Ziqi Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ziqi Li has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Tao Gao
School of Data Science and Artificial Intelligence, Chang’an University, Xi’an, China
16 shared publications - Ting Chen
School of Information Engineering, Changan University, Xian, China
14 shared publications - Yuanbo Wen
School of Information Engineering, Changan University, Xian, China
12 shared publications - Shan Liang
School of Information Engineering, Changan University, Xian, China
5 shared publications - Jing Zhang
Australian National University
4 shared publications - Mengkun Liu
Department of Data Science and Artificial Intelligence, Changan University, Xian, China
4 shared publications
Latest Publications
- Open Access
- 14 September 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1) , 9787
Frequency-oriented adaptive real-time object detector for cluttered traffic scenes
Given the growing demand for traffic object detection in autonomous driving, achieving both efficiency and accuracy on in-vehicle platforms remains challenging. To address this issue, we propose a Frequency-Oriented Adaptive Detector for vehicle-mounted intelligent traffic object detection. It integrates high- and low-frequency information to enhance the texture and semantic representations of multi-scale objects in complex traffic scenarios while maintaining low computational overhead. Specifically, we introduce Frequency Dynamic Convolution to construct a lightweight backbone with frequency-domain adaptive dilated receptive fields and balanced effective bandwidth. The adaptive kernel decomposes convolutional weights into high- and low-frequency components, which are selectively recalibrated to balance frequency responses in feature maps. Moreover, we propose an Adaptive Frequency-Oriented Fusion framework to reorganize high- and low-frequency features across scales. The framework balances object details, fine boundaries, and deep semantic features, thereby reducing feature inconsistencies during multi-scale fusion. Extensive experiments demonstrate that our Frequency-Oriented Adaptive Detector outperforms state-of-the-art detectors. With only 8.77 million parameters, it achieves mAP values of 90.9%, 53.7%, 50.2%, and 53.1% on KITTI, BDD100K, Cityscapes, and Waymo datasets respectively.
- 14 September 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1) , 9787
Open AccessFrequency-oriented adaptive real-time object detector for cluttered traffic scenes
Given the growing demand for traffic object detection in autonomous driving, achieving both efficiency and accuracy on in-vehicle platforms remains challenging. To address this issue, we propose a Frequency-Oriented Adaptive Detector for vehicle-mounted intelligent traffic object detection. It integrates high- and low-frequency information to enhance the texture and semantic representations of multi-scale objects in complex traffic scenarios while maintaining low computational overhead. Specifically, we introduce Frequency Dynamic Convolution to construct a lightweight backbone with frequency-domain adaptive dilated receptive fields and balanced effective bandwidth. The adaptive kernel decomposes convolutional weights into high- and low-frequency components, which are selectively recalibrated to balance frequency responses in feature maps. Moreover, we propose an Adaptive Frequency-Oriented Fusion framework to reorganize high- and low-frequency features across scales. The framework balances object details, fine boundaries, and deep semantic features, thereby reducing feature inconsistencies during multi-scale fusion. Extensive experiments demonstrate that our Frequency-Oriented Adaptive Detector outperforms state-of-the-art detectors. With only 8.77 million parameters, it achieves mAP values of 90.9%, 53.7%, 50.2%, and 53.1% on KITTI, BDD100K, Cityscapes, and Waymo datasets respectively.
- Open Access
- 15 June 2026
- Published by Elsevier in SSRN Electronic Journal
HP-Net: Hierarchical Pooling Interaction Network for RGB-D Salient Object Detection
RGB-D saliency object detection emphasizes the integration of RGB and depth map cues to effectively distinguish between foreground and background regions.Most methods concentrate on crafting various cross-modal fusion modules to seamlessly incorporate multi-modal information into features.However, for many real-life cases where the depth maps have poor quality or contain abundant saliency cues, these methods would yield error-proneresults.In this paper, we propose a Hierarchical Pooling Interaction Network (HP-Net) to effectively exploit complementary information for RGB-D salient object detection.To mitigate the impact of low-quality depth maps and facilitate cross-modal fusion, we design a Hierarchical Pooling Interaction Module (HPIM) to adaptively filter useful information from RGB and depth features and to further optimize multi-scale information.Subsequently, we propose a Cross-modal Mutual Attention (CMMA) unit to obtain high-level semantic information, which could roughly locate the salient object positions and offer initial guidance for the decoding process.Moreover, a Bi-directional Gated Module (BGM) based on GRU is utilized to progressively obtain saliency results from coarse to fine in a gated manner.Experimental results and theoretical analysis reveal that the proposed network outperforms existing methods in enhancing detection capabilities across five benchmark datasets.
