Papers › Multimodal Multi-loss Fusion Network for Sentiment Analysis

Multimodal Multi-loss Fusion Network for Sentiment Analysis

1 Aug 2023arXiv:2308.00264archive 2025-07-28

Zehui Wu, Ziwei Gong, Jaywon Koo, Julia Hirschberg

This paper investigates the optimal selection and fusion of feature encoders across multiple modalities and combines these in one neural network to improve sentiment detection. We compare different fusion methods and examine the impact of multi-loss training within the multi-modality fusion network, identifying surprisingly important findings relating to subnet performance. We have also found that integrating context significantly enhances model performance. Our best model achieves state-of-the-art performance for three datasets (CMU-MOSI, CMU-MOSEI and CH-SIMS). These results suggest a roadmap toward an optimized feature selection and fusion approach for enhancing sentiment detection in neural networks.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

zehuiwu/MMML officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with... (arXiv:2505.19525; that paper's own run record: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multimodal Sentiment AnalysisSentiment Analysisfeature selection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multimodal Sentiment Analysis CH-SIMS MMML CORR 73.26 #1 of 2 Archive leaderboard report
Multimodal Sentiment Analysis CH-SIMS MMML F1 82.9 #1 of 2 Archive leaderboard report
Multimodal Sentiment Analysis CH-SIMS MMML MAE 0.332 #1 of 2 Archive leaderboard report
Multimodal Sentiment Analysis CMU-MOSEI MMML Acc-5 57.45 #2 of 15 Archive leaderboard report
Multimodal Sentiment Analysis CMU-MOSEI MMML Acc-7 54.77 #2 of 15 Archive leaderboard report
Multimodal Sentiment Analysis CMU-MOSEI MMML Accuracy 88.22 #2 of 15 Archive leaderboard report
Multimodal Sentiment Analysis CMU-MOSEI MMML Corr 81.42 #2 of 15 Archive leaderboard report
Multimodal Sentiment Analysis CMU-MOSEI MMML F1 88.04 #2 of 15 Archive leaderboard report
Multimodal Sentiment Analysis CMU-MOSEI MMML MAE 0.5072 #2 of 15 Archive leaderboard report
Multimodal Sentiment Analysis CMU-MOSI MMML Acc-2 90.35 #1 of 12 Archive leaderboard report
Multimodal Sentiment Analysis CMU-MOSI MMML Acc-5 60.01 #1 of 12 Archive leaderboard report
Multimodal Sentiment Analysis CMU-MOSI MMML Acc-7 52.72 #1 of 12 Archive leaderboard report
Multimodal Sentiment Analysis CMU-MOSI MMML Corr 0.8824 #1 of 12 Archive leaderboard report
Multimodal Sentiment Analysis CMU-MOSI MMML F1 90.35 #1 of 12 Archive leaderboard report
Multimodal Sentiment Analysis CMU-MOSI MMML MAE 0.5573 #1 of 12 Archive leaderboard report
Multimodal Sentiment Analysis MOSI MMML Accuracy 90.35 #1 of 11 Archive leaderboard report
Multimodal Sentiment Analysis MOSI MMML F1 score 90.35 #1 of 11 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Feature Selection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections