Yaxiong Wang
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
Yaxiong Wang has a total of 107 co-authors. Here are the top co-authors by number of shared publications:
- Xueming Qian
Xi’an Jiaotong University
17 shared publications - Zhedong Zheng
University of Macau, Macau, China
10 shared publications - Li Zhu
School of Software Engineering, Xi’an Jiaotong University, Xi’an 710049, China
9 shared publications - Zhun Zhong
Hefei University of Technology, Hefei, China
8 shared publications - Lechao Cheng
Hefei University of Technology, Hefei, China
6 shared publications - Mengjian Li
Zhejiang Lab, Hangzhou, China
4 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1120-1128
SplitGaussian: Reconstructing Dynamic Scenes via Visual Geometry Decomposition
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1120-1128
Open AccessSplitGaussian: Reconstructing Dynamic Scenes via Visual Geometry Decomposition
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3598-3607
Acoustically Grounded Cost Learning for Open-Vocabulary Audio-Visual Semantic Segmentation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3598-3607
Open AccessAcoustically Grounded Cost Learning for Open-Vocabulary Audio-Visual Semantic Segmentation
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 2320-2331
Pretrain-then-Adapt: Uncertainty-Aware Test-Time Adaptation for Text-based Person Search
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 2320-2331
Open AccessPretrain-then-Adapt: Uncertainty-Aware Test-Time Adaptation for Text-based Person Search
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (7) , 5415-5426
Look, Compare and Draw: Differential Query Transformer for Automatic Oil Painting
This work introduces a new approach to automatic oil painting that emphasizes the creation of dynamic and expressive brushstrokes. A pivotal challenge lies in mitigating the duplicate and common-place strokes, which often lead to less aesthetic outcomes. Inspired by the human painting process, i.e., observing, comparing, and drawing, we incorporate differential image analysis into a neural oil painting model, allowing the model to effectively concentrate on the incremental impact of successive brushstrokes. To operationalize this concept, we propose the Differential Query Transformer (DQ-Transformer), a new architecture that leverages differentially derived image representations enriched with positional encoding to guide the stroke prediction process. This integration enables the model to maintain heightened sensitivity to local details, resulting in more refined and nuanced stroke generation. Furthermore, we incorporate adversarial training into our framework, enhancing the accuracy of stroke prediction and thereby improving the overall realism and fidelity of the synthesized paintings. Extensive qualitative evaluations, complemented by a controlled user study, validate that our DQ-Transformer surpasses existing methods in both visual realism and artistic authenticity, typically achieving these results with fewer strokes.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (7) , 5415-5426
Look, Compare and Draw: Differential Query Transformer for Automatic Oil Painting
This work introduces a new approach to automatic oil painting that emphasizes the creation of dynamic and expressive brushstrokes. A pivotal challenge lies in mitigating the duplicate and common-place strokes, which often lead to less aesthetic outcomes. Inspired by the human painting process, i.e., observing, comparing, and drawing, we incorporate differential image analysis into a neural oil painting model, allowing the model to effectively concentrate on the incremental impact of successive brushstrokes. To operationalize this concept, we propose the Differential Query Transformer (DQ-Transformer), a new architecture that leverages differentially derived image representations enriched with positional encoding to guide the stroke prediction process. This integration enables the model to maintain heightened sensitivity to local details, resulting in more refined and nuanced stroke generation. Furthermore, we incorporate adversarial training into our framework, enhancing the accuracy of stroke prediction and thereby improving the overall realism and fidelity of the synthesized paintings. Extensive qualitative evaluations, complemented by a controlled user study, validate that our DQ-Transformer surpasses existing methods in both visual realism and artistic authenticity, typically achieving these results with fewer strokes.
- Open Access
- 10 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (8) , 1-17
POS: A Prompts Optimization Suite for Augmenting Text-to-Video Generation
This paper targets to enhance the diffusion-based text-to-video generation by improving the two input prompts, including the noise and the text. Accommodated with this goal, we propose POS, a P rompt O ptimization S uite to boost text-to-video models. POS is motivated by two observations: (1) Video generation shows instability in terms of noise. Given the same text, different noises lead to videos that differ significantly in terms of both frame quality and temporal consistency. This observation implies that there exists an optimal noise matched to each textual input; To capture the potential noise, we propose an optimal noise approximator to approach the potential optimal noise. Particularly, the optimal noise approximator initially searches a video that closely relates to the text prompt and then inverts it into the noise space to serve as an improved noise prompt for the textual input. (2) Improving the text prompt via LLMs often causes semantic deviation. Many existing text-to-vision works have utilized LLMs to improve the text prompts for generation enhancement.However, existing methods often neglect the semantic alignment between the original text and the rewritten one.In response to this issue, we design a semantic-preserving rewriter to impose constraints in both rewriting and denoising phrases to preserve semantic consistency. Extensive experiments on popular benchmarks show that our POS can improve the text-to-video models with a clear margin.
- 10 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (8) , 1-17
Open AccessPOS: A Prompts Optimization Suite for Augmenting Text-to-Video Generation
This paper targets to enhance the diffusion-based text-to-video generation by improving the two input prompts, including the noise and the text. Accommodated with this goal, we propose POS, a P rompt O ptimization S uite to boost text-to-video models. POS is motivated by two observations: (1) Video generation shows instability in terms of noise. Given the same text, different noises lead to videos that differ significantly in terms of both frame quality and temporal consistency. This observation implies that there exists an optimal noise matched to each textual input; To capture the potential noise, we propose an optimal noise approximator to approach the potential optimal noise. Particularly, the optimal noise approximator initially searches a video that closely relates to the text prompt and then inverts it into the noise space to serve as an improved noise prompt for the textual input. (2) Improving the text prompt via LLMs often causes semantic deviation. Many existing text-to-vision works have utilized LLMs to improve the text prompts for generation enhancement.However, existing methods often neglect the semantic alignment between the original text and the rewritten one.In response to this issue, we design a semantic-preserving rewriter to impose constraints in both rewriting and denoising phrases to preserve semantic consistency. Extensive experiments on popular benchmarks show that our POS can improve the text-to-video models with a clear margin.
- 21 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
3 × 3 Kernel is ALL You Need for Vision
Most modern Convolutional Neural Networks (CNNs) employ a multi-branch structure with various-sized convolutions to capture long- and short-range dependencies. However, these CNNs use large kernel convolutions (e.g., astonishingly 101 kernels) and specialized techniques (e.g., reparameterization and sparsity), increasing complexity in both training and inference stages. This paper focuses on designing an efficient CNN based on pure 3×3 convolutions without introducing complex operations and techniques. Specifically, we propose a Spatial Pyramid (SP) block, which consists of the Multi-branch Residual (MbR) module and the Gated-branch Residual (GbR) module. The MbR introduces multiscale pooling as the key component, thus capturing long-range visual cues through large down-sampling rates and shorter-range dependencies through low down-sampling rates while maintaining low computational complexity. Besides, the GbR uses one 3×3 convolution to refine dependencies along spatial and channel dimensions. Based on the SP block, we construct the Spatial Pyramid CNN (SPCNN), a model composed exclusively of Point-Wise Convolution and 3×3 Depth-Wise Convolution. Under comparable computational complexity, SPCNN significantly outperforms the state-of-the-art CNN PeLK (83.6% vs 82.6%) with only 3 × 3 kernels (compared to 101 × 101 kernels in PeLK). Besides, our SPCNN demonstrates comparability with state-of-the-art backbones in lightweight models, object detection, instance segmentation, and semantic segmentation. Moreover, evaluations of four image retrieval benchmarks also demonstrate the effectiveness. All codes are released at https://github.com/xiaolai-sqlai/SPCNN.
- 21 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
3 × 3 Kernel is ALL You Need for Vision
Most modern Convolutional Neural Networks (CNNs) employ a multi-branch structure with various-sized convolutions to capture long- and short-range dependencies. However, these CNNs use large kernel convolutions (e.g., astonishingly 101 kernels) and specialized techniques (e.g., reparameterization and sparsity), increasing complexity in both training and inference stages. This paper focuses on designing an efficient CNN based on pure 3×3 convolutions without introducing complex operations and techniques. Specifically, we propose a Spatial Pyramid (SP) block, which consists of the Multi-branch Residual (MbR) module and the Gated-branch Residual (GbR) module. The MbR introduces multiscale pooling as the key component, thus capturing long-range visual cues through large down-sampling rates and shorter-range dependencies through low down-sampling rates while maintaining low computational complexity. Besides, the GbR uses one 3×3 convolution to refine dependencies along spatial and channel dimensions. Based on the SP block, we construct the Spatial Pyramid CNN (SPCNN), a model composed exclusively of Point-Wise Convolution and 3×3 Depth-Wise Convolution. Under comparable computational complexity, SPCNN significantly outperforms the state-of-the-art CNN PeLK (83.6% vs 82.6%) with only 3 × 3 kernels (compared to 101 × 101 kernels in PeLK). Besides, our SPCNN demonstrates comparability with state-of-the-art backbones in lightweight models, object detection, instance segmentation, and semantic segmentation. Moreover, evaluations of four image retrieval benchmarks also demonstrate the effectiveness. All codes are released at https://github.com/xiaolai-sqlai/SPCNN.
- 13 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 3887-3899
Dynamic Correlation-Guided Disentanglement and Contrastive Learning for RGB-D Cross-Modal Re-Identification
Person re-identification (Re-ID) across RGB and depth modalities offers complementary cues for robust pedestrian matching under challenging conditions. However, the significant discrepancy between RGB appearance features and depth structural features complicates cross-modal alignment. Existing methods either depend on static architectural designs or impose strong constraints to capture the common features of the two modalities, often suffering from branch imbalance or distorted identity features. In this work, we propose a novel framework, Dynamic Correlation-Guided Disentanglement and Contrastive Learning (DCG-DCL), for RGB-D cross-modal Re-ID. First, the Dynamic Correlation-guided Disentanglement (DCGD) dynamically decouples features with the guidance of inter-modal correlation, which explicitly enforces common-feature learning via a cross-correlation constraint and adaptively separates common and unique components without predefined assumptions. Second, a Common & Unique Contrastive Learning (CUCL) strategy fully leverages these decoupled features, which aligns RGB/depth features closer to their common representation and pushes them away from unique redundancies. This dual mechanism effectively narrows modality discrepancy and boosts robustness against modality-specific noise. Extensive experiments on multiple public benchmarks demonstrate that our method achieves state-of-the-art performance, with ablation studies validating the necessity of each component.
- 13 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 3887-3899
Dynamic Correlation-Guided Disentanglement and Contrastive Learning for RGB-D Cross-Modal Re-Identification
Person re-identification (Re-ID) across RGB and depth modalities offers complementary cues for robust pedestrian matching under challenging conditions. However, the significant discrepancy between RGB appearance features and depth structural features complicates cross-modal alignment. Existing methods either depend on static architectural designs or impose strong constraints to capture the common features of the two modalities, often suffering from branch imbalance or distorted identity features. In this work, we propose a novel framework, Dynamic Correlation-Guided Disentanglement and Contrastive Learning (DCG-DCL), for RGB-D cross-modal Re-ID. First, the Dynamic Correlation-guided Disentanglement (DCGD) dynamically decouples features with the guidance of inter-modal correlation, which explicitly enforces common-feature learning via a cross-correlation constraint and adaptively separates common and unique components without predefined assumptions. Second, a Common & Unique Contrastive Learning (CUCL) strategy fully leverages these decoupled features, which aligns RGB/depth features closer to their common representation and pushes them away from unique redundancies. This dual mechanism effectively narrows modality discrepancy and boosts robustness against modality-specific noise. Extensive experiments on multiple public benchmarks demonstrate that our method achieves state-of-the-art performance, with ablation studies validating the necessity of each component.
- 17 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 179
Minimizing the pretraining gap: Domain-aligned text-based person retrieval
- 17 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 179
Minimizing the pretraining gap: Domain-aligned text-based person retrieval
- 18 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 1820-1832
LEViT: Locally Enhanced Vision Transformer for Efficient Object Re-Identification
Vision Transformer (ViT) on object re-identification (ReID) has attracted significant attention recently. However, ViT-based ReID substantially increases computational complexity, imposing significant burdens during training and inference. This paper presents an efficient and effective ViT-based backbone for ReID tasks, called the Locally Enhanced Vision Transformer (LEViT). ViT models typically emphasize global relationship modeling, yet ReID tasks are more sensitive to local information. To address this gap, we propose a Locally Enhanced (LE) block to enhance local information by performing self-attention within local split windows. Since part-based models dominate ReID, calculating self-attention across all patches is computationally inefficient. We also replace the traditional Query-Key-Value projector with the Group Convolution (G-Conv) projector, enabling the model to capture local details more efficiently. Furthermore, G-Conv is integrated into the channel MLP to strengthen local feature sensitivity. Using these components, we develop two LEViT variants: LEViT-S and LEViT-L. To our knowledge, LEViT is the first highly adaptable ViT backbone for ReID tasks. Experimental evaluations demonstrate the effectiveness in five ReID datasets: Market1501, DukeMTMC, MSMT17, VeRi-776, and VehicleID. Notably, LEViT-S outperforms TransReID while requiring less than 10% computational complexity. Furthermore, LEViT obtains the state-of-the-art on three deep metric learning datasets: CUB-200-2011, Cars196, and University-1652. Our code will be available at https://github.com/YuhuiWang99/LEViT.
- 18 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 1820-1832
LEViT: Locally Enhanced Vision Transformer for Efficient Object Re-Identification
Vision Transformer (ViT) on object re-identification (ReID) has attracted significant attention recently. However, ViT-based ReID substantially increases computational complexity, imposing significant burdens during training and inference. This paper presents an efficient and effective ViT-based backbone for ReID tasks, called the Locally Enhanced Vision Transformer (LEViT). ViT models typically emphasize global relationship modeling, yet ReID tasks are more sensitive to local information. To address this gap, we propose a Locally Enhanced (LE) block to enhance local information by performing self-attention within local split windows. Since part-based models dominate ReID, calculating self-attention across all patches is computationally inefficient. We also replace the traditional Query-Key-Value projector with the Group Convolution (G-Conv) projector, enabling the model to capture local details more efficiently. Furthermore, G-Conv is integrated into the channel MLP to strengthen local feature sensitivity. Using these components, we develop two LEViT variants: LEViT-S and LEViT-L. To our knowledge, LEViT is the first highly adaptable ViT backbone for ReID tasks. Experimental evaluations demonstrate the effectiveness in five ReID datasets: Market1501, DukeMTMC, MSMT17, VeRi-776, and VehicleID. Notably, LEViT-S outperforms TransReID while requiring less than 10% computational complexity. Furthermore, LEViT obtains the state-of-the-art on three deep metric learning datasets: CUB-200-2011, Cars196, and University-1652. Our code will be available at https://github.com/YuhuiWang99/LEViT.
- Open Access
- 8 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
A Survey for Point Prompt of Segment Anything Model
- 8 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessA Survey for Point Prompt of Segment Anything Model