SOTA Video-level A/H Recognition on BAH (test) and PapersWithCode

82.72MF1

Multimodal Fusion Model with Prototype Head

Updated 1mo ago

Evaluation Results

Method
Multimodal Fusion Model with Prototype Head 2026.03	82.72	83.25	-
Ensemble of Five Multimodal Fusion Models with Prototype Head 2026.03	80.77	81.89	-
Ensemble of Five Multimodal Fusion Models 2026.03	80.64	81.29	-
Multimodal Fusion Model 2026.03	79.94	82.66	-
Multimodal Fusion Model 2026.03	79.15	77.62	-
Multimodal Fusion Model 2026.03	79	80.39	-
Multimodal Fusion Model 2026.03	78.54	78.22	-
Multimodal Fusion Model 2026.03	77.66	77.51	-
Multimodal Fusion Model 2026.03	77.65	78.77	-
Multimodal Fusion Model 2026.03	77.63	78.76	-
Multimodal Fusion Model 2026.03	77.09	77.58	-
Multimodal Fusion Model 2026.03	77.03	78.91	-
Multimodal Fusion Model 2026.03	77.03	77.69	-
TF-IDF 2026.03	72.02	68.79	-
Fine-tuned EmotionDistilRoBERTa 2026.03	71.49	70.02	-
Multimodal Fusion Model 2026.03	71.44	67.4	-
Ensemble of Five Multimodal Fusion Models with Prototype Head 2026.03	71.43	-	-
Multimodal Fusion Model 2026.03	70.99	69.02	-
EmotionWav2Vec2.0 + Mamba 2026.03	70.87	69.03	-
Fine-tuned EmotionTextClassifier 2026.03	70.72	70	-
Multimodal Fusion Model 2026.03	70.41	69.25	-
Ensemble of Five Multimodal Fusion Models 2026.03	70.17	-	-
Multimodal Fusion Model 2026.03	68.32	-	-
TF-IDF 2026.03	67.75	68.03	-
Multimodal Fusion Model with Prototype Head 2026.03	65.21	-	-
VideoMAE 2026.03	62.21	61.96	-
Multimodal Fusion Model 2026.03	61.19	63.24	-
EmotionEfficientNetB0 + Statistical Features 2026.03	60.05	62.67	-
Visual AUs (XGBoost) 2026.03	-	-	56.42
Audio Wav2Vec (LSTM) 2026.03	-	-	61.41
Text BERT 2026.03	-	-	59.04
Fusion A (implicit) 2026.03	-	-	66.04
Fusion B (divergence) 2026.03	-	-	68.08
Fusion C (combined) 2026.03	-	-	67.66
Fusion B (divergence) 2026.03	-	-	66.02
Challenge baseline 2026.03	-	-	28.27