Yifan Shi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yifan Shi has a total of 58 co-authors. Here are the top co-authors by number of shared publications:
- Zhiwen Yu
South China University of Technology
12 shared publications - Huanqiang Zeng
Huaqiao University
10 shared publications - Kaixiang Yang
South China University of Technology
10 shared publications - Chun Lung Philip Chen
South China University of Technology
8 shared publications - Jianqing Zhu
College of Engineering, Huaqiao University, Quanzhou, China
7 shared publications - Huijie Zheng
School of Information Science and Engineering, Huaqiao University, Xiamen 361021, China
3 shared publications
Latest Publications
- Open Access
- 17 July 2026
- Published by Institution of Engineering and Technology (IET) in CAAI Transactions on Intelligence Technology
- Vol. 11 (4) , 1215-1230
Align What Truly Matters: Pedestrian‐Relevant Hierarchical Parsing Network for Text‐Based Person Retrieval
Fine‐grained alignment is crucial for text‐based person retrieval, which searches for relevant pedestrian images using a text query. However, background clutter and semantically vacuous words can cause interference and misalignment, hindering retrieval performance. Existing methods employ masked language modelling to randomly mask and predict words, or leverage multimodal large language models to generate diverse and pure samples. However, these methods rely on external tools and are not sufficiently stable or controllable. In this paper, we propose a pedestrian‐relevant hierarchical parsing (PHP) module to extract well‐aligned fine‐grained visual and textual features for alignment. First, we design a coarse relevant feature mapping (CRFM) module, which uses learnable unified tokens to project both modalities into a shared low‐dimensional space, enabling coarse‐level semantic filtering. Next, we design an expert‐driven feature parsing (EFP) module, which integrates the representational power of a mixture of experts with a modality‐aware gating mechanism to uncover deep semantic associations between text and image features. Extensive experiments on three public large‐scale datasets demonstrate that our approach outperforms existing state‐of‐the‐art methods, achieving, in particular, a 5.68% improvement in mAP and a 4.81% boost in R1 accuracy on the CUHK‐PEDES dataset.
- 17 July 2026
- Published by Institution of Engineering and Technology (IET) in CAAI Transactions on Intelligence Technology
- Vol. 11 (4) , 1215-1230
Open AccessAlign What Truly Matters: Pedestrian‐Relevant Hierarchical Parsing Network for Text‐Based Person Retrieval
Fine‐grained alignment is crucial for text‐based person retrieval, which searches for relevant pedestrian images using a text query. However, background clutter and semantically vacuous words can cause interference and misalignment, hindering retrieval performance. Existing methods employ masked language modelling to randomly mask and predict words, or leverage multimodal large language models to generate diverse and pure samples. However, these methods rely on external tools and are not sufficiently stable or controllable. In this paper, we propose a pedestrian‐relevant hierarchical parsing (PHP) module to extract well‐aligned fine‐grained visual and textual features for alignment. First, we design a coarse relevant feature mapping (CRFM) module, which uses learnable unified tokens to project both modalities into a shared low‐dimensional space, enabling coarse‐level semantic filtering. Next, we design an expert‐driven feature parsing (EFP) module, which integrates the representational power of a mixture of experts with a modality‐aware gating mechanism to uncover deep semantic associations between text and image features. Extensive experiments on three public large‐scale datasets demonstrate that our approach outperforms existing state‐of‐the‐art methods, achieving, in particular, a 5.68% improvement in mAP and a 4.81% boost in R1 accuracy on the CUHK‐PEDES dataset.
- 27 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. PP (15249050) , 1-15
Structural Feature Modulation for Day–Night Cross-Domain Object Re-Identification
Day-night cross-domain object re-identification presents significant challenges due to severe illumination-induced domain gaps. Unlike conventional attention mechanisms that suffer from limited dimensional coverage and rely on single-type normalization strategies, we propose a structural feature modulation (SFM) approach that operates from a modulation perspective. Our SFM approach incorporates a gated batch-layer normalization strategy within the modulation architecture, resulting in the construction of a gated normalization-based modulation (GNM) module. This module effectively leverages the complementary advantages of both batch normalization and layer normalization to balance intra-domain discriminability and cross-domain generalization. Furthermore, we develop a multi-granularity modulation (MGM) module that recalibrates features across both edge-granularity and area-granularity pathways, enabling comprehensive structural modulation. Extensive experiments on the DN-348 and LLCM benchmark datasets demonstrate that our SFM approach consistently outperforms state-of-the-art approaches, achieving notable improvements including a 2.51% mAP increase on the DN-348 dataset. Our codes are available at https://github.com/SimiiZ/SFM
- 27 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. PP (15249050) , 1-15
Structural Feature Modulation for Day–Night Cross-Domain Object Re-Identification
Day-night cross-domain object re-identification presents significant challenges due to severe illumination-induced domain gaps. Unlike conventional attention mechanisms that suffer from limited dimensional coverage and rely on single-type normalization strategies, we propose a structural feature modulation (SFM) approach that operates from a modulation perspective. Our SFM approach incorporates a gated batch-layer normalization strategy within the modulation architecture, resulting in the construction of a gated normalization-based modulation (GNM) module. This module effectively leverages the complementary advantages of both batch normalization and layer normalization to balance intra-domain discriminability and cross-domain generalization. Furthermore, we develop a multi-granularity modulation (MGM) module that recalibrates features across both edge-granularity and area-granularity pathways, enabling comprehensive structural modulation. Extensive experiments on the DN-348 and LLCM benchmark datasets demonstrate that our SFM approach consistently outperforms state-of-the-art approaches, achieving notable improvements including a 2.51% mAP increase on the DN-348 dataset. Our codes are available at https://github.com/SimiiZ/SFM
- 21 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (8) , 5047-5061
Enhancing Active Learning for Class Imbalance With an Incrementally Weighted Approach
Active learning can significantly reduce the cost of labeling instances while improving model performance. However, similar to other traditional algorithms, active learning encounters the problem of class imbalance and delivers sub-optimal performance. Additionally, existing approaches suffer from poor performance and are time-consuming. To address these issues, we propose an Actively Incrementally Weighted Broad Learning System (AI-WBLS). Firstly, we introduce an active learning framework based on the weighted broad learning system, which employs a double uncertainty sample selection strategy to enhance the value and reasonableness of sample selection in each iteration of active learning. To further improve the model's adaptability during the iterative learning process, an adaptive weighting strategy is designed to adaptively modify the penalty weights according to the changes in the sample labels. Finally, an efficient incremental paradigm is developed to update the model with newly labelled samples instead of re-training, resulting in improved performance and efficiency. Extensive comparative experiments confirm that our approach outperforms other imbalanced active learning methods.
- 21 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (8) , 5047-5061
Enhancing Active Learning for Class Imbalance With an Incrementally Weighted Approach
Active learning can significantly reduce the cost of labeling instances while improving model performance. However, similar to other traditional algorithms, active learning encounters the problem of class imbalance and delivers sub-optimal performance. Additionally, existing approaches suffer from poor performance and are time-consuming. To address these issues, we propose an Actively Incrementally Weighted Broad Learning System (AI-WBLS). Firstly, we introduce an active learning framework based on the weighted broad learning system, which employs a double uncertainty sample selection strategy to enhance the value and reasonableness of sample selection in each iteration of active learning. To further improve the model's adaptability during the iterative learning process, an adaptive weighting strategy is designed to adaptively modify the penalty weights according to the changes in the sample labels. Finally, an efficient incremental paradigm is developed to update the model with newly labelled samples instead of re-training, resulting in improved performance and efficiency. Extensive comparative experiments confirm that our approach outperforms other imbalanced active learning methods.
- Open Access
- 7 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (10) , 4586
CDD-Guard: A Training-Free Endogenous Defense Framework for LLMs via Contrastive Latent Distribution Analysis
While the integration of large language models (LLMs) drives intelligent automation, their endogenous vulnerability to complex adversarial prompts engenders critical security threats. To address the limitations of existing defenses relying on prohibitive fine-tuning or lagging text matching, this paper proposes Contrastive Distribution Discriminator Guard (CDD-Guard), a training-free endogenous monitoring framework. CDD-Guard pioneers mapping a latent bipolar semantic axis to geometrically separate benign and malicious representations. To mitigate structural noise, it introduces an adaptive layer filtering mechanism driven by statistical effect size, while a cross-layer projection normalization mechanism utilizes Z-Scores to isolate statistical anomalies from thematic variances. Evaluations across heterogeneous LLMs demonstrate superior detection efficacy. Crucially, by directly reusing hidden states generated during a single forward pass, CDD-Guard circumvents the autoregressive generation overhead of external monitors, reducing computational monitoring latency by over 99%. Operating strictly under the constraint of preserving original weights, this framework achieves substantial improvements in attack interception rates and cross-model generalization, providing a lightweight yet robust contribution to LLM security.
- 7 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (10) , 4586
Open AccessCDD-Guard: A Training-Free Endogenous Defense Framework for LLMs via Contrastive Latent Distribution Analysis
While the integration of large language models (LLMs) drives intelligent automation, their endogenous vulnerability to complex adversarial prompts engenders critical security threats. To address the limitations of existing defenses relying on prohibitive fine-tuning or lagging text matching, this paper proposes Contrastive Distribution Discriminator Guard (CDD-Guard), a training-free endogenous monitoring framework. CDD-Guard pioneers mapping a latent bipolar semantic axis to geometrically separate benign and malicious representations. To mitigate structural noise, it introduces an adaptive layer filtering mechanism driven by statistical effect size, while a cross-layer projection normalization mechanism utilizes Z-Scores to isolate statistical anomalies from thematic variances. Evaluations across heterogeneous LLMs demonstrate superior detection efficacy. Crucially, by directly reusing hidden states generated during a single forward pass, CDD-Guard circumvents the autoregressive generation overhead of external monitors, reducing computational monitoring latency by over 99%. Operating strictly under the constraint of preserving original weights, this framework achieves substantial improvements in attack interception rates and cross-model generalization, providing a lightweight yet robust contribution to LLM security.
- Open Access
- 8 April 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (8) , 3640
Adaptive Decision Fusion in Probability Space for Pedestrian Gender Recognition
Pedestrian gender recognition plays an important role in pedestrian analysis and intelligent video applications, for example, in demographic statistics, soft biometric analysis, and context-aware person retrieval. However, it remains a challenging task owing to viewpoint variations, illumination changes, occlusions, and low image quality in real-world imagery. To address these issues, an effective adaptive decision fusion framework, termed the Decision Fusion Learning Network (DFLN), is proposed in this paper. The key novel aspect of DFLN is that it effectively explores both an appearance-centered view that emphasizes detailed texture and clothing information and a structure-centered view that captures rich contour and structural information for pedestrian gender recognition. To realize DFLN, a Parallel CNN Prediction Probability Learning Module (PCNNM) is first constructed to independently learn modality-specific probabilities from color image and edge maps. Subsequently, a learnable Decision Fusion Module (DFM) is designed to fuse the modality-specific probabilities and explore their complementary merits for realizing accurate pedestrian gender recognition. The DFM can be easily coupled with the PCNNM, forming an end-to-end decision fusion learning framework that simultaneously learns the feature representations and carries out adaptive decision fusion. Experiments on two pedestrian benchmark datasets, named PETA and PA-100K, show that DFLN achieves competitive or superior performance compared with several state-of-the-art pedestrian gender recognition methods. Extensive experimental analysis further confirms the effectiveness of the proposed decision fusion strategy and its favorable generalization ability under domain shift.
- 8 April 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (8) , 3640
Open AccessAdaptive Decision Fusion in Probability Space for Pedestrian Gender Recognition
Pedestrian gender recognition plays an important role in pedestrian analysis and intelligent video applications, for example, in demographic statistics, soft biometric analysis, and context-aware person retrieval. However, it remains a challenging task owing to viewpoint variations, illumination changes, occlusions, and low image quality in real-world imagery. To address these issues, an effective adaptive decision fusion framework, termed the Decision Fusion Learning Network (DFLN), is proposed in this paper. The key novel aspect of DFLN is that it effectively explores both an appearance-centered view that emphasizes detailed texture and clothing information and a structure-centered view that captures rich contour and structural information for pedestrian gender recognition. To realize DFLN, a Parallel CNN Prediction Probability Learning Module (PCNNM) is first constructed to independently learn modality-specific probabilities from color image and edge maps. Subsequently, a learnable Decision Fusion Module (DFM) is designed to fuse the modality-specific probabilities and explore their complementary merits for realizing accurate pedestrian gender recognition. The DFM can be easily coupled with the PCNNM, forming an end-to-end decision fusion learning framework that simultaneously learns the feature representations and carries out adaptive decision fusion. Experiments on two pedestrian benchmark datasets, named PETA and PA-100K, show that DFLN achieves competitive or superior performance compared with several state-of-the-art pedestrian gender recognition methods. Extensive experimental analysis further confirms the effectiveness of the proposed decision fusion strategy and its favorable generalization ability under domain shift.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 11782-11797
Fovea-SR: Dual-Fovea Vision Transformer for Lightweight Image Super-Resolution in Industrial Detection Scenarios
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 11782-11797
Fovea-SR: Dual-Fovea Vision Transformer for Lightweight Image Super-Resolution in Industrial Detection Scenarios
