Guanwen Feng

Guanwen Feng

Auto-generated profile, based on publicly available information

Guanwen Feng

School of Computer Science and Technology, Xidian University, Xian, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 January 2024 in Knowledge-Based Systems
Verified
Journal Article
Closed access
CLChaoneng Li
Chaoneng Li
GFGuanwen Feng
Guanwen Feng
YLYunan Li
Yunan Li
RLRuyi Liu
Ruyi Liu
Qiguang MiaoQiguang Miao
Qiguang Miao
LCLiang Chang
Liang Chang

28 May 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
HYHang Yao
Hang Yao
Qiguang MiaoQiguang Miao
Qiguang Miao
PZPeipei Zhao
Peipei Zhao
CLChaoneng Li
Chaoneng Li
XLXin Li
Xin Li
Ruyi LiuRuyi Liu
Ruyi Liu
Different from large-scale classification tasks, fine-grained visual classification is a challenging task due to two critical problems: 1) evident intra-class variances and subtle inter-class differences, and 2) overfitting owing to fewer training samples in datasets. Most existing methods extract key features to reduce intra-class variances, but pay no attention to subtle inter-class differences in fine-grained visual classification. To address this issue, we propose a loss function named exploration of class center, which consists of a multiple class-center constraint and a class-center label generation. This loss function fully utilizes the information of the class center from the perspective of features and labels. From the feature perspective, the multiple class-center constraint pulls samples closer to the target class center, and pushes samples away from the most similar nontarget class center. Thus, the constraint reduces intra-class variances and enlarges inter-class differences. From the label perspective, the class-center label generation utilizes class-center distributions to generate soft labels to alleviate overfitting. Our method can be easily integrated with existing fine-grained visual classification approaches as a loss function, to further boost excellent performance with only slight training costs. Extensive experiments are conducted to demonstrate consistent improvements achieved by our method on four widely-used fine-grained visual classification datasets. In particular, our method achieves state-of-the-art performance on the FGVC-Aircraft and CUB-200-2011 datasets.

6 January 2026 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
GFGuanwen Feng
Guanwen Feng
HCHaoran Cheng
Haoran Cheng
YLYunan Li
Yunan Li
ZMZhiyuan Ma
Zhiyuan Ma
CLChaoneng Li
Chaoneng Li
Chi-Man PunChi-Man Pun
Chi-Man Pun
Implementing fine-grained emotion control is crucial for emotion generation tasks because it enhances the expressive capability of the generative model, allowing it to accurately and comprehensively capture and express various nuanced emotional states, thereby improving the emotional quality and personalization of generated content. Generating fine-grained facial animations that accurately portray emotional expressions using only a portrait and an audio recording presents a challenge. In order to address this challenge, we propose a visual attribute-guided audio decoupler. This enables the obtention of content vectors solely related to the audio content, enhancing the stability of subsequent lip movement coefficient predictions. To achieve more precise emotional expression, we introduce a fine-grained emotion coefficient prediction module. Additionally, we propose an emotion intensity control method using a fine-grained emotion matrix. Through these, effective control over emotional expression in the generated videos and finer classification of emotion intensity are accomplished. Subsequently, a series of 3DMM coefficient generation networks are designed to predict 3D coefficients, followed by the utilization of a rendering network to generate the final video. Our experimental results demonstrate that our proposed method, EmoSpeaker, outperforms existing emotional talking face generation methods in terms of expression variation and lip synchronization. Project page: https://peterfanfan.github.io/EmoSpeaker/

5 December 2025 in Knowledge-Based Systems
Verified
Journal Article
Closed access
Qiguang MiaoQiguang Miao
Qiguang Miao
GFGuanwen Feng
Guanwen Feng
JJJunwei Jing
Junwei Jing
YZYilin Zhang
Yilin Zhang
ALAn Liu
An Liu
Chi-Man PunChi-Man Pun
Chi-Man Pun

21 August 2026 in Expert Systems with Applications
Verified
Journal Article
Closed access
GFGuanwen Feng
Guanwen Feng
Qiguang MiaoQiguang Miao
Qiguang Miao
ALAn Liu
An Liu
CWChencai Wang
Chencai Wang
YLYunan Li
Yunan Li
Chi-Man PunChi-Man Pun
Chi-Man Pun

23 March 2026 in IEEE Transactions on Affective Computing
Verified
Journal Article
Closed access
GFGuanwen Feng
Guanwen Feng
ZQZhihao Qian
Zhihao Qian
YLYunan Li
Yunan Li
SJSiyu Jin
Siyu Jin
Qiguang MiaoQiguang Miao
Qiguang Miao
Chi-Man PunChi-Man Pun
Chi-Man Pun
While existing one-shot talking head generation models have achieved progress in coarse-grained emotion editing, there is still a lack of fine-grained emotion editing models with high interpretability. We argue that for an approach to be considered fine-grained, it needs to provide clear definitions and sufficiently detailed differentiation. We present LES-Talker, a novel one-shot talking head generation model with high interpretability, to achieve fine-grained emotion editing across emotion types, emotion levels, and facial units. We propose a Linear Emotion Space (LES) definition based on Facial Action Units to characterize emotion transformations as vector transformations. We design the Cross-Dimension Attention Net (CDAN) to deeply mine the correlation between LES representation and 3D model representation. Through mining multiple relationships across different feature and structure dimensions, we enable LES representation to guide the controllable deformation of 3D model. In order to adapt the multimodal data with deviations to the LES and enhance visual quality, we utilize specialized network design and training strategies. Experiments show that our method provides high visual quality along with multilevel and inter pretable fine-grained emotion editing, outperforming mainstream methods. Project page: https://peterfanfan.github.io/LES-Talker/