Rudong An

Rudong An

Auto-generated profile, based on publicly available information

Rudong An

NetEase, Hangzhou, 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
19 February 2024 in IEEE Transactions on Affective Computing
Verified
Journal Article
Closed access
BMBowen Ma
Bowen Ma
RARudong An
Rudong An
WZWei Zhang
Wei Zhang
YDYu Ding
Yu Ding
ZZZeng Zhao
Zeng Zhao
ZHZhipeng Hu
Zhipeng Hu
As a fine-grained and local expression behavior measurement, facial action unit (FAU) analysis (e.g., detection and intensity estimation) has been documented for its time-consuming, labor-intensive, and error-prone annotation. Thus a long-standing challenge of FAU analysis arises from the data scarcity of manual annotations, limiting the generalization ability of trained models to a large extent. Amounts of previous works have made efforts to alleviate this issue via semi/weakly supervised methods and extra auxiliary information. However, these methods still require domain knowledge and have not yet avoided the high dependency on data annotation. This paper introduces a robust facial representation model MAE-Face for AU analysis. Using masked autoencoding as the self-supervised pre-training approach, MAE-Face first learns a high-capacity model from a feasible collection of face images without additional data annotations. Then after being fine-tuned on AU datasets, MAE-Face exhibits convincing performance for both AU detection and AU intensity estimation, achieving a new state-of-the-art on nearly all the evaluation results. Further investigation shows that MAE-Face achieves decent performance even when fine-tuned on only 1% of the AU training set, strongly proving its robustness and generalization performance. The pre-trained model is available at GitHub repository.

27 November 2024
Verified
Book Chapter
Closed access
PDF file
HLHanwei Liu
Hanwei Liu
RARudong An
Rudong An
ZZZhimeng Zhang
Zhimeng Zhang
BMBowen Ma
Bowen Ma
WZWei Zhang
Wei Zhang
YDYu Ding
Yu Ding

3 December 2024
Verified
Conference Paper
Open access
FQfeng qiu
feng qiu
WZWei Zhang
Wei Zhang
CLChen Liu
Chen Liu
RARudong An
Rudong An
LLLincheng Li
Lincheng Li
XYXin Yu
Xin Yu

22 July 2024 in arXiv
Verified
Preprint
Open access
PDF file
HLHanwei Liu
Hanwei Liu
RARudong An
Rudong An
ZZZhimeng Zhang
Zhimeng Zhang
BMBowen Ma
Bowen Ma
WZWei Zhang
Wei Zhang
YDYu Ding
Yu Ding
Facial Expression Analysis remains a challenging task due to unexpected task-irrelevant noise, such as identity, head pose, and background. To address this issue, this paper proposes a novel framework, called Norface, that is unified for both Action Unit (AU) analysis and Facial Emotion Recognition (FER) tasks. Norface consists of a normalization network and a classification network. First, the carefully designed normalization network struggles to directly remove the above task-irrelevant noise, by maintaining facial expression consistency but normalizing all original images to a common identity with consistent pose, and background. Then, these additional normalized images are fed into the classification network. Due to consistent identity and other factors (e.g. head pose, background, etc.), the normalized images enable the classification network to extract useful expression information more effectively. Additionally, the classification network incorporates a Mixture of Experts to refine the latent representation, including handling the input of facial representations and the output of multiple (AU or emotion) labels. Extensive experiments validate the carefully designed framework with the insight of identity normalization. The proposed method outperforms existing SOTA methods in multiple facial expression analysis tasks, including AU detection, AU intensity estimation, and FER tasks, as well as their cross-dataset tasks. For the normalized datasets and code please visit {https://norface-fea.github.io/}.