HyperAI초신경

Multimodal Sentiment Analysis On Cmu Mosei 1

평가 지표

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
SeMUL-PCD	88.62	Multi-label Emotion Analysis in Conversation via Multimodal Knowledge Distillation
MMML	88.22	Multimodal Multi-loss Fusion Network for Sentiment Analysis
UniMSE	87.50	UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition
SPECTRA	87.34	Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
Transformer-based joint-encoding	82.48	A Transformer-based joint-encoding for Emotion Recognition and Sentiment Analysis
Modulated-fusion transformer	82.45	Modulated Fusion using Transformer for Linguistic-Acoustic Emotion Recognition
MMLatch	82.4	MMLatch: Bottom-up Top-down Fusion for Multimodal Sentiment Analysis
Multilogue-Net	82.10	Multilogue-Net: A Context Aware RNN for Multi-modal Emotion Detection and Sentiment Analysis in Conversation
Proposed: B2 + B4 w/ multimodal fusion	81.14	Gated Mechanism for Attention Based Multimodal Sentiment Analysis
CAE-LR	78	Unsupervised Multimodal Language Representations using Convolutional Autoencoders
Graph-MFN	76.9	Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph
MARLIN (ViT-L)	74.83	MARLIN: Masked Autoencoder for facial video Representation LearnINg
MARLIN (ViT-B)	73.7	MARLIN: Masked Autoencoder for facial video Representation LearnINg
MARLIN (ViT-S)	72.69	MARLIN: Masked Autoencoder for facial video Representation LearnINg
ALMT	-	Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis

0 of 15 row(s) selected.