Feng Tian
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Feng Tian has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Hongge Yao
School of Computer Science and Engineering, Xi’an Technological University, Xi’an 710064, China
2 shared publications - Jinyuan Jia
The Hong Kong University of Science and Technology, Guangzhou, China
2 shared publications - Anning Huang
Tongji University
1 shared publication - Atsushi Suzuki
King’s College London
1 shared publication Baolong Su
1 shared publication- Bo Yang
School of Computer Science and Engineering, Xi’an Technological University, Xi’an, China
1 shared publication
Latest Publications
- 19 March 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 174
A reinforcement learning-assisted differential evolution with population feature replay
- 19 March 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 174
A reinforcement learning-assisted differential evolution with population feature replay
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 73-82
MGGA: Universal Perturbations against Deepfake via Multiple Model-based Gradient-Guided Feature Layer Attack
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 73-82
Open AccessMGGA: Universal Perturbations against Deepfake via Multiple Model-based Gradient-Guided Feature Layer Attack
- Open Access
- 24 July 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (15) , 2370
Image Inpainting Algorithm Based on Structure-Guided Generative Adversarial Network
To address the challenges of image inpainting in scenarios with extensive or irregular missing regions—particularly detail oversmoothing, structural ambiguity, and textural incoherence—this paper proposes an Image Structure-Guided (ISG) framework that hierarchically integrates structural priors with semantic-aware texture synthesis. The proposed methodology advances a two-stage restoration paradigm: (1) Structural Prior Extraction, where adaptive edge detection algorithms identify residual contours in corrupted regions, and a transformer-enhanced network reconstructs globally consistent structural maps through contextual feature propagation; (2) Structure-Constrained Texture Synthesis, wherein a multi-scale generator with hybrid dilated convolutions and channel attention mechanisms iteratively refines high-fidelity textures under explicit structural guidance. The framework introduces three innovations: (1) a hierarchical feature fusion architecture that synergizes multi-scale receptive fields with spatial-channel attention to preserve long-range dependencies and local details simultaneously; (2) spectral-normalized Markovian discriminator with gradient-penalty regularization, enabling adversarial training stability while enforcing patch-level structural consistency; and (3) dual-branch loss formulation combining perceptual similarity metrics with edge-aware constraints to align synthesized content with both semantic coherence and geometric fidelity. Our experiments on the two benchmark datasets (Places2 and CelebA) have demonstrated that our framework achieves more unified textures and structures, bringing the restored images closer to their original semantic content.
- 24 July 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (15) , 2370
Open AccessImage Inpainting Algorithm Based on Structure-Guided Generative Adversarial Network
To address the challenges of image inpainting in scenarios with extensive or irregular missing regions—particularly detail oversmoothing, structural ambiguity, and textural incoherence—this paper proposes an Image Structure-Guided (ISG) framework that hierarchically integrates structural priors with semantic-aware texture synthesis. The proposed methodology advances a two-stage restoration paradigm: (1) Structural Prior Extraction, where adaptive edge detection algorithms identify residual contours in corrupted regions, and a transformer-enhanced network reconstructs globally consistent structural maps through contextual feature propagation; (2) Structure-Constrained Texture Synthesis, wherein a multi-scale generator with hybrid dilated convolutions and channel attention mechanisms iteratively refines high-fidelity textures under explicit structural guidance. The framework introduces three innovations: (1) a hierarchical feature fusion architecture that synergizes multi-scale receptive fields with spatial-channel attention to preserve long-range dependencies and local details simultaneously; (2) spectral-normalized Markovian discriminator with gradient-penalty regularization, enabling adversarial training stability while enforcing patch-level structural consistency; and (3) dual-branch loss formulation combining perceptual similarity metrics with edge-aware constraints to align synthesized content with both semantic coherence and geometric fidelity. Our experiments on the two benchmark datasets (Places2 and CelebA) have demonstrated that our framework achieves more unified textures and structures, bringing the restored images closer to their original semantic content.
- Open Access
- 9 June 2025
- Published by MDPI AG in Electronics
- Vol. 14 (12) , 2361
A Coordination Optimization Framework for Multi-Agent Reinforcement Learning Based on Reward Redistribution and Experience Reutilization
Cooperative multi-agent reinforcement learning (MARL) has emerged as a powerful paradigm for addressing complex real-world challenges, including autonomous robot control, strategic decision-making, and decentralized coordination in unmanned swarm systems. However, it still faces challenges in learning proper coordination among multiple agents. The lack of effective knowledge sharing and experience interaction mechanisms among agents has led to substantial performance decline, especially in terms of low sampling efficiency and slow convergence rates, ultimately constraining the practical applicability of MARL. To address these challenges, this paper proposes a novel framework termed Reward redistribution and Experience reutilization based Coordination Optimization (RECO). This innovative approach employs a hierarchical experience pool mechanism that enhances exploration through strategic reward redistribution and experience reutilization. The RECO framework incorporates a sophisticated evaluation mechanism that assesses the quality of historical sampling data from individual agents and optimizes reward distribution by maximizing mutual information across hierarchical experience trajectories. Extensive comparative analyses of computational efficiency and performance metrics across diverse environments reveal that the proposed method not only enhances training efficiency in multi-agent gaming scenarios but also significantly strengthens algorithmic robustness and stability in dynamic environments.
