通过时序建模与跨任务融合，提升多任务情感行为分析性能。
AffectFuse: Cross-Task Feature Fusion with Temporal Modeling for Multi-Task Affective Behavior Analysis
- 冻结预训练主干网络，用任务专用时序头和融合模块提取有效特征。
- 在s-Aff-Wild2数据集上验证集得分达1.7302，优于直接迁移方法。
- 适合需要高效多任务情感识别的场景，尤其关注动作单元检测。
野外环境下的情感行为识别需同时预测连续效价-唤醒度、分类面部表情及多标签动作单元，基于未约束的面部图像完成。本文针对第11届Affective Behavior Analysis in-the-wild（ABAW）竞赛的多任务学习（MTL）赛道，采用s-Aff-Wild2（Aff-Wild2的静态帧子集）作为测试基准。方法聚焦于编码器后处理适应：使用AffectNet监督训练的冻结主干网络提供多分辨率特征，任务特异性时序头与跨任务融合模块分别筛选各任务的有效信号。对于动作单元识别，采用低秩适配（LoRA）对MAE-Face进行微调，并通过按单元专家路由机制替代直接序列迁移，利用DISFA数据集优化。通过主干、时序、融合及动作单元适配策略的消融实验，确定最终配置。系统在官方验证集上取得P = 1.7302的成绩，表明无需训练新的大规模人脸基础模型，仅通过编码器后适应与任务定制化设计即可构建强大的多任务学习流程。
原文摘要 · Abstract (English)
Affective behavior recognition in the wild requires joint prediction of continuous valence-arousal, categorical facial expression, and multi-label action units from unconstrained face images. We present our system for the Multi-Task Learning (MTL) track of the 11th Affective Behavior Analysis in-the-wild (ABAW) competition on s-Aff-Wild2, the static selected-frame version of Aff-Wild2. The method focuses on post-encoder adaptation: frozen AffectNet-supervised backbones provide multi-resolution features, while task-specific temporal heads and cross-task fusion modules select the useful signals for each target. For action-unit recognition, we adapt MAE-Face with Low-Rank Adaptation (LoRA) and use DISFA through per-unit expert routing rather than direct sequential transfer. Ablations over backbone, temporal, fusion, and AU-adaptation choices define the final configuration. The final system obtains P = 1.7302 on the official validation split, showing that post-encoder adaptation and task-wise modeling choices provide a strong MTL pipeline without training a new large-scale face foundation model.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。