- 15 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessHP-Net: Hierarchical Pooling Interaction Network for RGB-D Salient Object Detection
RGB-D saliency object detection emphasizes the integration of RGB and depth map cues to effectively distinguish between foreground and background regions.Most methods concentrate on crafting various cross-modal fusion modules to seamlessly incorporate multi-modal information into features.However, for many real-life cases where the depth maps have poor quality or contain abundant saliency cues, these methods would yield error-proneresults.In this paper, we propose a Hierarchical Pooling Interaction Network (HP-Net) to effectively exploit complementary information for RGB-D salient object detection.To mitigate the impact of low-quality depth maps and facilitate cross-modal fusion, we design a Hierarchical Pooling Interaction Module (HPIM) to adaptively filter useful information from RGB and depth features and to further optimize multi-scale information.Subsequently, we propose a Cross-modal Mutual Attention (CMMA) unit to obtain high-level semantic information, which could roughly locate the salient object positions and offer initial guidance for the decoding process.Moreover, a Bi-directional Gated Module (BGM) based on GRU is utilized to progressively obtain saliency results from coarse to fine in a gated manner.Experimental results and theoretical analysis reveal that the proposed network outperforms existing methods in enhancing detection capabilities across five benchmark datasets.
- 14 April 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 323
A wavelet-guided and physics-aware network for remote sensing image dehazing
- 14 April 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 323
A wavelet-guided and physics-aware network for remote sensing image dehazing
- Top Cited Papers
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. PP (2162237X) , 1-15
When Optimal Transport Meets Photo-Realistic Image Dehazing With Unpaired Training
Image hazing is crucial for enhancing the image visibility and mitigating the weather degradations. However, most existing approaches rely on the paired hazy and clean images, which are challenging to obtain in real-world scenarios. To this end, we propose an oriented Bayesian-regularized consistent optimal transport (OBCOT) framework, which formulates the unpaired image dehazing task as an optimal transport (OT) problem. Specifically, we introduce a structure-preserving transport cost, incorporating the structural similarity (SSIM) constraint to minimize the duality gap between the primal and dual formulations, while preserving the structural details of reconstructed images. Furthermore, we derive the Bayesian frequency-domain regularization (BFR) to balance the spectral consistency with clean References and repulsion from hazy patterns. In addition, we employ a pretrained one-step stable diffusion model as the restoration network, which is fine-tuned using the low-rank adaptation (LoRA) adapters and zero convolutional layers, while integrating the domain-specific text prompts for both degraded and clean images to guide the generation process. Extensive experiments demonstrate that our method surpasses the existing well-performing unpaired learning approaches, achieving notable improvements in both the fidelity and photo-realism.
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. PP (2162237X) , 1-15
Top Cited PapersWhen Optimal Transport Meets Photo-Realistic Image Dehazing With Unpaired Training
Image hazing is crucial for enhancing the image visibility and mitigating the weather degradations. However, most existing approaches rely on the paired hazy and clean images, which are challenging to obtain in real-world scenarios. To this end, we propose an oriented Bayesian-regularized consistent optimal transport (OBCOT) framework, which formulates the unpaired image dehazing task as an optimal transport (OT) problem. Specifically, we introduce a structure-preserving transport cost, incorporating the structural similarity (SSIM) constraint to minimize the duality gap between the primal and dual formulations, while preserving the structural details of reconstructed images. Furthermore, we derive the Bayesian frequency-domain regularization (BFR) to balance the spectral consistency with clean References and repulsion from hazy patterns. In addition, we employ a pretrained one-step stable diffusion model as the restoration network, which is fine-tuned using the low-rank adaptation (LoRA) adapters and zero convolutional layers, while integrating the domain-specific text prompts for both degraded and clean images to guide the generation process. Extensive experiments demonstrate that our method surpasses the existing well-performing unpaired learning approaches, achieving notable improvements in both the fidelity and photo-realism.