- 9 June 2025
- Published by MDPI AG in Electronics
- Vol. 14 (12) , 2361
Open AccessA Coordination Optimization Framework for Multi-Agent Reinforcement Learning Based on Reward Redistribution and Experience Reutilization
Cooperative multi-agent reinforcement learning (MARL) has emerged as a powerful paradigm for addressing complex real-world challenges, including autonomous robot control, strategic decision-making, and decentralized coordination in unmanned swarm systems. However, it still faces challenges in learning proper coordination among multiple agents. The lack of effective knowledge sharing and experience interaction mechanisms among agents has led to substantial performance decline, especially in terms of low sampling efficiency and slow convergence rates, ultimately constraining the practical applicability of MARL. To address these challenges, this paper proposes a novel framework termed Reward redistribution and Experience reutilization based Coordination Optimization (RECO). This innovative approach employs a hierarchical experience pool mechanism that enhances exploration through strategic reward redistribution and experience reutilization. The RECO framework incorporates a sophisticated evaluation mechanism that assesses the quality of historical sampling data from individual agents and optimizes reward distribution by maximizing mutual information across hierarchical experience trajectories. Extensive comparative analyses of computational efficiency and performance metrics across diverse environments reveal that the proposed method not only enhances training efficiency in multi-agent gaming scenarios but also significantly strengthens algorithmic robustness and stability in dynamic environments.
- Open Access
- 16 December 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (1) , 1-21
Double Reference Guided Interactive 2D and 3D Caricature Generation
In this article, we propose the first geometry and texture (double) referenced interactive two-dimensional (2D) and 3D caricature generating and editing method. The main challenge of caricature generation lies in the fact that it not only exaggerates the facial geometry but also refreshes the facial texture. We address this challenge by utilizing the semantic segmentation maps as an intermediary domain, removing the influence of photo texture while preserving the person-specific geometry features. Specifically, our proposed method consists of two main components: 3D-CariNet and CariMaskGAN. 3D-CariNet uses sketches or caricatures to exaggerate the input photo into several types of 3D caricatures. To generate a CariMask, we geometrically exaggerate the photos using the projection of exaggerated 3D landmarks, after which CariMask is converted into a caricature by CariMaskGAN. In this step, users can edit and adjust the geometry of caricatures freely. Moreover, we propose a semantic detail preprocessing approach that considerably increases the details of generated caricatures and allows modification of hair strands, wrinkles, and beards. By rendering high-quality 2D caricatures as textures, we produce 3D caricatures with a variety of texture styles. Extensive experimental results have demonstrated that our method can produce higher-quality caricatures as well as support interactive modification with ease.
- 16 December 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (1) , 1-21
Open AccessDouble Reference Guided Interactive 2D and 3D Caricature Generation
In this article, we propose the first geometry and texture (double) referenced interactive two-dimensional (2D) and 3D caricature generating and editing method. The main challenge of caricature generation lies in the fact that it not only exaggerates the facial geometry but also refreshes the facial texture. We address this challenge by utilizing the semantic segmentation maps as an intermediary domain, removing the influence of photo texture while preserving the person-specific geometry features. Specifically, our proposed method consists of two main components: 3D-CariNet and CariMaskGAN. 3D-CariNet uses sketches or caricatures to exaggerate the input photo into several types of 3D caricatures. To generate a CariMask, we geometrically exaggerate the photos using the projection of exaggerated 3D landmarks, after which CariMask is converted into a caricature by CariMaskGAN. In this step, users can edit and adjust the geometry of caricatures freely. Moreover, we propose a semantic detail preprocessing approach that considerably increases the details of generated caricatures and allows modification of hair strands, wrinkles, and beards. By rendering high-quality 2D caricatures as textures, we produce 3D caricatures with a variety of texture styles. Extensive experimental results have demonstrated that our method can produce higher-quality caricatures as well as support interactive modification with ease.
