Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cui, Feng-Qi, Huang, Jinyang, Zhao, Sirui, Li, Xinyu, Yan, Xin, Jia, Ziyu, Zhou, Xiaokang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.11406
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917545581215744
author Cui, Feng-Qi
Huang, Jinyang
Zhao, Sirui
Li, Xinyu
Yan, Xin
Jia, Ziyu
Zhou, Xiaokang
author_facet Cui, Feng-Qi
Huang, Jinyang
Zhao, Sirui
Li, Xinyu
Yan, Xin
Jia, Ziyu
Zhou, Xiaokang
contents Video-based Affective Computing (VAC), vital for emotion analysis and human-computer interaction, suffers from model instability and representational degradation due to complex emotional dynamics. Since the meaning of different emotional fluctuations may differ under different emotional contexts, the core limitation is the lack of a hierarchical structural mechanism to disentangle distinct affective components, i.e., emotional bases (the long-term emotional tone), and transient fluctuations (the short-term emotional fluctuations). To address this, we propose the Low-Rank Sparse Emotion Understanding Framework (LSEF), a unified model grounded in the Low-Rank Sparse Principle, which theoretically reframes affective dynamics as a hierarchical low-rank sparse compositional process. LSEF employs three plug-and-play modules, i.e., the Stability Encoding Module (SEM) captures low-rank emotional bases; the Dynamic Decoupling Module (DDM) isolates sparse transient signals; and the Consistency Integration Module (CIM) reconstructs multi-scale stability and reactivity coherence. This framework is optimized by a Rank Aware Optimization (RAO) strategy that adaptively balances gradient smoothness and sensitivity. Extensive experiments across multiple datasets confirm that LSEF significantly enhances robustness and dynamic discrimination, which further validates the effectiveness and generality of hierarchical low-rank sparse modeling for understanding affective dynamics.
format Preprint
id arxiv_https___arxiv_org_abs_2511_11406
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust Low-Rank Sparse Framework for Video-Based Affective Computing
Cui, Feng-Qi
Huang, Jinyang
Zhao, Sirui
Li, Xinyu
Yan, Xin
Jia, Ziyu
Zhou, Xiaokang
Computer Vision and Pattern Recognition
Video-based Affective Computing (VAC), vital for emotion analysis and human-computer interaction, suffers from model instability and representational degradation due to complex emotional dynamics. Since the meaning of different emotional fluctuations may differ under different emotional contexts, the core limitation is the lack of a hierarchical structural mechanism to disentangle distinct affective components, i.e., emotional bases (the long-term emotional tone), and transient fluctuations (the short-term emotional fluctuations). To address this, we propose the Low-Rank Sparse Emotion Understanding Framework (LSEF), a unified model grounded in the Low-Rank Sparse Principle, which theoretically reframes affective dynamics as a hierarchical low-rank sparse compositional process. LSEF employs three plug-and-play modules, i.e., the Stability Encoding Module (SEM) captures low-rank emotional bases; the Dynamic Decoupling Module (DDM) isolates sparse transient signals; and the Consistency Integration Module (CIM) reconstructs multi-scale stability and reactivity coherence. This framework is optimized by a Rank Aware Optimization (RAO) strategy that adaptively balances gradient smoothness and sensitivity. Extensive experiments across multiple datasets confirm that LSEF significantly enhances robustness and dynamic discrimination, which further validates the effectiveness and generality of hierarchical low-rank sparse modeling for understanding affective dynamics.
title Robust Low-Rank Sparse Framework for Video-Based Affective Computing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.11406