Kangli Zeng
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
Kangli Zeng has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Zhongyuan Wang
School of Geomatics Science and Technology, Nanjing Tech University, Nanjing, China
6 shared publications - Jianyu Chen
National Engineering Research Center for Multimedia Software, Wuhan University, Whuan, China
4 shared publications - Tao Lu
Hubei Key Laboratory of Intelligent Robot, School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan 430205, China
4 shared publications Jianyu Chen
3 shared publicationsZhen Han
NERCMS, School of Computer Science, Wuhan University, Wuhan, China
3 shared publications- Zheng He
Wuhan University
3 shared publications
Latest Publications
- 3 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 1866-1870
MSAW-Net: Dual-Path Fusion Network With Multi-Scale Spatiotemporal Attention Weighting for Human Action Recognition
Human action recognition methods based on multimodal channels, especially the strategy combining RGB and skeleton information, have achieved remarkable success. However, the existing action recognition methods still face challenges in terms of insufficient multimodal fusion, imperfect multi-scale modeling, and inadequate preservation of spatial information. This paper proposes an innovative framework: by combining early bidirectional lateral connections with late fusion, deep interaction between modalities and complementarity at the prediction layer are achieved; the Multi-scale Spatiotemporal Attention Weighting (MSAW) mechanism is designed to adaptively fuse spatiotemporal features across different scales, selecting key frames in spatiotemporal sequences; the Pixel Sub-sampling Downsampling (PSD) module is proposed, which effectively retains spatial details during the strong downsampling process. A large number of experiments on the NTU RGB+D 60, NTU RGB+D 120, and Kinetics-400 datasets verified the effectiveness of the proposed method. The results show that our method demonstrates stronger competitiveness compared with the current state-of-the-art (SOTA) methods. Our code is available at: https://github.com/course-prog/MASW
- 3 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 1866-1870
MSAW-Net: Dual-Path Fusion Network With Multi-Scale Spatiotemporal Attention Weighting for Human Action Recognition
Human action recognition methods based on multimodal channels, especially the strategy combining RGB and skeleton information, have achieved remarkable success. However, the existing action recognition methods still face challenges in terms of insufficient multimodal fusion, imperfect multi-scale modeling, and inadequate preservation of spatial information. This paper proposes an innovative framework: by combining early bidirectional lateral connections with late fusion, deep interaction between modalities and complementarity at the prediction layer are achieved; the Multi-scale Spatiotemporal Attention Weighting (MSAW) mechanism is designed to adaptively fuse spatiotemporal features across different scales, selecting key frames in spatiotemporal sequences; the Pixel Sub-sampling Downsampling (PSD) module is proposed, which effectively retains spatial details during the strong downsampling process. A large number of experiments on the NTU RGB+D 60, NTU RGB+D 120, and Kinetics-400 datasets verified the effectiveness of the proposed method. The results show that our method demonstrates stronger competitiveness compared with the current state-of-the-art (SOTA) methods. Our code is available at: https://github.com/course-prog/MASW
- 26 March 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 320
An angle-guided bidirectional feature transformation network for multi-frame tilt-angle face recognition
- 26 March 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 320
An angle-guided bidirectional feature transformation network for multi-frame tilt-angle face recognition
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19, 23695-23707
Frequency-Aware Prompt Learning for Remote Sensing Image Super-Resolution
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19, 23695-23707
Open AccessFrequency-Aware Prompt Learning for Remote Sensing Image Super-Resolution
- Top Cited Papers
- 21 January 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (5) , 1-13
CrowdFPN: crowd counting via scale-enhanced and location-aware feature pyramid network
- 21 January 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (5) , 1-13
Top Cited PapersCrowdFPN: crowd counting via scale-enhanced and location-aware feature pyramid network
- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34, 1726-1736
Multi-Stage Statistical Texture-Guided GAN for Tilted Face Frontalization
Existing pose-invariant face recognition mainly focuses on frontal or profile, whereas high-pitch angle face recognition, prevalent under surveillance videos, has yet to be investigated. More importantly, tilted faces significantly differ from frontal or profile faces in the potential feature space due to self-occlusion, thus seriously affecting key feature extraction for face recognition. In this paper, we asymptotically reshape challenging high-pitch angle faces into a series of small-angle approximate frontal faces and exploit a statistical approach to learn texture features to ensure accurate facial component generation. In particular, we design a statistical texture-guided GAN for tilted face frontalization (STG-GAN) consisting of three main components. First, the face encoder extracts shallow features, followed by the face statistical texture modeling module that learns multi-scale face texture features based on the statistical distributions of the shallow features. Then, the face decoder performs feature deformation guided by the face statistical texture features while highlighting the pose-invariant face discriminative information. With the addition of multi-scale content loss, identity loss and adversarial loss, we further develop a pose contrastive loss of potential spatial features to constrain pose consistency and make its face frontalization process more reliable. On this basis, we propose a divide-and-conquer strategy, using STG-GAN to progressively synthesize faces with small pitch angles in multiple stages to achieve frontalization gradually. A unified end-to-end training across multiple stages facilitates the generation of numerous intermediate results to achieve a reasonable approximation of the ground truth. Extensive qualitative and quantitative experiments on multiple-face datasets demonstrate the superiority of our approach.
- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34, 1726-1736
Multi-Stage Statistical Texture-Guided GAN for Tilted Face Frontalization
Existing pose-invariant face recognition mainly focuses on frontal or profile, whereas high-pitch angle face recognition, prevalent under surveillance videos, has yet to be investigated. More importantly, tilted faces significantly differ from frontal or profile faces in the potential feature space due to self-occlusion, thus seriously affecting key feature extraction for face recognition. In this paper, we asymptotically reshape challenging high-pitch angle faces into a series of small-angle approximate frontal faces and exploit a statistical approach to learn texture features to ensure accurate facial component generation. In particular, we design a statistical texture-guided GAN for tilted face frontalization (STG-GAN) consisting of three main components. First, the face encoder extracts shallow features, followed by the face statistical texture modeling module that learns multi-scale face texture features based on the statistical distributions of the shallow features. Then, the face decoder performs feature deformation guided by the face statistical texture features while highlighting the pose-invariant face discriminative information. With the addition of multi-scale content loss, identity loss and adversarial loss, we further develop a pose contrastive loss of potential spatial features to constrain pose consistency and make its face frontalization process more reliable. On this basis, we propose a divide-and-conquer strategy, using STG-GAN to progressively synthesize faces with small pitch angles in multiple stages to achieve frontalization gradually. A unified end-to-end training across multiple stages facilitates the generation of numerous intermediate results to achieve a reasonable approximation of the ground truth. Extensive qualitative and quantitative experiments on multiple-face datasets demonstrate the superiority of our approach.
- 19 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 6 (2) , 182-194
Implicit Mutual Learning With Dual-Branch Networks for Face Super-Resolution
Face super-resolution (SR) algorithms have recently made significant progress. However, most existing methods prefer to employ texture and structure information together to promote the generation of high-resolution features, neglecting the mutual encouragement between them, as well as the effective unification of their own low-level and high-level information, thus yielding unsatisfactory results. To address these problems, we propose an implicit mutual learning of dual-branch networks for face super-resolution, which adequately considers both extraction and aggregation of structure and texture information. The proposed approach consists of four essential blocks. First, the deep feature extractor is equipped with a deep feature reinforcement module (DFRM) based on two-stage cross-dimensional attention (TCA), which behaves in the texture enhancement and structure reconstruction branches, respectively. Then, we elaborate two information exchange blocks for two branches, one for the first information exchange block (FIEB) from the texture branch to the structure branch and one for the second information exchange block (SIEB) from the structure branch to the texture branch. These two interaction blocks perform further fusion enhancement of potential features. Finally, a hybrid fusion network (HFNet) based on supervised attention executes adaptive aggregation of the enhanced texture and structure maps. Additionally, we use a joint loss function that modifies the recovery of structure information, diminishes the use of potentially erroneous information, and encourages the generation of realistic face images. Experiments on public datasets show that our method consistently achieves better quantitative and qualitative results than SOTA methods.
