Xiong Pan

Xiong Pan

Auto-generated profile, based on publicly available information

Xiong Pan

School of Artificial Intelligence, Xidian University, Xian, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 October 2024 in Neurocomputing
Verified
Journal Article
Closed access
XPXiong Pan
Xiong Pan
Xuemei XieXuemei Xie
Xuemei Xie
JYJianxiu Yang
Jianxiu Yang

20 October 2025 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
XPXiong Pan
Xiong Pan
Xuemei XieXuemei Xie
Xuemei Xie
Jianxiu YangJianxiu Yang
Jianxiu Yang
XSXiaodan Song
Xiaodan Song
GSGuangming Shi
Guangming Shi
Referring Image Segmentation (RIS) aims to generate specified target masks in the image using natural language. While existing methods have made progress in modeling the relationship between words and pixels, they often overlook sentence-level semantic information. This limits the model's ability to fully comprehend the deeper meaning of language, affecting target localization and segmentation. To address this problem, we propose a Context-aware Mutual Attention Network (CMANet), which integrates both word-level and sentence-level semantic information to guide visual features in generating precise object masks. Specifically, during the feature encoding stage, we design a Shallow Mutual Attention (SMA) module to reduce the discrepancy between visual and linguistic representations, enhancing pixel-word alignment. In the global representation stage, we introduce a Context-aware Mutual Attention (CMA) module that utilizes sentence-level target semantics to guide the contextual representation of multi-modal features. Experiments conducted on several commonly used RIS datasets, including the natural image referring segmentation dataset, Robust RIS dataset, and referring remote sensing image dataset, show that CMANet outperforms current state-of-the-art methods on all these datasets, demonstrating superior segmentation accuracy.

3 October 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
QXQi-Hang Xia
Qi-Hang Xia
YHYun He
Yun He
MMMengsen Ma
Mengsen Ma
XPXiong Pan
Xiong Pan
We investigate the thermodynamic properties and Joule-Thomson (JT) expansion of AdS black holes surrounded by quintessence in both unconstrained and constrained thermodynamic phase spaces. Starting from a singular black-hole solution supported by nonlinear electrodynamics and quintessence, a supplementary constraint is imposed to construct a constrained black hole system corresponding to a Bardeen-AdS black hole immersed in quintessence. We analyze the thermodynamic quantities, critical behavior, heat capacity, and Gibbs free energy in both frameworks. The unconstrained black hole exhibits rich phase structures, including first-order and reentrant phase transitions. In contrast, the constrained system displays significantly modified thermodynamic behavior due to the reduction of the thermodynamic phase space. We further study the JT expansion and derive the corresponding inversion curves and JT coefficients. The unconstrained black hole possesses multi-branch inversion curves and multiple divergence structures, whereas the constrained black hole exhibits only a single minimum in the inversion curve and a single divergence point in the Joule–Thomson coefficient. Our results demonstrate that supplementary constraints can substantially alter black hole thermodynamics even when spacetime singularities persist, thereby providing evidence that many thermodynamic features originate from phase-space reduction rather than spacetime regularization.

10 March 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
XPXiong Pan
Xiong Pan
Xuemei XieXuemei Xie
Xuemei Xie
QPQingzhe Pan
Qingzhe Pan
XSXiaodan Song
Xiaodan Song
JYJianxiu Yang
Jianxiu Yang
CYChangcai Yang
Changcai Yang
Referring expression segmentation (RES) aims to generate precise masks in images based on natural language descriptions. Existing approaches typically integrate text prompt into the segment anything model (SAM) via multi-modal encoder. However, these methods overlook a critical aspect: SAM’s inherently strength in processing visual prompt. To address this limitation, we propose a vision-language prompting framework that extends SAM to RES through a coarse-to-fine decoding strategy. Specifically, we first leverage existing multi-modal encoders to establish semantic consistency between visual and linguistic representations. Subsequently, a spatial–semantic interaction module generates a coarse target estimation that approximately localizes the referred regions. The resulting multi-modal spatial relations are then converted into visual prompts, enabling SAM to function as a vision-refined mask generator guided by visual information. In this framework, visual prompts provide the main guidance, while semantic prompts offer complementary support for fine-grained mask refinement. Extensive experiments demonstrate that our framework achieves performance on par with or surpassing state-of-the-art methods.

18 October 2026 in Pattern Recognition
Verified
Journal Article
Closed access
XPXiong Pan
Xiong Pan
XXXuemei Xie
Xuemei Xie
QPQingzhe Pan
Qingzhe Pan
XSXiaodan Song
Xiaodan Song
JYJianxiu Yang
Jianxiu Yang
CYChangcai Yang
Changcai Yang

14 July 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
YZYiPeng Zhang
YiPeng Zhang
XPXiong Pan
Xiong Pan
HCHao Chen
Hao Chen
LWLifang Wei
Lifang Wei
CYChangcai Yang
Changcai Yang
RCRiqing Chen
Riqing Chen
Correspondence pruning aims to identify inliers from an initial set of putative correspondences. Most existing methods establish putative correspondences via appearance-based matching and perform context aggregation directly on these pairs. While this effectively models cross-view dependencies, processing pairs as integral units overlooks the intra-view geometric structures formed by per-view keypoints. Consequently, such methods fail to leverage cross-view structural consistency, missing a critical geometric prior for separating inliers from outliers. To address this limitation, we propose the Hierarchical Geometric Consistency Network (HGCNet), which introduces a Hierarchical Geometric Relation (HGR) branch that directly leverages per-view keypoints to explicitly model intra-view geometric structures. Unlike existing methods that reason solely at the correspondence level, the HGR branch further exploits cross-view structural consistency as a complementary cue for verification, suppressing structurally inconsistent correspondence. Moreover, we introduce a Discrepancy-aware Enhancement (DaE) module and a Multi-Stage Attention Fusion (MSAF) module to preserve discriminative representations and effectively exploit hierarchical features across pruning stages. Extensive experiments on multiple benchmark datasets demonstrate that the proposed method achieves state-of-the-art performance in two-view correspondence pruning. The code is available at https://github.com/ruifen98/HGCNet.