AI Paper Atlas

Research map / Benchmarks / CMU-MOSEI

CMU-MOSEI leaderboard

28 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CMU-MOSEI. Best MAE: 0.489 (HCMNet, AAAI 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

CMU-MOSEI · MAE

19 papers, each with its best reported number for its own method; lower is better.

9 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

CMU-MOSEI · F1

17 papers, each with its best reported number for its own method; higher is better.

7 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

CMU-MOSEI · Acc-7

16 papers, each with its best reported number for its own method; higher is better.

6 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

CMU-MOSEI · Corr

15 papers, each with its best reported number for its own method; higher is better.

#Corr ↑MethodPaperTopic
10.831PaSE
BERT-base
PaSE: Prototype-aligned Calibration and Shapley-based Equilibrium for Multimodal Sentiment Analysis
AAAI 2026 · Table 1
Cross-modal learning
20.825QaP
DeBERTa-V2-XLarge
Querying as Prompt: Parameter-Efficient Learning for Multimodal Language Model
CVPR 2024 · Table 4
CLIP and zero-shot
30.824EBMCEnhance-then-Balance Modality Collaboration for Robust Multimodal Sentiment Analysis
CVPR 2026 · Table 1
Cross-modal learning
40.819HCMNetTowards Multimodal Sentiment Analysis via Hierarchical Correlation Modeling with Semantic Distribution Constraints
AAAI 2025 · Table 3
Cross-modal learning
50.816EAUEmbracing Unimodal Aleatoric Uncertainty for Robust Multimodal Fusion
CVPR 2024 · Table 1
Cross-modal learning
60.813ITHP
DeBERTa
Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning
ICLR 2024 · CMU-MOSEI results table
Cross-modal learning
70.812PLUM-NetPLUM-Net: Prototype-Induced Label Structuring for Disentangled Multimodal Representation Network
AAAI 2026 · Table 1
Cross-modal learning
80.81Joint experts & routerFuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion
NeurIPS 2024 · CMU-MOSI and MOSEI results tab
Cross-modal learning
90.802PaP
ChatGLM-6B
Prototype-as-Prompt: Multimodal Sentiment Prototypes Endowing Large Language Models the Capability to Perform Multimodal Sentiment Analysis
CVPR 2026 · Table 1
Cross-modal learning
100.799CaReFlowCaReFlow: Cyclic Adaptive Rectified Flow for Multimodal Fusion
CVPR 2026 · Table 1
Cross-modal learning
5 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

CMU-MOSEI · Acc-2

15 papers, each with its best reported number for its own method; higher is better.

5 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.