Disagreement Matters: Exploring Internal Diversification for Redundant Attention in Generic Facial Action Analysis

计算机科学 面部表情 人工智能 情感计算 模式 多元化(营销策略) 机器学习 社会科学 营销 社会学 业务
作者
Xiaotian Li,Zheng Zhang,Xiang Zhang,Taoyue Wang,Zhihua Li,Huiyuan Yang,Umur Aybars Çiftçi,Qiang Ji,Jeffrey F. Cohn,Lijun Yin
出处
期刊:IEEE Transactions on Affective Computing [Institute of Electrical and Electronics Engineers]
卷期号:: 1-12 被引量:5
标识
DOI:10.1109/taffc.2023.3286838
摘要

This paper demonstrates the effectiveness of a diversification mechanism for building a more robust multi-attention system in generic facial action analysis. While previous multi-attention (e.g., visual attention and self-attention) research on facial expression recognition (FER) and Action Unit (AU) detection have been thoroughly studied to focus on ”external attention diversification”, where attention branches localize different facial areas, we delve into the realm of ”internal attention diversification” and explore the impact of diverse attention patterns within the same Region of Interest (RoI). Our experiments reveal that variability in attention patterns significantly impacts model performance, indicating that unconstrained multi-attention plagued by redundancy and over-parameterization, leading to sub-optimal results. To tackle this issue, we propose a compact module that guides the model to achieve self-diversified multi-attention. Our method is applied to both CNN-based and Transformer-based models, benchmarked on popular databases such as BP4D and DISFA for AU detection, as well as CK+, MMI, BU-3DFE, and BP4D+ for facial expression recognition. We also evaluate the mechanism on Self-attention and Channel-wise attention designs for improving their adaptive capabilities in multi-modal feature fusion tasks. The multi-modal evaluation is conducted on BP4D, BP4D+, and our newly developed large-scale comprehensive emotion database BP4D++, which contains well-synchronized and aligned sensor modalities, addressing the scarcity of annotations and identities in human affective computing. We plan to release the new database to the research community, fostering further advancements in this field.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
微笑芷蕾发布了新的文献求助30
1秒前
1秒前
Shrine发布了新的文献求助10
1秒前
cxy完成签到,获得积分10
2秒前
3秒前
3秒前
田様应助旧梦采纳,获得10
4秒前
mx发布了新的文献求助10
5秒前
寒天抒完成签到 ,获得积分10
6秒前
6秒前
QQ发布了新的文献求助10
7秒前
无情心情完成签到,获得积分10
8秒前
无情心情发布了新的文献求助10
10秒前
老大蒂亚戈应助潇湘雪月采纳,获得10
11秒前
打我呀发布了新的文献求助30
11秒前
12秒前
所所应助科研通管家采纳,获得10
12秒前
汉堡包应助科研通管家采纳,获得10
13秒前
MchemG应助科研通管家采纳,获得10
13秒前
YamDaamCaa应助科研通管家采纳,获得30
13秒前
852应助科研通管家采纳,获得10
13秒前
大模型应助科研通管家采纳,获得30
13秒前
MchemG应助科研通管家采纳,获得10
13秒前
完美世界应助科研通管家采纳,获得30
13秒前
情怀应助科研通管家采纳,获得10
13秒前
科研通AI5应助科研通管家采纳,获得10
13秒前
隐形曼青应助科研通管家采纳,获得10
13秒前
MchemG应助科研通管家采纳,获得10
13秒前
13秒前
李爱国应助深情的雁露采纳,获得10
13秒前
14秒前
盘尼西林发布了新的文献求助10
19秒前
幸福大白发布了新的文献求助10
19秒前
希望天下0贩的0应助李李采纳,获得10
20秒前
QQ完成签到,获得积分20
20秒前
20秒前
BiuBiu怪完成签到,获得积分10
22秒前
Dellamoffy完成签到,获得积分10
22秒前
23秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989406
求助须知:如何正确求助?哪些是违规求助? 3531522
关于积分的说明 11254187
捐赠科研通 3270174
什么是DOI,文献DOI怎么找? 1804901
邀请新用户注册赠送积分活动 882105
科研通“疑难数据库(出版商)”最低求助积分说明 809174