- 30 November 2025
- Published by Elsevier in Pattern Recognition
- Vol. 173
Hybrid-stage association with dynamicity adaptation and enhanced cues for multi-object tracking and segmentation
- 30 November 2025
- Published by Elsevier in Pattern Recognition
- Vol. 173
Hybrid-stage association with dynamicity adaptation and enhanced cues for multi-object tracking and segmentation
- 22 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 56 (2) , 867-879
Tensor-Based Semi-Supervised Multiview Subspace Clustering With Pairwise Constraint Propagation
Semi-supervised multiview clustering has garnered considerable attention for its ability to integrate multiview data with limited labeled information. However, existing methods predominantly focus on labeled samples, neglecting abundant unlabeled data, which leads to suboptimal utilization of available prior knowledge. Moreover, existing pairwise constraint propagation-based methods typically follow a two-stage procedure, resulting in unstable clustering outcomes. To address these limitations, we introduce a unified framework that integrates multiview subspace clustering with pairwise constraint propagation, proposing a tensor-based semi-supervised multiview subspace clustering (TSMSC) method with pairwise constraint propagation. Specifically, each view’s subspace representation is decomposed into a consensus part and private parts, enabling the consensus representation to better approximate the low-rank structure. Then, a pairwise constraint propagation method is developed for multiview data, which propagates the initial pairwise constraint through a low-rank matrix completion approach. Finally, observing that the ideal multiview consensus representation and the propagated pairwise constraint matrix share the same low-rank structure, we naturally construct them into a third-order tensor to capture high-order correlations via tensor low-rank representation, allowing for joint optimization within a unified framework. Extensive experiments on eight real-world datasets demonstrate the superiority of our method over state-of-the-art approaches.
- 22 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 56 (2) , 867-879
Tensor-Based Semi-Supervised Multiview Subspace Clustering With Pairwise Constraint Propagation
Semi-supervised multiview clustering has garnered considerable attention for its ability to integrate multiview data with limited labeled information. However, existing methods predominantly focus on labeled samples, neglecting abundant unlabeled data, which leads to suboptimal utilization of available prior knowledge. Moreover, existing pairwise constraint propagation-based methods typically follow a two-stage procedure, resulting in unstable clustering outcomes. To address these limitations, we introduce a unified framework that integrates multiview subspace clustering with pairwise constraint propagation, proposing a tensor-based semi-supervised multiview subspace clustering (TSMSC) method with pairwise constraint propagation. Specifically, each view’s subspace representation is decomposed into a consensus part and private parts, enabling the consensus representation to better approximate the low-rank structure. Then, a pairwise constraint propagation method is developed for multiview data, which propagates the initial pairwise constraint through a low-rank matrix completion approach. Finally, observing that the ideal multiview consensus representation and the propagated pairwise constraint matrix share the same low-rank structure, we naturally construct them into a third-order tensor to capture high-order correlations via tensor low-rank representation, allowing for joint optimization within a unified framework. Extensive experiments on eight real-world datasets demonstrate the superiority of our method over state-of-the-art approaches.
- Open Access
- 21 July 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (14) , 8094
Multi-View Cluster Structure Guided One-Class BLS-Autoencoder for Intrusion Detection
Intrusion detection systems are crucial for cybersecurity applications. Network traffic data originate from diverse terminal sources, exhibiting multi-view feature spaces, while the collection of unknown intrusion data is costly. Current one-class classification (OCC) approaches are mainly designed for single-view data. Multi-view OCC approaches usually require collecting multi-view traffic data from all sources and have difficulty detecting intrusion independently in each view. Furthermore, they commonly ignore the potential subcategories in normal traffic data. To address these limitations, this paper utilizes the Broad Learning System (BLS) technique and proposes an intrusion detection framework based on a multi-view cluster structure guided one-class BLS-autoencoder (IDF-MOCBLSAE). Specifically, a multi-view co-association matrix optimization objective function with doubly-stochastic constraints is first designed to capture the cross-view cluster structure. Then, a multi-view cluster structure guided one-class BLS-autoencoder (MOCBLSAEs) is proposed, which learns the discriminative patterns of normal traffic data by preserving the cross-view clustering structure while minimizing the intra-view sample reconstruction errors, thereby enabling the identification of unknown intrusion data. Finally, an intrusion detection framework is constructed based on multiple MOCBLSAEs to achieve both individual and ensemble intrusion detection. Through experimentation, IDF-MOCBLSAE is validated on real-world network traffic datasets for multi-view one-class classification tasks, demonstrating its superiority over state-of-the-art one-class approaches.