- 19 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 6 (2) , 182-194
Implicit Mutual Learning With Dual-Branch Networks for Face Super-Resolution
Face super-resolution (SR) algorithms have recently made significant progress. However, most existing methods prefer to employ texture and structure information together to promote the generation of high-resolution features, neglecting the mutual encouragement between them, as well as the effective unification of their own low-level and high-level information, thus yielding unsatisfactory results. To address these problems, we propose an implicit mutual learning of dual-branch networks for face super-resolution, which adequately considers both extraction and aggregation of structure and texture information. The proposed approach consists of four essential blocks. First, the deep feature extractor is equipped with a deep feature reinforcement module (DFRM) based on two-stage cross-dimensional attention (TCA), which behaves in the texture enhancement and structure reconstruction branches, respectively. Then, we elaborate two information exchange blocks for two branches, one for the first information exchange block (FIEB) from the texture branch to the structure branch and one for the second information exchange block (SIEB) from the structure branch to the texture branch. These two interaction blocks perform further fusion enhancement of potential features. Finally, a hybrid fusion network (HFNet) based on supervised attention executes adaptive aggregation of the enhanced texture and structure maps. Additionally, we use a joint loss function that modifies the recovery of structure information, diminishes the use of potentially erroneous information, and encourages the generation of realistic face images. Experiments on public datasets show that our method consistently achieves better quantitative and qualitative results than SOTA methods.
- 24 October 2023
- Published by Elsevier in Pattern Recognition Letters
- Vol. 176, 1-6
Implicit space pose consistent transfer network for deep face verification
- 24 October 2023
- Published by Elsevier in Pattern Recognition Letters
- Vol. 176, 1-6
Implicit space pose consistent transfer network for deep face verification
- Open Access
- 1 September 2023
- Published by Taylor & Francis in International Journal of Digital Earth
- Vol. 16 (1) , 3560-3579
A lightweight distillation CNN-transformer architecture for remote sensing image super-resolution
- 1 September 2023
- Published by Taylor & Francis in International Journal of Digital Earth
- Vol. 16 (1) , 3560-3579
Open AccessA lightweight distillation CNN-transformer architecture for remote sensing image super-resolution
- 14 January 2023
- Published by Elsevier in Neural Networks
- Vol. 160, 164-174
Self-attention learning network for face super-resolution
- 14 January 2023
- Published by Elsevier in Neural Networks
- Vol. 160, 164-174
Self-attention learning network for face super-resolution
- 11 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 4 (4) , 582-595
Gait Pyramid Attention Network: Toward Silhouette Semantic Relation Learning for Gait Recognition
Gait recognition refers to video-based biometric techniques for recognizing subjects by walking patterns under a long-distance situation. Despite the progress of existing gait recognition methods, the recognition ability of subjects in carrying situations is still limited (e.g., carrying bags or wearing coats or jackets). To address this issue, this paper proposes to extract human gait information from different ranges of receptive fields, providing richer internal features of the deep network. Moreover, we propose two attention mechanisms, Local Pyramid Attention and Global Attention Fusion Learning, to focus on the key features in human gait from different perspectives. Depending on the different attention mechanisms employed in the network, three network variants are derived, where the Gait Pyramid Attention Network (GPAN) contains two attention mechanisms, while GPAN-P and GPAN-L contain a single attention mechanism. We evaluated our method on two large datasets, CASIA-B and OUMVLP. Experiments show that the proposed network gives an average rank-1 accuracy of 97.8% on CASIA-B under normal walking conditions. We also achieve 94.2% and 81.8% accuracy on CASIA-B dataset under the complex bag-walking and coat-walking scenarios, which are dramatically superior to the state-of-the-art methods.
- 11 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 4 (4) , 582-595
Gait Pyramid Attention Network: Toward Silhouette Semantic Relation Learning for Gait Recognition
Gait recognition refers to video-based biometric techniques for recognizing subjects by walking patterns under a long-distance situation. Despite the progress of existing gait recognition methods, the recognition ability of subjects in carrying situations is still limited (e.g., carrying bags or wearing coats or jackets). To address this issue, this paper proposes to extract human gait information from different ranges of receptive fields, providing richer internal features of the deep network. Moreover, we propose two attention mechanisms, Local Pyramid Attention and Global Attention Fusion Learning, to focus on the key features in human gait from different perspectives. Depending on the different attention mechanisms employed in the network, three network variants are derived, where the Gait Pyramid Attention Network (GPAN) contains two attention mechanisms, while GPAN-P and GPAN-L contain a single attention mechanism. We evaluated our method on two large datasets, CASIA-B and OUMVLP. Experiments show that the proposed network gives an average rank-1 accuracy of 97.8% on CASIA-B under normal walking conditions. We also achieve 94.2% and 81.8% accuracy on CASIA-B dataset under the complex bag-walking and coat-walking scenarios, which are dramatically superior to the state-of-the-art methods.