.png){kind=icon}
.png){kind=icon}
Return
Temporal–spatial cross-fusion for dynamic micro expression recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2026.113715.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Proposed a novel dual-stream framework called TSFmicro for dynamic micro-expression recognition that effectively fuses time-dependent and spatial features. • Identified a parallel temporal and spatial fusion method that captures complementary “where-how” relationships in high-dimensional feature space to provide richer semantic information for models. • Revisiting spatio-temporal feature contributions, proposing a new paradigm for multi-dimensional fusion. • Exploring multi-dimensional fusion in dynamic micro-expression recognition with spatio-temporal feature combinations.
Keywords:
micro-expression recognition
dual-stream framework
spatio-temporal fusion
temporal features
spatial features
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W