Guoqing Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Guoqing Wang has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
- Yang Yang
University of Electronic Science and Technology of China, Chengdu, China
8 shared publications - Heng Tao Shen
Tongji University, Shanghai, China
7 shared publications - Mingfeng Zha
Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
4 shared publications - Tianyu Li
University of Electronic Science and Technology of China, Chengdu, China
4 shared publications - Peng Wang
University of Electronic Science and Technology of China, Chengdu, China
3 shared publications Chaofan Qiao
Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
2 shared publications
Latest Publications
- Open Access
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1018-1034
Group-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNs
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1018-1034
Open AccessGroup-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNs
- 11 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 6331-6345
DSPFusion: Image Fusion via Degradation and Semantic Dual-Prior Guidance
Existing infrared-visible image fusion methods are mainly tailored for high-quality source images. Although recent studies have begun to explore degradation-aware fusion, most existing methods still focus on specific degradation types, while unified frameworks that aim to handle diverse degradations often depend on auxiliary textual prompts, which limits their practicality in automatic fusion scenarios. This work presents a Degradation and Semantic Prior dual-guided framework for degraded image Fusion (DSPFusion), which jointly performs degradation-aware restoration and complementary information aggregation in a unified architecture without relying on auxiliary prompts. Specifically, it first extracts modality-specific degradation priors from degraded infrared and visible images, while capturing compact semantic embeddings from paired source images as low-quality semantic priors to encode global scene context. Then, a semantic prior diffusion model is devised to restore high-quality scene semantic priors in a compact latent space, providing global scene guidance with low computational overhead and enabling over 30× inference speedup compared with mainstream diffusion model-based image fusion schemes, such as DDFM. Guided by the restored semantic priors and degradation priors, the enhancement and fusion network adaptively suppresses degradations and aggregates complementary information. Extensive experiments under both degraded and normal scenarios demonstrate that DSPFusion effectively handles representative degradations, preserves complementary information, and achieves competitive performance with low computational cost, thereby broadening the practical application scope of image fusion. The source code is publicly available at https://github.com/Linfeng-Tang/DSPFusion.
- 11 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 6331-6345
DSPFusion: Image Fusion via Degradation and Semantic Dual-Prior Guidance
Existing infrared-visible image fusion methods are mainly tailored for high-quality source images. Although recent studies have begun to explore degradation-aware fusion, most existing methods still focus on specific degradation types, while unified frameworks that aim to handle diverse degradations often depend on auxiliary textual prompts, which limits their practicality in automatic fusion scenarios. This work presents a Degradation and Semantic Prior dual-guided framework for degraded image Fusion (DSPFusion), which jointly performs degradation-aware restoration and complementary information aggregation in a unified architecture without relying on auxiliary prompts. Specifically, it first extracts modality-specific degradation priors from degraded infrared and visible images, while capturing compact semantic embeddings from paired source images as low-quality semantic priors to encode global scene context. Then, a semantic prior diffusion model is devised to restore high-quality scene semantic priors in a compact latent space, providing global scene guidance with low computational overhead and enabling over 30× inference speedup compared with mainstream diffusion model-based image fusion schemes, such as DDFM. Guided by the restored semantic priors and degradation priors, the enhancement and fusion network adaptively suppresses degradations and aggregates complementary information. Extensive experiments under both degraded and normal scenarios demonstrate that DSPFusion effectively handles representative degradations, preserves complementary information, and achieves competitive performance with low computational cost, thereby broadening the practical application scope of image fusion. The source code is publicly available at https://github.com/Linfeng-Tang/DSPFusion.
- Top Cited Papers
- 28 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (6) , 8125-8141
Think Twice Before Determining: Toward Scene-Aware Visual Reasoning for Mirror Detection
Mirror detection (MD) aims to overcome interference caused by reflections and locate mirror regions. Existing methods focus on designing components to explicitly establish the associations between physical entities and corresponding imagings, or utilizing rotation to construct symmetric consistency. We observe that: a) incomplete and incorrect correspondence between entities and imagings; b) other physical materials (e.g., glass) exhibit characteristics partially similar to mirrors, causing confusion when they co-occur; c) complex interfering factors (e.g., occlusion) and reflection mechanisms may expand vector space several times over. To address these issues in a unified manner, we formulate the scene-aware visual reasoning network (SVRNet) based on visual prompts. Specifically, we construct the prototype-guided prompt chain reasoning (PPCR) that generates a mixed chain of thought reasoning based on maximal difference heterogeneous prototypes to construct comprehensive spatial location and semantic perception. Noise may accumulate gradually through the chain, and crucial clues may also disappear. Therefore, we design the prompt evolution (PE) to filter out noise and enhance the coupling between prompts. We further develop the mixture of prompt injection expert (MPIE) to dynamically select the optimal injection strategy in the low-rank space based on specific scene. Due to reflection interference and random parameter space introducing potential ambiguity, we formulate the three-way evidence-aware (TEA) loss to quantify the uncertainty, thereby providing reliable predictions. To leverage historical knowledge and further disentangle representations, we propose the frequency prototype contrastive (FPC) loss for learning more generalizable features across images. Finally, we relabel 25,828 images and formulate the first point-supervised MD framework. Extensive experiments conducted on four mirror benchmarks under three settings demonstrate that our method surpasses state-of-the-art approaches. Promising results are also achieved on six related benchmarks, showing its generality.
- 28 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (6) , 8125-8141
Top Cited PapersThink Twice Before Determining: Toward Scene-Aware Visual Reasoning for Mirror Detection
Mirror detection (MD) aims to overcome interference caused by reflections and locate mirror regions. Existing methods focus on designing components to explicitly establish the associations between physical entities and corresponding imagings, or utilizing rotation to construct symmetric consistency. We observe that: a) incomplete and incorrect correspondence between entities and imagings; b) other physical materials (e.g., glass) exhibit characteristics partially similar to mirrors, causing confusion when they co-occur; c) complex interfering factors (e.g., occlusion) and reflection mechanisms may expand vector space several times over. To address these issues in a unified manner, we formulate the scene-aware visual reasoning network (SVRNet) based on visual prompts. Specifically, we construct the prototype-guided prompt chain reasoning (PPCR) that generates a mixed chain of thought reasoning based on maximal difference heterogeneous prototypes to construct comprehensive spatial location and semantic perception. Noise may accumulate gradually through the chain, and crucial clues may also disappear. Therefore, we design the prompt evolution (PE) to filter out noise and enhance the coupling between prompts. We further develop the mixture of prompt injection expert (MPIE) to dynamically select the optimal injection strategy in the low-rank space based on specific scene. Due to reflection interference and random parameter space introducing potential ambiguity, we formulate the three-way evidence-aware (TEA) loss to quantify the uncertainty, thereby providing reliable predictions. To leverage historical knowledge and further disentangle representations, we propose the frequency prototype contrastive (FPC) loss for learning more generalizable features across images. Finally, we relabel 25,828 images and formulate the first point-supervised MD framework. Extensive experiments conducted on four mirror benchmarks under three settings demonstrate that our method surpasses state-of-the-art approaches. Promising results are also achieved on six related benchmarks, showing its generality.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 13893-13907
Toward Real-World RAW Blind Super-Resolution: A Novel Metadata-Integrated Approach and Benchmark
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 13893-13907
Toward Real-World RAW Blind Super-Resolution: A Novel Metadata-Integrated Approach and Benchmark
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (10) , 1-18
Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems
Neuro-Symbolic reasoning, commonly abbreviated as "NeSy," represents a critical and challenging area in artificial intelligence, characterized by its integration of data-driven neural learning and interpretable symbolic reasoning. Unfortunately, most NeSy research to date has mainly concentrated on developing interpretable AI systems for tasks like visual scene parsing or question answering, and has not adequately addressed the need for causal reasoning, cognitive autonomy, and adaptive self-evolution in open-world environments. This bring great challenges and makes previous methods fail to disentangle these causal cognitive complexities. This paper propose Self-Evolving Neuro-Symbolic Autonomy (SENSA) with causal resilience, integrating neural-symbolic bidirectional self-alignment, causal driven self-evolution, and hierarchical resilience planning to achieve autonomous cognitive decision-making. With this regard, a neural-symbolic bidirectional self-alignment is developed, which enables real-time mutual adaptation, ensuring robustness against adversarial noise and causal coherence in dynamic open-real environments. Specifically, we design a novel causal-driven self evolution that enables AI systems to autonomously refine their decision-making policies by leveraging causal reasoning and counterfactual analysis. On this basis, we further develope the hierarchical resilience planning to adapt, recover, and maintain performance even under disruptive or adversarial conditions. The SENSA bridges the gap between neural adaptability and symbolic rigor, which is called industrial brain, achieving causal reasoning and self-evolving autonomy in Cyber-Physical Systems. Theoretically, we prove that the causal reasoning, cognitive autonomy, and adaptive self-evolution by our SENSA can approximate the ground-truth. Empirically, extensive evaluations on eight benchmark datasets demonstrate our superiority over state-of-the-art baselines.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (10) , 1-18
Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems
Neuro-Symbolic reasoning, commonly abbreviated as "NeSy," represents a critical and challenging area in artificial intelligence, characterized by its integration of data-driven neural learning and interpretable symbolic reasoning. Unfortunately, most NeSy research to date has mainly concentrated on developing interpretable AI systems for tasks like visual scene parsing or question answering, and has not adequately addressed the need for causal reasoning, cognitive autonomy, and adaptive self-evolution in open-world environments. This bring great challenges and makes previous methods fail to disentangle these causal cognitive complexities. This paper propose Self-Evolving Neuro-Symbolic Autonomy (SENSA) with causal resilience, integrating neural-symbolic bidirectional self-alignment, causal driven self-evolution, and hierarchical resilience planning to achieve autonomous cognitive decision-making. With this regard, a neural-symbolic bidirectional self-alignment is developed, which enables real-time mutual adaptation, ensuring robustness against adversarial noise and causal coherence in dynamic open-real environments. Specifically, we design a novel causal-driven self evolution that enables AI systems to autonomously refine their decision-making policies by leveraging causal reasoning and counterfactual analysis. On this basis, we further develope the hierarchical resilience planning to adapt, recover, and maintain performance even under disruptive or adversarial conditions. The SENSA bridges the gap between neural adaptability and symbolic rigor, which is called industrial brain, achieving causal reasoning and self-evolving autonomy in Cyber-Physical Systems. Theoretically, we prove that the causal reasoning, cognitive autonomy, and adaptive self-evolution by our SENSA can approximate the ground-truth. Empirically, extensive evaluations on eight benchmark datasets demonstrate our superiority over state-of-the-art baselines.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 6860-6875
Hierarchical Consistency Learning for Test-Time Adaptation in Camouflage Perception
Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes. Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and annotation dependency, limiting their adaptability to scene variations and unseen camouflage patterns. To overcome these, we propose the hierarchical consistency learning (HCL) framework, which integrates test-time adaptation for dynamic representation recalibration. Specifically, we design the hierarchical representation reconstruction (HRR) to alleviate feature entanglement by synergizing spatial reconstruction with dual-stream frequency-domain decomposition, enhancing robustness against appearance homogenization. The pixel and spectrum inference provide structural and contextual priors. We further introduce task affinity guidance (TAG) to propagate knowledge across branches via channel-wise affinity, aligning local discriminative cues and mitigating semantic drift. To ensure semantic invariance, we formulate the prototype consistency calibration (PCC), which aggregates region features into compact prototypes and establishes prototype-feature similarity. This imposes implicit and hierarchical constraints that bridge task and representation gaps. Extensive experiments across four camouflaged and four underwater object benchmarks, under three degradation settings, demonstrate that our method consistently outperforms state-of-the-art approaches, highlighting its robustness and generalization under distribution shifts.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 6860-6875
