Table 1 Benchmarking MultiCauseNet against baseline methods.
From: MULTICAUSENET temporal attention for multimodal emotion cause pair extraction
Method (year) | Deep learning technique | Dataset | Notable aspects |
|---|---|---|---|
DialogueGCN (2019)17 | Graph Convolutional Network (GCN) | IEMOCAP | Models interrelations among dialogue turns |
DialogueRNN (2019)18 | Recurrent Neural Network (RNN) | IEMOCAP, MELD | Captures sequential dynamics of dialogue |
MMGCN (2019)19 | Multimodal GCN | IEMOCAP | Enhances recognition for Sadness and Excitement |
IterativeERC (2020)20 | Iterative Method | IEMOCAP | Refines predictions through multiple iterations |
QMNN (2021)21 | Quantum-Inspired Techniques | Various | Integrates techniques across modalities |
MM-DFN (2022)22 | Deep Fusion Network | IEMOCAP | Addresses complex emotional expressions |
MVN (2022)23 | Multi-View Approach | Various | Extracts diverse emotional signals |
UniMSE (2022)24 | Self-Supervised Learning | Various | Unified multimodal strategy |
EmoCaps (2022)2 | Various | Various | Detects nuanced emotional expressions |
GA2MIF (2023)25 | Facial and Contextual Info | Various | Enhances emotion recognition |
MALN (2023)26 | Multimodal Learning Network | Various | Excels in recognizing multiple emotions |
MultiEMO (2023)27 | Advanced Methodology | Various | Excels in detecting Sad emotions |
