Sentiment Analysis on CMU-MOSEI

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	SeMUL-PCD	88.62	No	-	-	-
2	MMML	88.22	No	Multimodal Multi-loss Fusion Network for Sentime...	2023-08-01	Code
3	UniMSE	87.5	Yes	UniMSE: Towards Unified Multimodal Sentiment Ana...	2022-11-21	Code
4	SPECTRA	87.34	No	Speech-Text Dialog Pre-training for Spoken Dialo...	2023-05-19	Code
5	Transformer-based joint-encoding	82.48	Yes	A Transformer-based joint-encoding for Emotion R...	2020-06-29	Code
6	Modulated-fusion transformer	82.45	Yes	Modulated Fusion using Transformer for Linguisti...	2020-10-05	Code
7	MMLatch	82.4	Yes	MMLatch: Bottom-up Top-down Fusion for Multimoda...	2022-01-24	Code
8	Multilogue-Net	82.1	Yes	Multilogue-Net: A Context Aware RNN for Multi-mo...	2020-02-19	Code
9	Proposed: B2 + B4 w/ multimodal fusion	81.14	Yes	Gated Mechanism for Attention Based Multimodal S...	2020-02-21	-
10	CAE-LR	78	Yes	Unsupervised Multimodal Language Representations...	2021-10-06	-
11	Graph-MFN	76.9	Yes	-	-	-
12	MARLIN (ViT-L)	74.83	No	MARLIN: Masked Autoencoder for facial video Repr...	2022-11-12	Code
13	MARLIN (ViT-B)	73.7	No	MARLIN: Masked Autoencoder for facial video Repr...	2022-11-12	Code
14	MARLIN (ViT-S)	72.69	No	MARLIN: Masked Autoencoder for facial video Repr...	2022-11-12	Code

#1SeMUL-PCD
88.62
Accuracy
No paper
#2MMMLSOTA
88.22
Accuracy· 2023-08-01
Multimodal Multi-loss Fusion Network for Sentiment Analysis Code
#3UniMSESOTA
87.5
Accuracy· Extra Data· 2022-11-21
UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition Code
#4SPECTRA
87.34
Accuracy· 2023-05-19
Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment Code
#5Transformer-based joint-encodingSOTA
82.48
Accuracy· Extra Data· 2020-06-29
A Transformer-based joint-encoding for Emotion Recognition and Sentiment Analysis Code
#6Modulated-fusion transformer
82.45
Accuracy· Extra Data· 2020-10-05
Modulated Fusion using Transformer for Linguistic-Acoustic Emotion Recognition Code
#7MMLatch
82.4
Accuracy· Extra Data· 2022-01-24
MMLatch: Bottom-up Top-down Fusion for Multimodal Sentiment Analysis Code
#8Multilogue-NetSOTA
82.1
Accuracy· Extra Data· 2020-02-19
Multilogue-Net: A Context Aware RNN for Multi-modal Emotion Detection and Sentiment Analysis in Conversation Code
#9Proposed: B2 + B4 w/ multimodal fusion
81.14
Accuracy· Extra Data· 2020-02-21
Gated Mechanism for Attention Based Multimodal Sentiment Analysis
#10CAE-LR
78
Accuracy· Extra Data· 2021-10-06
Unsupervised Multimodal Language Representations using Convolutional Autoencoders
#11Graph-MFN
76.9
Accuracy· Extra Data
No paper
#12MARLIN (ViT-L)
74.83
Accuracy· 2022-11-12
MARLIN: Masked Autoencoder for facial video Representation LearnINg Code
#13MARLIN (ViT-B)
73.7
Accuracy· 2022-11-12
MARLIN: Masked Autoencoder for facial video Representation LearnINg Code
#14MARLIN (ViT-S)
72.69
Accuracy· 2022-11-12
MARLIN: Masked Autoencoder for facial video Representation LearnINg Code