- 10 December 2024
- Published by Elsevier in Applied Soft Computing
- Vol. 169
An autonomous differential evolution based on reinforcement learning for cooperative countermeasures of unmanned aerial vehicles
- 10 December 2024
- Published by Elsevier in Applied Soft Computing
- Vol. 169
An autonomous differential evolution based on reinforcement learning for cooperative countermeasures of unmanned aerial vehicles
- Open Access
- 3 October 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (19) , 3096
Analytical C2 Continuous Surface Blending
Surface blending is an important topic in geometric modelling and is widely applied in computer-aided design and creative industries to create smooth transition surfaces. Among various surface blending methods, partial differential equation (PDE)-based surface blending has the advantages of effective shape control and exact satisfaction of blending boundary constraints. However, it is not easy to solve partial differential equations subjected to blending boundary constraints. In this paper, we investigate how to solve PDEs analytically and develop an analytical PDE-based method to achieve surface blending with continuity. Taking advantage of elementary functions identified from blending boundary constraints, our proposed method first changes blending boundary constraints into a linear combination of the identified elementary functions. Accordingly, the functions for blending surfaces are constructed from these elementary functions, which transform sixth-order partial differential equations for surface blending into sixth-order ordinary differential equations (ODEs). We investigate the analytical solutions of the transformed sixth-order ordinary differential equations subjected to corresponding blending boundary constraints. With the developed analytical PDE-based method, we solve continuous surface blending problems. The surface blending example presented in this paper indicates that the developed method is simple and easy to use. It can be used to effectively control the shape of blending surfaces and at the same time exactly satisfy continuous blending boundary constraints.- 3 October 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (19) , 3096
Open AccessAnalytical C2 Continuous Surface Blending
Surface blending is an important topic in geometric modelling and is widely applied in computer-aided design and creative industries to create smooth transition surfaces. Among various surface blending methods, partial differential equation (PDE)-based surface blending has the advantages of effective shape control and exact satisfaction of blending boundary constraints. However, it is not easy to solve partial differential equations subjected to blending boundary constraints. In this paper, we investigate how to solve PDEs analytically and develop an analytical PDE-based method to achieve surface blending with continuity. Taking advantage of elementary functions identified from blending boundary constraints, our proposed method first changes blending boundary constraints into a linear combination of the identified elementary functions. Accordingly, the functions for blending surfaces are constructed from these elementary functions, which transform sixth-order partial differential equations for surface blending into sixth-order ordinary differential equations (ODEs). We investigate the analytical solutions of the transformed sixth-order ordinary differential equations subjected to corresponding blending boundary constraints. With the developed analytical PDE-based method, we solve continuous surface blending problems. The surface blending example presented in this paper indicates that the developed method is simple and easy to use. It can be used to effectively control the shape of blending surfaces and at the same time exactly satisfy continuous blending boundary constraints. - Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (3) , 2391-2399
G2L-CariGAN: Caricature Generation from Global Structure to Local Features
Existing GAN-based approaches to caricature generation mainly focus on exaggerating a character’s global facial structure. This often leads to the failure in highlighting significant facial features such as big eyes and hook nose. To address this limitation, we propose a new approach termed as G2L-CariGAN, which uses feature maps of spatial dimensions instead of latent codes for geometric exaggeration. G2L-CariGAN first exaggerates the global facial structure of the character on a low-dimensional feature map and then exaggerates its local facial features on a high-dimensional feature map. Moreover, we develop a caricature identity loss function based on feature maps, which well retains the character's identity after exaggeration. Our experiments have demonstrated that G2L-CariGAN outperforms the state-of-arts in terms of the quality of exaggerating a character and retaining its identity.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (3) , 2391-2399
Open AccessG2L-CariGAN: Caricature Generation from Global Structure to Local Features
Existing GAN-based approaches to caricature generation mainly focus on exaggerating a character’s global facial structure. This often leads to the failure in highlighting significant facial features such as big eyes and hook nose. To address this limitation, we propose a new approach termed as G2L-CariGAN, which uses feature maps of spatial dimensions instead of latent codes for geometric exaggeration. G2L-CariGAN first exaggerates the global facial structure of the character on a low-dimensional feature map and then exaggerates its local facial features on a high-dimensional feature map. Moreover, we develop a caricature identity loss function based on feature maps, which well retains the character's identity after exaggeration. Our experiments have demonstrated that G2L-CariGAN outperforms the state-of-arts in terms of the quality of exaggerating a character and retaining its identity.
- 29 December 2023
- Published by Springer Nature
- p. 159-170
Fine-Grained Web3D Culling-Transmitting-Rendering Pipeline
- 29 December 2023
- Published by Springer Nature
- p. 159-170
Fine-Grained Web3D Culling-Transmitting-Rendering Pipeline
- 4 September 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (9) , 28197-28213
AG-YOLO: Attention-guided network for real-time object detection
- 4 September 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (9) , 28197-28213
AG-YOLO: Attention-guided network for real-time object detection