- 21 July 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (14) , 8094
Open AccessMulti-View Cluster Structure Guided One-Class BLS-Autoencoder for Intrusion Detection
Intrusion detection systems are crucial for cybersecurity applications. Network traffic data originate from diverse terminal sources, exhibiting multi-view feature spaces, while the collection of unknown intrusion data is costly. Current one-class classification (OCC) approaches are mainly designed for single-view data. Multi-view OCC approaches usually require collecting multi-view traffic data from all sources and have difficulty detecting intrusion independently in each view. Furthermore, they commonly ignore the potential subcategories in normal traffic data. To address these limitations, this paper utilizes the Broad Learning System (BLS) technique and proposes an intrusion detection framework based on a multi-view cluster structure guided one-class BLS-autoencoder (IDF-MOCBLSAE). Specifically, a multi-view co-association matrix optimization objective function with doubly-stochastic constraints is first designed to capture the cross-view cluster structure. Then, a multi-view cluster structure guided one-class BLS-autoencoder (MOCBLSAEs) is proposed, which learns the discriminative patterns of normal traffic data by preserving the cross-view clustering structure while minimizing the intra-view sample reconstruction errors, thereby enabling the identification of unknown intrusion data. Finally, an intrusion detection framework is constructed based on multiple MOCBLSAEs to achieve both individual and ensemble intrusion detection. Through experimentation, IDF-MOCBLSAE is validated on real-world network traffic datasets for multi-view one-class classification tasks, demonstrating its superiority over state-of-the-art one-class approaches.
- Open Access
- 18 June 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (12) , 6884
Consensus Guided Multi-View Unsupervised Feature Selection with Hybrid Regularization
Multi-source heterogeneous data has been widely adopted in developing artificial intelligence systems in recent years. In real-world scenarios, raw multi-source data are generally unlabeled and inherently contain multi-view noise and feature redundancy, leading to extensive research on unsupervised multi-view feature selection. However, existing approaches mainly utilize the local adjacency relationships and the -norm to guide the feature selection process, which may lead to instability in performance. To address these problems, this paper proposes a Consensus Guided Multi-view Unsupervised Feature Selection with Hybrid Regularization (CGMvFS). Specifically, CGMvFS integrates multiple view-specific basic partitions into a unified consensus matrix, which is constructed to guide the feature selection process by preserving comprehensive pairwise constraints across diverse views. A hybrid regularization strategy incorporating the -norm and the Frobenius norm is introduced into the feature selection objective function, which not only promotes feature sparsity but also effectively prevents overfitting, thereby improving the stability of the model. Extensive empirical evaluations demonstrate that CGMVFS outperforms state-of-the-art comparison approaches across diverse multi-view datasets.- 18 June 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (12) , 6884
Open AccessConsensus Guided Multi-View Unsupervised Feature Selection with Hybrid Regularization
Multi-source heterogeneous data has been widely adopted in developing artificial intelligence systems in recent years. In real-world scenarios, raw multi-source data are generally unlabeled and inherently contain multi-view noise and feature redundancy, leading to extensive research on unsupervised multi-view feature selection. However, existing approaches mainly utilize the local adjacency relationships and the -norm to guide the feature selection process, which may lead to instability in performance. To address these problems, this paper proposes a Consensus Guided Multi-view Unsupervised Feature Selection with Hybrid Regularization (CGMvFS). Specifically, CGMvFS integrates multiple view-specific basic partitions into a unified consensus matrix, which is constructed to guide the feature selection process by preserving comprehensive pairwise constraints across diverse views. A hybrid regularization strategy incorporating the -norm and the Frobenius norm is introduced into the feature selection objective function, which not only promotes feature sparsity but also effectively prevents overfitting, thereby improving the stability of the model. Extensive empirical evaluations demonstrate that CGMVFS outperforms state-of-the-art comparison approaches across diverse multi-view datasets.