LGJun 22, 2021

Sequential Late Fusion Technique for Multi-modal Sentiment Analysis

arXiv:2106.11473v1
AI Analysis

This work addresses sentiment analysis for users of multi-modal systems, but appears incremental as it builds on existing fusion methods without clear breakthrough claims.

The authors tackled multi-modal sentiment analysis by proposing a sequential late fusion technique using a multi-head attention LSTM network on text, audio, and visual data from the MOSI dataset, achieving unspecified classification performance results.

Multi-modal sentiment analysis plays an important role for providing better interactive experiences to users. Each modality in multi-modal data can provide different viewpoints or reveal unique aspects of a user's emotional state. In this work, we use text, audio and visual modalities from MOSI dataset and we propose a novel fusion technique using a multi-head attention LSTM network. Finally, we perform a classification task and evaluate its performance.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes