HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Facial Action Unit Detection On Bp4D

평가 지표

Average F1

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Average F1	Paper Title	Repository
ResNet 50	59.1	Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition
AUFormer	66.2	AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors
Multi-dimensional Edge Feature-based AU Relation Graph (Swin-B)	65.5	Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition
FMAE	66.6	Representation Learning and Identity Adversarial Training for Facial Behavior Understanding
JAA-Net	60.0	Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignment
Norface	69.3	Norface: Improving Facial Expression Analysis by Identity Normalization
Multi-View Dynamic Facial Action Unit Detection	63.0	Multi-View Dynamic Facial Action Unit Detection
Multi-dimensional Edge Feature-based AU Relation Graph (ResNet 50)	64.7	Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition
FMAE-IAT	67.1	Representation Learning and Identity Adversarial Training for Facial Behavior Understanding
Multi-scale Promoted Self-adjusting Correlation Learning for Facial Action Unit Detection	65.6	Multi-scale Promoted Self-adjusting Correlation Learning for Facial Action Unit Detection
Swin-B	62.6	Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition
MDHRD	66.6	Multi-scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition
DRML	48.3	Deep Region and Multi-Label Learning for Facial Action Unit Detection	-

0 of 13 row(s) selected.