Jing Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jing Wang has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Jiayu Xiong
College of Computer Science and Technology, Huaqiao University, Xiamen, Fujian, China
3 shared publications Xueqing Li
Huaqiao University
3 shared publicationsJixiang Du
Huaqiao University
2 shared publications- Wanlong Wang
College of Computer Science and Technology, Huaqiao University, Xiamen, Fujian, China
2 shared publications - Bineng Zhong
Guangxi Normal University
1 shared publication - Binfei Chu
Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 10645-10653
Fast Perceptual Cross-Modal Hashing via Closed-Form Solution
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 10645-10653
Open AccessFast Perceptual Cross-Modal Hashing via Closed-Form Solution
- 20 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
Visible and Infrared Image Fusion Based on Adaptive Weighted Multimodal Features Extraction and Bidirectional Guidance Structure
Efficient fusion of infrared and visible images is of critical importance for real-time applications such as autonomous driving. While deep learning-based fusion methods have demonstrated significant improvements in fusion quality in recent years, current network architectures still exhibit unsatisfactory computational complexity and processing speed. To reduce computational complexity and improve fusion efficiency, mask-based methods or approaches driven by downstream tasks often prioritize key regions. However, such methods tend to overemphasize target objects, potentially overlooking contextually significant elements. To address this limitation and achieve more effective fusion, we propose BEFuse, a decoupled two-stage training strategy with an end-to-end inference framework. BEFuse extracts shallow features and gradient information from images in the first stage via a cross-modal image segmentation subnetwork. In the fusion stage, we use the Hadamard product to map features to an implicit quadratic feature space, combining feature similarity and gradient mask information, allowing automatic adjustment of loss weights and improving fusion accuracy. Experiments on four datasets (MSRS, TNO, RoadScene, and M3FD) show that BEFuse outperforms existing methods in both fusion quality and computational speed.
- 20 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
Visible and Infrared Image Fusion Based on Adaptive Weighted Multimodal Features Extraction and Bidirectional Guidance Structure
Efficient fusion of infrared and visible images is of critical importance for real-time applications such as autonomous driving. While deep learning-based fusion methods have demonstrated significant improvements in fusion quality in recent years, current network architectures still exhibit unsatisfactory computational complexity and processing speed. To reduce computational complexity and improve fusion efficiency, mask-based methods or approaches driven by downstream tasks often prioritize key regions. However, such methods tend to overemphasize target objects, potentially overlooking contextually significant elements. To address this limitation and achieve more effective fusion, we propose BEFuse, a decoupled two-stage training strategy with an end-to-end inference framework. BEFuse extracts shallow features and gradient information from images in the first stage via a cross-modal image segmentation subnetwork. In the fusion stage, we use the Hadamard product to map features to an implicit quadratic feature space, combining feature similarity and gradient mask information, allowing automatic adjustment of loss weights and improving fusion accuracy. Experiments on four datasets (MSRS, TNO, RoadScene, and M3FD) show that BEFuse outperforms existing methods in both fusion quality and computational speed.
- 22 January 2026
- Published by Elsevier in Pattern Recognition
- Vol. 175
Masked autoencoders for spatio-temporal audio representations: Theory and optimization
- 22 January 2026
- Published by Elsevier in Pattern Recognition
- Vol. 175
Masked autoencoders for spatio-temporal audio representations: Theory and optimization
- 21 October 2025
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 64 (5) , 1-33
Predicting residents’ travel mode choice based on MAML
- 21 October 2025
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 64 (5) , 1-33
Predicting residents’ travel mode choice based on MAML
- Open Access
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 2078-2082
Contrastive Single-Stream Spatio-Temporal Joint Modeling for Few-Shot Action Recognition
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 2078-2082
Open AccessContrastive Single-Stream Spatio-Temporal Joint Modeling for Few-Shot Action Recognition
- 19 December 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 309
Local tangent space transfer and alignment for incomplete data
- 19 December 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 309
Local tangent space transfer and alignment for incomplete data
- Open Access
- 15 April 2024
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 10 (4) , 1-16
Deep matrix factorization via feature subspace transfer for recommendation system
- 15 April 2024
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 10 (4) , 1-16
Open AccessDeep matrix factorization via feature subspace transfer for recommendation system
- 28 February 2024
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 27 (1) , 1-12
Learning discriminative local contexts for person re-identification in vehicle surveillance scenarios
- 28 February 2024
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 27 (1) , 1-12
Learning discriminative local contexts for person re-identification in vehicle surveillance scenarios
- Open Access
- 17 February 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 19 (2s) , 1-15
Robust Long-Term Tracking via Localizing Occluders
Occlusion is known as one of the most challenging factors in long-term tracking because of its unpredictable shape. Existing works devoted into the design of loss functions, training strategies or model architectures, which are considered to have not directly touched the key point. Alternatively, we came up with a direct and natural idea that is discarding things that covers the target. We propose a novel occluder-aware representation learning framework to develop this idea. First, we design a local occluders detection module (LODM) to localize the occluders, which works on the principle that discriminates the non-noumenal part from a target based on the general knowledge of this category. An extra dataset and a clustering strategy is proposed to support this general knowledge. Second, we devise a feature reconstruction module to guide the occluder-aware representation learning. With the help of above methods, our localizing occluders tracker, called LOTracker, can learn an occluder-free representation and promote the performance that tracks with occlusion scenarios. Extensive experimental results show that our LOTracker achieves a state-of-the-art performance in multiple benchmarks such as LaSOT, VOTLT2018, VOTLT2019, and OxUvALT.
- 17 February 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 19 (2s) , 1-15
Open AccessRobust Long-Term Tracking via Localizing Occluders
Occlusion is known as one of the most challenging factors in long-term tracking because of its unpredictable shape. Existing works devoted into the design of loss functions, training strategies or model architectures, which are considered to have not directly touched the key point. Alternatively, we came up with a direct and natural idea that is discarding things that covers the target. We propose a novel occluder-aware representation learning framework to develop this idea. First, we design a local occluders detection module (LODM) to localize the occluders, which works on the principle that discriminates the non-noumenal part from a target based on the general knowledge of this category. An extra dataset and a clustering strategy is proposed to support this general knowledge. Second, we devise a feature reconstruction module to guide the occluder-aware representation learning. With the help of above methods, our localizing occluders tracker, called LOTracker, can learn an occluder-free representation and promote the performance that tracks with occlusion scenarios. Extensive experimental results show that our LOTracker achieves a state-of-the-art performance in multiple benchmarks such as LaSOT, VOTLT2018, VOTLT2019, and OxUvALT.
- 31 October 2022
- Published by Springer Nature in Neural Computing and Applications
- Vol. 35 (7) , 5207-5220
A deep spatiotemporal network for forecasting the risk of traffic accidents in low-risk regions
- 31 October 2022
- Published by Springer Nature in Neural Computing and Applications
- Vol. 35 (7) , 5207-5220
A deep spatiotemporal network for forecasting the risk of traffic accidents in low-risk regions