Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions
Skeleton-based emotion recognition from body motion remains challenging because emotional expressions are often characterized by subtle dynamic and relational motion cues, and hard labels may not fully capture ambiguity among related emotion categories. For the DIEM-A task in the MMAC ACII 2026 Challenge, we propose a multi-branch skeleton-based emotion recognition framework that combines a 6D rotation-based branch, a part-aware kinetic multi-stream branch, and a metadata-conditioned weak label distribution learning (LDL) branch. The branches are trained independently and fused by a probabilit
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “Learning Emotion from Motion: Kinetic Multi-Stream Skeleton ” ≈ “aymericdamien/TopDeepLearning””
- LinkedLinked via arxiv author · 85%Sosuke Suzuki →
“Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions”
- LinkedLinked via arxiv author · 85%Yijin Wei →
“Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions”
- LinkedLinked via arxiv author · 85%Koichiro Kamide →
“Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions”
- LinkedLinked via arxiv author · 85%Ran Dong →
“Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions”
- LinkedLinked via arxiv author · 85%Haoran Xie →
“Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions”
- LinkedLinked via arxiv author · 85%Chao Zhang →
“Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions”