MATIC: A Lightweight Decision-Level Attention Model as a Strong Baseline for Multimodal Time-Series Classification

Multimodal time-series classification has been successfully applied to diverse domains, yet recent research has increasingly favored complex feature-level fusion architectures whose computational cost often limits practical deployment. In this work, we investigate whether such complexity is necessary through a comprehensive cross-domain empirical study of decision-level fusion. We introduce MATIC (Multimodal Attention-based Time-series Classifier), a lightweight framework in which channel-specific convolutional neural networks independently classify each signal stream and a self-attention module adaptively fuses the resulting class-probability distributions. This modular formulation decouples feature extraction from multimodal fusion, enabling efficient training, reduced model complexity, and straightforward scalability across heterogeneous modalities. We evaluate the proposed approach on six public benchmark datasets spanning emotion recognition, human activity recognition, and stock movement prediction. Across all benchmarks, MATIC achieves competitive performance while requiring substantially fewer trainable parameters (0.11–1.95 M) than many specialized multimodal architectures. Comparisons with conventional decision fusion strategies and architectural ablations show that adaptive attention outperforms static and MLP-based fusion in most settings, and robustness analyses characterize its sensitivity to noisy and missing inputs. These findings suggest that lightweight decision-level attention fusion constitutes a strong baseline for multimodal time-series classification and provides a simpler alternative to increasingly complex multimodal fusion architectures.

Authors

Institutions

Publication Details

Journal
Big Data and Cognitive Computing
Published
2026-11-17
DOI
https://doi.org/10.3390/bdcc10110393
Primary Topic
Time Series Analysis and Forecasting
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

MATIC: A Lightweight Decision-Level Attention Model as a Strong Baseline for Multimodal Time-Series Classification

Bonny Banerjee, Rabin Nepal
1 links
Big Data and Cognitive Computing
Time Series Analysis and Forecasting
article

MATIC: A Lightweight Decision-Level Attention Model as a Strong Baseline for Multimodal Time-Series Classification

Bonny Banerjee, Rabin Nepal
article en

Abstract

Multimodal time-series classification has been successfully applied to diverse domains, yet recent research has increasingly favored complex feature-level fusion architectures whose computational cost often limits practical deployment. In this work, we investigate whether such complexity is necessary through a comprehensive cross-domain empirical study of decision-level fusion. We introduce MATIC (Multimodal Attention-based Time-series Classifier), a lightweight framework in which channel-specific convolutional neural networks independently classify each signal stream and a self-attention module adaptively fuses the resulting class-probability distributions. This modular formulation decouples feature extraction from multimodal fusion, enabling efficient training, reduced model complexity, and straightforward scalability across heterogeneous modalities. We evaluate the proposed approach on six public benchmark datasets spanning emotion recognition, human activity recognition, and stock movement prediction. Across all benchmarks, MATIC achieves competitive performance while requiring substantially fewer trainable parameters (0.11–1.95 M) than many specialized multimodal architectures. Comparisons with conventional decision fusion strategies and architectural ablations show that adaptive attention outperforms static and MLP-based fusion in most settings, and robustness analyses characterize its sensitivity to noisy and missing inputs. These findings suggest that lightweight decision-level attention fusion constitutes a strong baseline for multimodal time-series classification and provides a simpler alternative to increasingly complex multimodal fusion architectures.

Big Data and Cognitive ComputingVol. 10(11)
University of Memphis (US)
Time Series Analysis and Forecasting
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon