Qingbao Huang
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
Research Interests
Qingbao Huang has a total of 126 co-authors. Here are the top co-authors by number of shared publications:
- Yi Cai
Key Laboratory of Big Data and Intelligent Robot, Ministry of Education, South China University of Technology, Guangzhou, China
20 shared publications - Qing Li
The Hong Kong Polytechnic University, Hong Kong, China
13 shared publications - Pijian Li
School of Electrical Engineering, Guangxi University, Nanning, China
6 shared publications - Tao Wang
Department of Biostatistics & Health Informatics King's College London London United Kingdom
6 shared publications Yi Cai
Key Laboratory of Big Data and Intelligent Robot of Ministry of Education, SCUT, Guangzhou, China School of Software Engineering, South China University of Technology, Guangzhou, China
6 shared publicationsXingmao Zhang
Guangxi Arts University
5 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17510-17516
EgoSEV: A Social Evidence Verification Method for Egocentric Social Relationship and Emotion-Causality Reasoning
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17510-17516
Open AccessEgoSEV: A Social Evidence Verification Method for Egocentric Social Relationship and Emotion-Causality Reasoning
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9628-9637
HCNet: Hyperbolic Hierarchical Clause Network for Weakly Supervised Multi-task Visual Grounding
Existing weakly supervised referring expression comprehension (WREC) and segmentation (WRES) methods perform anchor-text matching using flat sentence-level representations, thereby discarding the multi-granularity hierarchical semantics inherent in both visual and linguistic modalities. Because referring expressions naturally form hierarchical clauses of increasing specificity and flat Euclidean space distorts such tree-like structures, explicit hierarchical modeling is necessary yet overlooked. We propose HCNet (Hyperbolic hierarchical Clause Network), which first decomposes each expression into four hierarchical clauses via dependency parsing, then refines sentence representations through a hierarchical text enhancer that attends to coarser clause levels. Subsequently, both visual and textual features are projected into a dual Euclidean-Lorentzian hyperbolic space, where an entailment cone loss enforces hierarchical nesting on the text side and a structure alignment loss transfers this hierarchy to the visual modality. Experiments on RefCOCO, RefCOCO+, and RefCOCOg demonstrate that HCNet achieves state-of-the-art on both WREC and WRES, with improvements of up to +3.54% over the previous best. The code is available at https://github.com/VILAN-Lab/HCNet.
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9628-9637
Open AccessHCNet: Hyperbolic Hierarchical Clause Network for Weakly Supervised Multi-task Visual Grounding
Existing weakly supervised referring expression comprehension (WREC) and segmentation (WRES) methods perform anchor-text matching using flat sentence-level representations, thereby discarding the multi-granularity hierarchical semantics inherent in both visual and linguistic modalities. Because referring expressions naturally form hierarchical clauses of increasing specificity and flat Euclidean space distorts such tree-like structures, explicit hierarchical modeling is necessary yet overlooked. We propose HCNet (Hyperbolic hierarchical Clause Network), which first decomposes each expression into four hierarchical clauses via dependency parsing, then refines sentence representations through a hierarchical text enhancer that attends to coarser clause levels. Subsequently, both visual and textual features are projected into a dual Euclidean-Lorentzian hyperbolic space, where an entailment cone loss enforces hierarchical nesting on the text side and a structure alignment loss transfers this hierarchy to the visual modality. Experiments on RefCOCO, RefCOCO+, and RefCOCOg demonstrate that HCNet achieves state-of-the-art on both WREC and WRES, with improvements of up to +3.54% over the previous best. The code is available at https://github.com/VILAN-Lab/HCNet.
- 23 October 2026
- Published by Elsevier in Information Processing & Management
- Vol. 64 (2)
A unified framework for large-foundation-model-based multi-phrasing synthetic VQA data generation and downstream VQA training
- 23 October 2026
- Published by Elsevier in Information Processing & Management
- Vol. 64 (2)
A unified framework for large-foundation-model-based multi-phrasing synthetic VQA data generation and downstream VQA training
- 1 October 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (13) , 540
SPVIS: stabilized object-query propagation for robust video instance segmentation
- 1 October 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (13) , 540
SPVIS: stabilized object-query propagation for robust video instance segmentation
- 17 July 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 351
ExCap: Entity-aware zero-shot image captioning via faithful synthetic image–text alignment
- 17 July 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 351
ExCap: Entity-aware zero-shot image captioning via faithful synthetic image–text alignment
- 5 June 2026
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- p. 1-21
PointerHalo: Hands-Free XR App Navigation Using Subtle Head Movements
- 5 June 2026
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- p. 1-21
PointerHalo: Hands-Free XR App Navigation Using Subtle Head Movements
- 16 March 2026
- Published by Aerospace Information Research Institute, Chinese Academy of Sciences in Journal of Image and Graphics
- Vol. 31 (3) , 826-839
面向组合零样本识别的图文解耦合方法
目的组合零样本识别是计算机视觉领域零样本学习任务的子任务,旨在从已经见过的组合图像中学习属性和物体概念,并将其迁移到未见过的组合上。现有方法对组合图像中属性和物体的解耦合能力不足,并且未能充分发挥文本标签对于属性和物体信息的解耦合作用。方法为解决组合图像中属性与物体信息纠缠的问题,针对文本与视觉模态的差异,提出双模态解耦机制:在文本端构建图神经网络以建模属性与物体间的语义关系,在视觉端引入交叉注意力机制增强对属性和物体特征的分离能力。该方法集成于语言图像预训练框架中,从语言与视觉两个层面提升模型对属性与物体概念的建模能力,从而增强未见组合的识别效果。结果在3个主流的组合零样本识别基准数据集MIT-States、UT-Zappos和C-GQA(compositional GQA)上对所提方法进行了系统评估,结果表明模型性能显著提升。以MIT-States数据集为例,在封闭世界设置下,相较于性能排名第2的模型,本文方法的AUC(area under curve) 提升3.3%,HM(Harmonic mean)提升2.4%,已见组合的识别准确率提升5.3%,未见组合提升1.0%;在开放世界设置下,本文方法的AUC提升0.9%,HM提升0.7%,已见组合与未见组合准确率分别提升3.2% 和1.0%。此外,在MIT-States数据集上对提出的文本与视觉解耦模块及其上下文建模组件进行了消融实验,进一步验证了各子模块对整体性能的有效贡献。结论所提出的图文双端解耦合模块提升了模型对于组合中属性和物体的学习能力,显著提升了模型在组合零样本识别任务上的表现。
- 16 March 2026
- Published by Aerospace Information Research Institute, Chinese Academy of Sciences in Journal of Image and Graphics
- Vol. 31 (3) , 826-839
面向组合零样本识别的图文解耦合方法
目的组合零样本识别是计算机视觉领域零样本学习任务的子任务,旨在从已经见过的组合图像中学习属性和物体概念,并将其迁移到未见过的组合上。现有方法对组合图像中属性和物体的解耦合能力不足,并且未能充分发挥文本标签对于属性和物体信息的解耦合作用。方法为解决组合图像中属性与物体信息纠缠的问题,针对文本与视觉模态的差异,提出双模态解耦机制:在文本端构建图神经网络以建模属性与物体间的语义关系,在视觉端引入交叉注意力机制增强对属性和物体特征的分离能力。该方法集成于语言图像预训练框架中,从语言与视觉两个层面提升模型对属性与物体概念的建模能力,从而增强未见组合的识别效果。结果在3个主流的组合零样本识别基准数据集MIT-States、UT-Zappos和C-GQA(compositional GQA)上对所提方法进行了系统评估,结果表明模型性能显著提升。以MIT-States数据集为例,在封闭世界设置下,相较于性能排名第2的模型,本文方法的AUC(area under curve) 提升3.3%,HM(Harmonic mean)提升2.4%,已见组合的识别准确率提升5.3%,未见组合提升1.0%;在开放世界设置下,本文方法的AUC提升0.9%,HM提升0.7%,已见组合与未见组合准确率分别提升3.2% 和1.0%。此外,在MIT-States数据集上对提出的文本与视觉解耦模块及其上下文建模组件进行了消融实验,进一步验证了各子模块对整体性能的有效贡献。结论所提出的图文双端解耦合模块提升了模型对于组合中属性和物体的学习能力,显著提升了模型在组合零样本识别任务上的表现。
- Open Access
- 10 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (2) , 1-24
Implement Referring Expression Comprehension by Extending Auto-focus Lens to Locked Vision Model
Referring Expression Comprehension (REC) aims to achieve fine-grained cross-modal content alignment. The traditional two-stage approaches, by decomposing REC into localization (region proposal) and comprehension (expression-based ranking), lead to the isolation of continuous image information and heavily rely on the quality of the proposals. In this article, we propose a point-based two-stage framework for REC to quickly achieve localization by inserting a language-modulated auto-focus module into the locked vision model. Specifically, we redefine REC as two processes: point-based cross-modal comprehension and point-based instance localization. For the comprehension stage, we reconstruct the raw annotations into soft masks at the feature point level as a metric of cross-modal correlation. With this indirect metric, REC can be approximated as a binary classification problem, which fundamentally avoids the impact of isolated regions. Remarkably, soft masks are shape-independent, which means our method is extremely general. By switching different vision models, different types of predictions (e.g., localization and segmentation) can be obtained. Experiments on multiple benchmarks demonstrate the feasibility and potential of our point-based paradigm. Our code will be public at https://github.com/VILAN-Lab/PBREC-AF .
- 10 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (2) , 1-24
Open AccessImplement Referring Expression Comprehension by Extending Auto-focus Lens to Locked Vision Model
Referring Expression Comprehension (REC) aims to achieve fine-grained cross-modal content alignment. The traditional two-stage approaches, by decomposing REC into localization (region proposal) and comprehension (expression-based ranking), lead to the isolation of continuous image information and heavily rely on the quality of the proposals. In this article, we propose a point-based two-stage framework for REC to quickly achieve localization by inserting a language-modulated auto-focus module into the locked vision model. Specifically, we redefine REC as two processes: point-based cross-modal comprehension and point-based instance localization. For the comprehension stage, we reconstruct the raw annotations into soft masks at the feature point level as a metric of cross-modal correlation. With this indirect metric, REC can be approximated as a binary classification problem, which fundamentally avoids the impact of isolated regions. Remarkably, soft masks are shape-independent, which means our method is extremely general. By switching different vision models, different types of predictions (e.g., localization and segmentation) can be obtained. Experiments on multiple benchmarks demonstrate the feasibility and potential of our point-based paradigm. Our code will be public at https://github.com/VILAN-Lab/PBREC-AF .
- 28 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 2047-2060
Anchor-Based Multimodal Verification: A Dynamic Query Framework for Fake News Forensics in Short Videos
The proliferation of maliciously altered short videos on social media platforms poses a significant threat to information security ecosystems, eroding public trust in digital media. Despite recent advancements in detecting fake video news, significant challenges remain in the forensic analysis of short videos, leading to issues of bias. First, as technology rapidly advances, fake videos are becoming increasingly semantically convincing, undermining the effectiveness of current classification methods. Second, the heterogeneous nature of video modalities (visual, textual, audio) creates critical challenges for models to learn discriminative feature representations. To address these challenges, we propose a dynamic query framework for fake news forensics in short videos, termed the Semantic Guided Adaptive Network (SGAN). Our approach is motivated by the need to utilize superficial alignment to identify suspicious manipulations through anchor-based verification and to leverage the adaptive capability of learnable queries to learn the heterogeneous boundary in each modality. Specifically, SGAN comprises a verification module and a flexible query learning module. The verification module employs text as the anchor to verify detailed context, mining fine-grained information while emphasizing key features, thereby providing candidate manipulations for downstream modules. The query learning module leverages learnable queries to map heterogeneous forensic features and integrates them through multi-level fusion for decision-making. Extensive experiments conducted on two widely used datasets demonstrate the effectiveness and generalization of the proposed method.
- 28 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 2047-2060
Anchor-Based Multimodal Verification: A Dynamic Query Framework for Fake News Forensics in Short Videos
The proliferation of maliciously altered short videos on social media platforms poses a significant threat to information security ecosystems, eroding public trust in digital media. Despite recent advancements in detecting fake video news, significant challenges remain in the forensic analysis of short videos, leading to issues of bias. First, as technology rapidly advances, fake videos are becoming increasingly semantically convincing, undermining the effectiveness of current classification methods. Second, the heterogeneous nature of video modalities (visual, textual, audio) creates critical challenges for models to learn discriminative feature representations. To address these challenges, we propose a dynamic query framework for fake news forensics in short videos, termed the Semantic Guided Adaptive Network (SGAN). Our approach is motivated by the need to utilize superficial alignment to identify suspicious manipulations through anchor-based verification and to leverage the adaptive capability of learnable queries to learn the heterogeneous boundary in each modality. Specifically, SGAN comprises a verification module and a flexible query learning module. The verification module employs text as the anchor to verify detailed context, mining fine-grained information while emphasizing key features, thereby providing candidate manipulations for downstream modules. The query learning module leverages learnable queries to map heterogeneous forensic features and integrates them through multi-level fusion for decision-making. Extensive experiments conducted on two widely used datasets demonstrate the effectiveness and generalization of the proposed method.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 2731-2743
DESSM: Dual Encoder-Based State Space Model for Image Inpainting
Image inpainting represents a fundamental and challenging problem in computer vision, requiring the synthesis of visually plausible content for missing regions while preserving both textural details and structural coherence. While current approaches employ auxiliary networks and attention mechanisms to capture structural priors and expand receptive fields, they remain constrained by two fundamental limitations: (1) insufficient interaction between textural and structural priors, and (2) the quadratic computational complexity inherent in attention operations. To overcome these challenges, we present DESSM, an innovative Dual Encoder-based State space Model for image inpainting that achieves efficient global context modeling with linear computational complexity. Our DESSM integrates three synergistically designed modules: (1) a dual-branch encoder for complementary learning of textural patterns and structural priors, (2) a Feature Cross Fusion Block (FCFB) enabling dynamic feature interaction while adaptively suppressing redundant information, and (3) a Spatial-Channel joint Selective scan Block (SCSB) for efficient long-range dependency modeling. Comprehensive evaluations across four standard benchmarks (i.e., CelebA, CelebA-HQ, Places2, and Paris StreetView) demonstrate that our DESSM achieves state-of-the-art performance in both visual fidelity and computational efficiency.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 2731-2743
DESSM: Dual Encoder-Based State Space Model for Image Inpainting
Image inpainting represents a fundamental and challenging problem in computer vision, requiring the synthesis of visually plausible content for missing regions while preserving both textural details and structural coherence. While current approaches employ auxiliary networks and attention mechanisms to capture structural priors and expand receptive fields, they remain constrained by two fundamental limitations: (1) insufficient interaction between textural and structural priors, and (2) the quadratic computational complexity inherent in attention operations. To overcome these challenges, we present DESSM, an innovative Dual Encoder-based State space Model for image inpainting that achieves efficient global context modeling with linear computational complexity. Our DESSM integrates three synergistically designed modules: (1) a dual-branch encoder for complementary learning of textural patterns and structural priors, (2) a Feature Cross Fusion Block (FCFB) enabling dynamic feature interaction while adaptively suppressing redundant information, and (3) a Spatial-Channel joint Selective scan Block (SCSB) for efficient long-range dependency modeling. Comprehensive evaluations across four standard benchmarks (i.e., CelebA, CelebA-HQ, Places2, and Paris StreetView) demonstrate that our DESSM achieves state-of-the-art performance in both visual fidelity and computational efficiency.