Qidong Liu
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
Qidong Liu has a total of 70 co-authors. Here are the top co-authors by number of shared publications:
- Mingliang Xu
Zhengzhou University
11 shared publications - Ruisheng Zhang
Lanzhou University
4 shared publications - Xin Zhou
Nanyang Technological University
4 shared publications - Cheng Long
Nanyang technological university, Singapore, Singapore
3 shared publications - Pei Lv
School of Computer and Artificial Intelligence, ZhengZhou University, Zhengzhou, China
3 shared publications - Shuai Guo
School of Computer and Artificial Intelligence, ZhengZhou University, Zhengzhou, China
3 shared publications
Latest Publications
- 8 June 2026
- Published by Springer Nature in Science China Information Sciences
- Vol. 69 (7) , 179101
LaTac: latent tactics for robust multi-agent coordination under intermittent communication
- 8 June 2026
- Published by Springer Nature in Science China Information Sciences
- Vol. 69 (7) , 179101
LaTac: latent tactics for robust multi-agent coordination under intermittent communication
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 14866-14878
HPBAFormer: Enhancing 3D Point Cloud Analysis With Hybrid Pooling Set Abstraction and Bypass Cross-Attention Learning
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 14866-14878
HPBAFormer: Enhancing 3D Point Cloud Analysis With Hybrid Pooling Set Abstraction and Bypass Cross-Attention Learning
- 5 November 2025
- Published by Elsevier in Neural Networks
- Vol. 195, 108276
Improving large models with small models: Lower costs and better performance
- 5 November 2025
- Published by Elsevier in Neural Networks
- Vol. 195, 108276
Improving large models with small models: Lower costs and better performance
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1845-1856
Enhancing Generalization in Large-Scale HCVRP: A Rank-Augmented Neural Solver
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1845-1856
Open AccessEnhancing Generalization in Large-Scale HCVRP: A Rank-Augmented Neural Solver
- 3 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (7) , 6561-6574
Adversarial Diffusion Network for Dunhuang Mural Inpainting
Dunhuang mural inpainting aims to fill in the missing regions of damaged murals with realistic content. Denoising probabilistic diffusion model (DDPM) has made great strides in semantic generation and shown promising results in image inpainting. However, three potential challenges prevent existing diffusion-based methods from restoring the Dunhuang murals: 1) effective visual information cannot be accurately extracted due to historical reasons, with most of the pixels being faded; 2) there are semantic discrepancy between damaged and visible regions in the inpainting results; and 3) the original structure and style of the damaged regions cannot be adequately restored. To this end, we propose a novel adversarial diffusion model for mural inpainting, which consists of: 1) a mural enhancement module named pixel-enhanced fire-controlled pulse-coupled neural network (PEFCPCNN), designed to enhance faded pixels to accurately extract the visual features of the mural; 2) a novel adversarial diffusion framework that optimizes the sampling prediction of mural over time steps; and 3) line drawing and different loss functions to constrain the reconstructed content to approximate the structure and style of original mural. The variational transform layer (VTL) and multi-scale contextual feature aggregation (MCFA) module are proposed to reconstruct content that is structurally coherent and texturally reasonable. Experiments on the Dunhuang mural dataset demonstrate that the proposed method outperforms state-of-the-art methods in terms of both the semantic reasonableness and global semantic consistency of inpainting content.
- 3 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (7) , 6561-6574
Adversarial Diffusion Network for Dunhuang Mural Inpainting
Dunhuang mural inpainting aims to fill in the missing regions of damaged murals with realistic content. Denoising probabilistic diffusion model (DDPM) has made great strides in semantic generation and shown promising results in image inpainting. However, three potential challenges prevent existing diffusion-based methods from restoring the Dunhuang murals: 1) effective visual information cannot be accurately extracted due to historical reasons, with most of the pixels being faded; 2) there are semantic discrepancy between damaged and visible regions in the inpainting results; and 3) the original structure and style of the damaged regions cannot be adequately restored. To this end, we propose a novel adversarial diffusion model for mural inpainting, which consists of: 1) a mural enhancement module named pixel-enhanced fire-controlled pulse-coupled neural network (PEFCPCNN), designed to enhance faded pixels to accurately extract the visual features of the mural; 2) a novel adversarial diffusion framework that optimizes the sampling prediction of mural over time steps; and 3) line drawing and different loss functions to constrain the reconstructed content to approximate the structure and style of original mural. The variational transform layer (VTL) and multi-scale contextual feature aggregation (MCFA) module are proposed to reconstruct content that is structurally coherent and texturally reasonable. Experiments on the Dunhuang mural dataset demonstrate that the proposed method outperforms state-of-the-art methods in terms of both the semantic reasonableness and global semantic consistency of inpainting content.
