中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos

文献类型：期刊论文

作者Chen, Yin1; Li, Jia1; Shan, Shiguang2,3; Wang, Meng1; Hong, Richang1
刊名IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
出版日期2025-04-01
卷号16期号:2页码:624-638
关键词Adaptation models Videos Computational modeling Feature extraction Transformers Task analysis Face recognition Dynamic facial expression recognition emotion ambiguity model adaptation transfer learning
ISSN号1949-3045
DOI10.1109/TAFFC.2024.3453443
英文摘要Dynamic facial expression recognition (DFER) in the wild is still hindered by data limitations, e.g., insufficient quantity and diversity of pose, occlusion and illumination, as well as the inherent ambiguity of facial expressions. In contrast, static facial expression recognition (SFER) currently shows much higher performance and can benefit from more abundant high-quality training data. Moreover, the appearance features and dynamic dependencies of DFER remain largely unexplored. Recognizing the potential in leveraging SFER knowledge for DFER, we introduce a novel Static-to-Dynamic model (S2D) that leverages existing SFER knowledge and dynamic information implicitly encoded in extracted facial landmark-aware features, thereby significantly improving DFER performance. First, we build and train an image model for SFER, which incorporates a standard Vision Transformer (ViT) and Multi-View Complementary Prompters (MCPs) only. Then, we obtain our video model (i.e., S2D), for DFER, by inserting Temporal-Modeling Adapters (TMAs) into the image model. MCPs enhance facial expression features with landmark-aware features inferred by an off-the-shelf facial landmark detector. And the TMAs capture and model the relationships of dynamic changes in facial expressions, effectively extending the pre-trained image model for videos. Notably, MCPs and TMAs only increase a fraction of trainable parameters (less than +10%) to the original image model. Moreover, we present a novel Emotion-Anchors (i.e., reference samples for each emotion category) based Self-Distillation Loss to reduce the detrimental influence of ambiguous emotion labels, further enhancing our S2D. Experiments conducted on popular SFER and DFER datasets show that we have achieved a new state of the art.
资助项目National Key Research and Development Program of China[2019YFA0706203] ; National Natural Science Foundation of China[62202139] ; University Synergy Innovation Program of Anhui Province[GXXT-2022-038]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001499580000033
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/42357]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Li, Jia
作者单位1.Hefei Univ Technol, Sch Comp Sci & Informat Engn, Hefei 230601, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Chen, Yin,Li, Jia,Shan, Shiguang,et al. From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos[J]. IEEE TRANSACTIONS ON AFFECTIVE COMPUTING,2025,16(2):624-638.
APA Chen, Yin,Li, Jia,Shan, Shiguang,Wang, Meng,&Hong, Richang.(2025).From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos.IEEE TRANSACTIONS ON AFFECTIVE COMPUTING,16(2),624-638.
MLA Chen, Yin,et al."From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos".IEEE TRANSACTIONS ON AFFECTIVE COMPUTING 16.2(2025):624-638.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。