of off-equilibrium state, which is realizable by mapping the equilibrium state in curved space to flat space through a suitable frame choice. It lifts the kinematic condition in the spin response to hydrodynamic gradient. We classify off-equilibrium effect on spin polarization into modifications of (i) spectral function; (ii) distribution function; (iii) KMS relation. While the last two have been studied using chiral kinetic theory, the first one is usually ignored in kinetic description. We perform a detailed analysis on the first one, finding the radiative correction to spectral function leads to a polarized quasi-particle. The degeneracy of spin responses to different hydrodynamic sources at tree-level is also lifted by radiative correction.

hep-ph↗

arXiv2024

SeaDATE: Remedy Dual-Attention Transformer with Semantic Alignment via Contrast Learning for Multimodal Object Detection

Multimodal object detection leverages diverse modal information to enhance the accuracy and robustness of detectors. By learning long-term dependencies, Transformer can effectively integrate multimodal features in the feature extraction stage, which greatly improves the performance of multimodal object detection. However, current methods merely stack Transformer-guided fusion techniques without exploring their capability to extract features at various depth layers of network, thus limiting the improvements in detection performance. In this paper, we introduce an accurate and efficient object detection method named SeaDATE. Initially, we propose a novel dual attention Feature Fusion (DTF) module that, under Transformer's guidance, integrates local and global information through a dual attention mechanism, strengthening the fusion of modal features from orthogonal perspectives using spatial and channel tokens. Meanwhile, our theoretical analysis and empirical validation demonstrate that the Transformer-guided fusion method, treating images as sequences of pixels for fusion, performs better on shallow features' detail information compared to deep semantic information. To address this, we designed a contrastive learning (CL) module aimed at learning features of multimodal samples, remedying the shortcomings of Transformer-guided fusion in extracting deep semantic features, and effectively utilizing cross-modal information. Extensive experiments and ablation studies on the FLIR, LLVIP, and M3FD datasets have proven our method to be effective, achieving state-of-the-art detection performance.

cs.CV↗

arXiv2024

In-medium Electromagnetic Form Factors and Spin Polarizations

We formulate the coupling between fermion spin and background electromagnetic fields using form factors. We show that the vacuum form factors at tree level reproduce the spin polarization effects found in chiral kinetic theory. The vacuum form factors corresponding to spin couplings to perpendicular electric field, parallel and perpendicular magnetic field are degenerate. The degeneracy is expected to be lifted in medium. As an example, we calculate the in-medium QCD radiative correction to the form factors at one-loop order, where we find partial lift of the degeneracy: the spin couplings to parallel and perpendicular magnetic field are different, but the spin couplings to perpendicular electric and parallel magnetic field remain the same.

hep-ph↗

arXiv2024

SwiMDiff: Scene-wide Matching Contrastive Learning with Diffusion Constraint for Remote Sensing Image

With recent advancements in aerospace technology, the volume of unlabeled remote sensing image (RSI) data has increased dramatically. Effectively leveraging this data through self-supervised learning (SSL) is vital in the field of remote sensing. However, current methodologies, particularly contrastive learning (CL), a leading SSL method, encounter specific challenges in this domain. Firstly, CL often mistakenly identifies geographically adjacent samples with similar semantic content as negative pairs, leading to confusion during model training. Secondly, as an instance-level discriminative task, it tends to neglect the essential fine-grained features and complex details inherent in unstructured RSIs. To overcome these obstacles, we introduce SwiMDiff, a novel self-supervised pre-training framework designed for RSIs. SwiMDiff employs a scene-wide matching approach that effectively recalibrates labels to recognize data from the same scene as false negatives. This adjustment makes CL more applicable to the nuances of remote sensing. Additionally, SwiMDiff seamlessly integrates CL with a diffusion model. Through the implementation of pixel-level diffusion constraints, we enhance the encoder's ability to capture both the global semantic information and the fine-grained features of the images more comprehensively. Our proposed framework significantly enriches the information available for downstream tasks in remote sensing. Demonstrating exceptional performance in change detection and land-cover classification tasks, SwiMDiff proves its substantial utility and value in the field of remote sensing.

cs.CV↗

arXiv2023

Medium Correction to Gravitational Form Factors

We generalize the gravitational form factor for chiral fermion in vacuum, which reproduces the well-known spin-vorticity coupling. We also calculate radiative correction to the gravitational form factors in quantum electrodynamics plasma. We find two structures in the form factors contributing to the scattering amplitude of fermion in vorticity field, one is from the fermion self-energy correction, pointing to suppression of spin-vorticity coupling in medium; the other structure comes from graviton-fermion vertex correction, which does not adopt potential interpretation, but corresponds to transition matrix element between initial and final states. Both structures contribute to axial chiral vortical effect. The net effect is that radiative correction enhances the axial chiral vortical effect. Our results clarify the relation and difference between spin-vorticity coupling and axial chiral vortical effect from the perspective of form factors. We also discuss the application of the results in quantum chromodynamic plasma, indicating radiative correction might have an appreciable effect in spin polarization effect in heavy ion collisions.

hep-ph↗