- 18 January 2025
- Published by Elsevier in Pattern Recognition
- Vol. 162
LCASAFormer: Cross-attention enhanced backbone network for 3D point cloud tasks
- 18 January 2025
- Published by Elsevier in Pattern Recognition
- Vol. 162
LCASAFormer: Cross-attention enhanced backbone network for 3D point cloud tasks
- 20 August 2024
- Published by Springer Nature
- p. 360-374
Solving Traveling Salesman Problem with Deep Reinforcement Learning and Knowledge Distillation
- 20 August 2024
- Published by Springer Nature
- p. 360-374
Solving Traveling Salesman Problem with Deep Reinforcement Learning and Knowledge Distillation
- 4 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 1003-1017
An Efficient Ungrouped Mask Method With two Learnable Parameters for 3D Object Detection
In 3D point cloud-based object detection, attention mechanism in Group-Free [1] learns direct relationships between proposals and all seed points, providing each proposal with a global context in the form of a cross-attention map. However, our analysis and experimental comparison show that the attention mechanism assigns inappropriately large attention weights to certain seed points far from a proposal, which is not conducive to detecting objects correctly. In this work, we alleviate the above problem by proposing a mask method. For an initial proposal, our method first calculates a spatial distance-based mask, which measures the spatial relationship between all seed points and the proposal. Then, we fuse the mask into cross-attention layers in stacked attention modules and get a refined cross-attention map. In essence, our mask gives each proposal a local context; after it is fused with the global context given by the attention mechanism, the refined cross-attention map could suppress the negative impact of some distant seed points on a proposal. We present two alternative strategies to compute the mask, a hard mask, and a soft mask. Experimental results demonstrate that the soft mask brings better performance. In the soft mask, for each initial proposal's 3D-box shape, we use a parametric approximate ellipsoid as the basis of the mask's calculation, which has only two learnable parameters. Experimental results show our work could outperform Group-Free 0.7 mAP@0.25 at the cost of increasing inference time by less than 1%. The performance of our algorithm on the public dataset SUN RGB-D is 63.7 mAP@0.25 and 45.5 mAP@0.5, which is the best performance among algorithms that preserve the irregular of seed points.
- 4 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 1003-1017
An Efficient Ungrouped Mask Method With two Learnable Parameters for 3D Object Detection
In 3D point cloud-based object detection, attention mechanism in Group-Free [1] learns direct relationships between proposals and all seed points, providing each proposal with a global context in the form of a cross-attention map. However, our analysis and experimental comparison show that the attention mechanism assigns inappropriately large attention weights to certain seed points far from a proposal, which is not conducive to detecting objects correctly. In this work, we alleviate the above problem by proposing a mask method. For an initial proposal, our method first calculates a spatial distance-based mask, which measures the spatial relationship between all seed points and the proposal. Then, we fuse the mask into cross-attention layers in stacked attention modules and get a refined cross-attention map. In essence, our mask gives each proposal a local context; after it is fused with the global context given by the attention mechanism, the refined cross-attention map could suppress the negative impact of some distant seed points on a proposal. We present two alternative strategies to compute the mask, a hard mask, and a soft mask. Experimental results demonstrate that the soft mask brings better performance. In the soft mask, for each initial proposal's 3D-box shape, we use a parametric approximate ellipsoid as the basis of the mask's calculation, which has only two learnable parameters. Experimental results show our work could outperform Group-Free 0.7 mAP@0.25 at the cost of increasing inference time by less than 1%. The performance of our algorithm on the public dataset SUN RGB-D is 63.7 mAP@0.25 and 45.5 mAP@0.5, which is the best performance among algorithms that preserve the irregular of seed points.
- 2 March 2023
- Published by Springer Nature
- p. 155-171
Focal and Global Spatial-Temporal Transformer for Skeleton-Based Action Recognition
- 2 March 2023
- Published by Springer Nature
- p. 155-171
Focal and Global Spatial-Temporal Transformer for Skeleton-Based Action Recognition
- 1 December 2022
- Published by Elsevier in Pattern Recognition Letters
- Vol. 165, 77-83
A novel ensemble model with two-stage learning for joint dialog act recognition and sentiment classification
- 1 December 2022
- Published by Elsevier in Pattern Recognition Letters
- Vol. 165, 77-83
A novel ensemble model with two-stage learning for joint dialog act recognition and sentiment classification