Hierarchical Consistency Learning for Test-Time Adaptation in Camouflage Perception
Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes. Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and annotation dependency, limiting their adaptability to scene variations and unseen camouflage patterns. To overcome these, we propose the hierarchical consistency learning (HCL) framework, which integrates test-time adaptation for dynamic representation recalibration. Specifically, we design the hierarchical representation reconstruction (HRR) to alleviate feature entanglement by synergizing spatial reconstruction with dual-stream frequency-domain decomposition, enhancing robustness against appearance homogenization. The pixel and spectrum inference provide structural and contextual priors. We further introduce task affinity guidance (TAG) to propagate knowledge across branches via channel-wise affinity, aligning local discriminative cues and mitigating semantic drift. To ensure semantic invariance, we formulate the prototype consistency calibration (PCC), which aggregates region features into compact prototypes and establishes prototype-feature similarity. This imposes implicit and hierarchical constraints that bridge task and representation gaps. Extensive experiments across four camouflaged and four underwater object benchmarks, under three degradation settings, demonstrate that our method consistently outperforms state-of-the-art approaches, highlighting its robustness and generalization under distribution shifts.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (10) , 1-16
Knowledge Diffusion-Based Adaptive Alignment with Hierarchical Context for Video Temporal Grounding
Video Temporal Grounding (VTG) aims to localize the temporal moment that corresponds to a natural-language query in an untrimmed video. However, VTG faces two core challenges: narrowing the semantic gap between concise text queries and complex visual content, and extracting discriminative moment cues from long background-dominant sequences. To address these challenges, we propose Knowledge Diffusion Alignment (KDA), a diffusion-based framework that operates in the semantic feature domain. At its core, a Background Residual Diffusion Model (BRDM) starts from adaptive global video knowledge and, under query conditioning, progressively removes query-irrelevant background residuals to synthesize moment knowledge. In addition, to provide a strong conditional prior and multi-scale supervision, Hierarchical Video Knowledge Extraction (HVKE) aggregates context at multiple temporal granularities, producing both video and moment knowledge. KDA is trained in three stages: first learning target-aware moment knowledge, then aligning the diffusion process to that target, and finally performing end-to-end inference using BRDM-generated knowledge. The synthesized moment knowledge is injected into knowledge prompt reasoning, where a Dynamic Moment-aware Encoder (DME) adaptively generates dynamic temporal convolution kernels conditioned on the moment knowledge, coupling efficient local modeling with global self-attention. For prediction, a Spans-Enhanced Hierarchical Decoder (SEHD) constructs a temporal pyramid and adaptively selects the most relevant initial spans to exploit intrinsic alignment cues. Experiments across public benchmarks demonstrate that the proposed KDA outperforms the state-of-the-art methods, and extensive ablations further verify the effectiveness of the module design. The code is available at https://github.com/Evangelion09/HKDA.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (10) , 1-16
Knowledge Diffusion-Based Adaptive Alignment with Hierarchical Context for Video Temporal Grounding
Video Temporal Grounding (VTG) aims to localize the temporal moment that corresponds to a natural-language query in an untrimmed video. However, VTG faces two core challenges: narrowing the semantic gap between concise text queries and complex visual content, and extracting discriminative moment cues from long background-dominant sequences. To address these challenges, we propose Knowledge Diffusion Alignment (KDA), a diffusion-based framework that operates in the semantic feature domain. At its core, a Background Residual Diffusion Model (BRDM) starts from adaptive global video knowledge and, under query conditioning, progressively removes query-irrelevant background residuals to synthesize moment knowledge. In addition, to provide a strong conditional prior and multi-scale supervision, Hierarchical Video Knowledge Extraction (HVKE) aggregates context at