- 14 March 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 341
EN-thinking: Enhancing entity-level reasoning in large language models for knowledge graph completion
- 14 March 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 341
EN-thinking: Enhancing entity-level reasoning in large language models for knowledge graph completion
- 10 February 2026
- Published by Elsevier in Pattern Recognition
- Vol. 177
DynStaticNet: A biological vision-inspired dual-branch all-in-one network for video weather removal
- 10 February 2026
- Published by Elsevier in Pattern Recognition
- Vol. 177
DynStaticNet: A biological vision-inspired dual-branch all-in-one network for video weather removal
- 2 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 312
Explicitly learning semantic relevance for salient object detection in remote sensing images
- 2 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 312
Explicitly learning semantic relevance for salient object detection in remote sensing images
- Top Cited Papers
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 3380-3395
Structure-Preserving Frequency-Regularized Text-Guided Optimal Transport for Unpaired Rain Streaks and Raindrops Removal
The removal of rain streaks and raindrops is crucial for enhancing the image visibility and mitigating the weather degradations. However, most existing approaches rely on the paired rainy and clean images, which are challenging to obtain in real-world scenarios. To this end, we propose a novel structure-preserving frequency-regularized text-guided optimal transport (SFTOT) framework, which formulates the unpaired rain streaks and raindrops removal as an optimal transport problem. Specifically, we introduce a structure-preserving transport cost, incorporating the structural similarity constraint to minimize the duality gap between the primal and dual formulations, while preserving the structural details of reconstructed images. Furthermore, by embedding the inherent frequency sparsity of rain streaks and raindrops into the transport cost, we derive a frequency-regularized optimal transport objective, ensuring consistency in frequency distributions between the generated and clean images. Additionally, we employ a pre-trained one-step stable diffusion model as the restoration network, which is fine-tuned using the low-rank adaptation (LoRA) adapters and zero convolutional layers, while integrating the domain-specific text prompts for both degraded and clean images to guide the generation process. Extensive experiments demonstrate that our method surpasses the existing well-performing unpaired learning approaches, achieving notable improvements in both the fidelity and photo-realism.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 3380-3395
Top Cited PapersStructure-Preserving Frequency-Regularized Text-Guided Optimal Transport for Unpaired Rain Streaks and Raindrops Removal
The removal of rain streaks and raindrops is crucial for enhancing the image visibility and mitigating the weather degradations. However, most existing approaches rely on the paired rainy and clean images, which are challenging to obtain in real-world scenarios. To this end, we propose a novel structure-preserving frequency-regularized text-guided optimal transport (SFTOT) framework, which formulates the unpaired rain streaks and raindrops removal as an optimal transport problem. Specifically, we introduce a structure-preserving transport cost, incorporating the structural similarity constraint to minimize the duality gap between the primal and dual formulations, while preserving the structural details of reconstructed images. Furthermore, by embedding the inherent frequency sparsity of rain streaks and raindrops into the transport cost, we derive a frequency-regularized optimal transport objective, ensuring consistency in frequency distributions between the generated and clean images. Additionally, we employ a pre-trained one-step stable diffusion model as the restoration network, which is fine-tuned using the low-rank adaptation (LoRA) adapters and zero convolutional layers, while integrating the domain-specific text prompts for both degraded and clean images to guide the generation process. Extensive experiments demonstrate that our method surpasses the existing well-performing unpaired learning approaches, achieving notable improvements in both the fidelity and photo-realism.
- 4 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 308
Prior-oriented specific and triple-view general prompts for multi-weather degraded image restoration
- 4 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 308
Prior-oriented specific and triple-view general prompts for multi-weather degraded image restoration
- 2 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 307
Unpaired iterative prompt learning for real-world image deraining
- 2 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 307
Unpaired iterative prompt learning for real-world image deraining