Jianxiang Zhu

Jianxiang Zhu

Auto-generated profile, based on publicly available information

Jianxiang Zhu

School of Future Technology, Shanghai University, Shanghai, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
27 November 2023 in Expert Systems with Applications
Verified
Journal Article
Closed access
JYJie Yang
Jie Yang
JZJianxiang Zhu
Jianxiang Zhu
XDXiaofeng Ding
Xiaofeng Ding
YPYaxin Peng
Yaxin Peng
YZYangchun Zhang
Yangchun Zhang

24 June 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
JZJianxiang Zhu
Jianxiang Zhu
KYKeni Yang
Keni Yang
YZYangchun Zhang
Yangchun Zhang
YPYan Peng
Yan Peng
YPYaxin Peng
Yaxin Peng
Place recognition holds a pivotal influence in the field of computer vision. Feature pyramid, an advanced architecture introduced into place recognition, aims to produce features with richer semantic content. However, existing methods ignore the efficient utilization of low-level features. To tackle this issue, we propose a novel place recognition architecture called the Adaptive Perspective-based Fusion Network (APFN). The main benefits of APFN lie in three aspects: (1) it adaptively optimizes the appropriate perspective and assigns the appropriate perspective-based weights dynamically for the multi-scale low-level feature maps by a newly designed Adaptive Perspective-based Attention (APA) module; (2) it effectively enhances the extracted low-level features and significantly shortens the transmission distance of low-level information; (3) it enhances global information extraction via supervising the generation of high-level features by regularization. Extensive experiments on several public datasets validate the effectiveness of our method. APFN outperforms previous baseline methods by 1.6 percentage points in average recall at top 1% (AR@1%) and 1.2 percentage points in average recall at top 1 (AR@1) metrics.

10 April 2026 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
KXkewen xia
kewen xia
XYXiaodong Yue
Xiaodong Yue
WLWei Liu
Wei Liu
ZWZhipeng Wei
Zhipeng Wei
JZJianxiang Zhu
Jianxiang Zhu
YPYaxin Peng
Yaxin Peng
Open World Object Detection (OWOD) faces a fundamental dilemma: maintaining a stable representation for known classes while reserving flexible space for discovering unknown objects. Existing methods, while improving recall, often fail to assign discriminative confidence scores to unknown instances, resulting in critically low Average Precision (U-AP) and representation degradation during incremental learning. To remedy this, we propose the Evidential Prior Guided Neural Collapse (ENC) framework. ENC unifies representation learning and uncertainty quantification via a Geometric-Evidence Coupling mechanism. Unlike previous approaches, we map evidential support directly to the angular alignment with Simplex Equiangular Tight Frame (ETF) prototypes. Theoretically, the evidential prior functions as a geometric regularizer: it maximizes equiangular separation for confident known samples, while constraining ambiguous queries to approximate an isotropic uniform distribution via distributional regularization. Furthermore, to mitigate decision conflicts in self-supervised learning, we propose a dissonance-aware objectness optimization strategy that mines informative samples near the decision boundary. Extensive experiments on M-OWODB and S-OWODB benchmarks demonstrate that ENC sets a new state-of-the-art. Notably, it achieves a significant improvement in unknown class discovery, boosting U-AP from ≈ 1% to 9.2%, while exhibiting superior robustness against catastrophic forgetting in challenging incremental scenarios.