multiple temporal granularities, producing both video and moment knowledge. KDA is trained in three stages: first learning target-aware moment knowledge, then aligning the diffusion process to that target, and finally performing end-to-end inference using BRDM-generated knowledge. The synthesized moment knowledge is injected into knowledge prompt reasoning, where a Dynamic Moment-aware Encoder (DME) adaptively generates dynamic temporal convolution kernels conditioned on the moment knowledge, coupling efficient local modeling with global self-attention. For prediction, a Spans-Enhanced Hierarchical Decoder (SEHD) constructs a temporal pyramid and adaptively selects the most relevant initial spans to exploit intrinsic alignment cues. Experiments across public benchmarks demonstrate that the proposed KDA outperforms the state-of-the-art methods, and extensive ablations further verify the effectiveness of the module design. The code is available at https://github.com/Evangelion09/HKDA.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 7200-7209
InteractGuide: LLM-Enhanced Multimodal Reasoning for User-Centric Interaction Recommendations in AR-HRI Authoring
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 7200-7209
Open AccessInteractGuide: LLM-Enhanced Multimodal Reasoning for User-Centric Interaction Recommendations in AR-HRI Authoring
- 27 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 37 (4) , 1618-1630
SNN-FT: Temporal-Coded Spiking Neural Networks for Fourier Transform
The Fourier transform (FT) stands as a fundamental tool in modern signal processing with widespread applications across various scientific and engineering fields. Therefore, there remains a need for continued research efforts to devise energy-efficient implementations of the FT. Due to their inherent energy efficiency, biologically plausible spiking neural networks (SNNs) emerge as a promising alternative solution. However, current SNN implementations of the FT suffer from two key shortcomings, namely, high latency and reduced accuracy. In this article, we analyze the underlying causes of these limitations and highlight deficiencies in the existing spike-based encoding mechanisms and spiking neuron models. We then propose a new SNN-based FT (SNN-FT) based on a logarithmically polarized time-to-first-spike (TTFS) encoding method (called LP-TTFS) along with a novel piecewise spiking neuron (PTSN) model based on ternary spikes (referred to as PTSN). The resulting SNN-FT is mathematically equivalent to the conventional FT and demonstrates superior performance in accuracy as well as reduced latency. We assess the performance of the proposed SNN-FT alternative through extensive experiments on FT-based applications, such as radar and audio signal processing, and the obtained results demonstrate the efficacy of SNN-FT and its superiority over the existing approaches. This study unveils a novel energy-efficient neuromorphic computing technique with great potential for FT applications across diverse scientific and engineering domains.
- 27 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 37 (4) , 1618-1630
SNN-FT: Temporal-Coded Spiking Neural Networks for Fourier Transform
The Fourier transform (FT) stands as a fundamental tool in modern signal processing with widespread applications across various scientific and engineering fields. Therefore, there remains a need for continued research efforts to devise energy-efficient implementations of the FT. Due to their inherent energy efficiency, biologically plausible spiking neural networks (SNNs) emerge as a promising alternative solution. However, current SNN implementations of the FT suffer from two key shortcomings, namely, high latency and reduced accuracy. In this article, we analyze the underlying causes of these limitations and highlight deficiencies in the existing spike-based encoding mechanisms and spiking neuron models. We then propose a new SNN-based FT (SNN-FT) based on a logarithmically polarized time-to-first-spike (TTFS) encoding method (called LP-TTFS) along with a novel piecewise spiking neuron (PTSN) model based on ternary spikes (referred to as PTSN). The resulting SNN-FT is mathematically equivalent to the conventional FT and demonstrates superior performance in accuracy as well as reduced latency. We assess the performance of the proposed SNN-FT alternative through extensive experiments on FT-based applications, such as radar and audio signal processing, and the obtained results demonstrate the efficacy of SNN-FT and its superiority over the existing approaches. This study unveils a novel energy-efficient neuromorphic computing technique with great potential for FT applications across diverse scientific and engineering domains.
- Open Access
- 27 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-19
AttentionAR: AR Adaptation and Warning for Real-World Safety via Attention Modeling and MLLM Reasoning
- 27 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Open AccessAttentionAR: AR Adaptation and Warning for Real-World Safety via Attention Modeling and MLLM Reasoning