| Challenge: | Comprehending multimodal language requires modeling interactions between modalities and between them. |
| Approach: | They propose a multistage fusion network which decomposes the fusion problem into multiple stages, each focused on a subset of multimodal signals for specialized, effective fusion. |
| Outcome: | The proposed model performs state-of-the-art across three datasets relating to multimodal sentiment analysis, emotion recognition, and speaker traits recognition. |
Similar Papers
Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph (P18-1)
Copied to clipboard
| Challenge: | Analyzing human multimodal language is emerging area of research in NLP. |
| Approach: | They propose a multimodal fusion technique to exploit how modalities interact in multimodal language. |
| Outcome: | The proposed technique exploits how modalities interact with each other in human multimodal language. |
MPID: A Modality-Preserving and Interaction-Driven Fusion Network for Multimodal Sentiment Analysis (2025.coling-main)
Copied to clipboard
| Challenge: | Current methods for multimodal sensing analysis overlook nuanced differences and similarities across modalities, leading to potential biases. |
| Approach: | They propose a Modal-Preserving and Interaction-Driven Fusion Network to address these challenges by integrating text with audio and a separate Adaptive Graded Fusion Module for text and visual data. |
| Outcome: | The proposed model achieves state-of-the-art on CMU-MOSI, CMU -MOSEI, and CH-SIMS datasets. |
Sequential Fusion of Text-close and Text-far Representations for Multimodal Sentiment Analysis (2025.coling-main)
Copied to clipboard
| Challenge: | Multimodal Sentiment Analysis (MSA) aims to identify human attitudes from diverse modalities such as visual, audio and text. |
| Approach: | They propose a framework to combine text-close and text-far representations to refine multimodal representations from multimodal data. |
| Outcome: | The proposed framework explores similarities and differences between text and audio/visual modalities and fuses extracted representations more effectively. |
Self-supervised Cross-modal Pretraining for Speech Emotion Recognition and Sentiment Analysis (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to multimodal speech emotion recognition and sentiment analysis have not improved results due to their relatively simple fusion mechanisms and lack of proper cross-modal pretraining. |
| Approach: | They propose a deep-fused audio-text bi-modal transformer with carefully designed cross-modal fusion mechanism and stage-wise cross-mod pretraining scheme to facilitate cross-modulation. |
| Outcome: | The proposed method exceeds benchmarks on public IEMOCAP emotion and CMU-MOSEI sentiment datasets by a large margin. |
ModRWKV: Transformer Multimodality in Linear Time (2025.emnlp-main)
Copied to clipboard
| Challenge: | Currently, multimodal studies are based on large language models with quadratic-complexity Transformer architectures. |
| Approach: | They propose a decoupled multimodal framework built upon the RWKV7 architecture as its LLM backbone and a lightweight architecture to achieve multi-source information fusion. |
| Outcome: | The proposed framework achieves multi-source information fusion through dynamically adaptable heterogeneous modality encoders. |
MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences (2021.naacl-main)
Copied to clipboard
Jianing Yang, Yongxin Wang, Ruitao Yi, Yuying Zhu, Azaan Rehman, Amir Zadeh, Soujanya Poria, Louis-Philippe Morency
| Challenge: | a novel graph-based neural model for multimodal sequential data is proposed . fusion is the process of blending information from multiple modalities, usually preceded by alignment . |
| Approach: | They propose a graph-based neural model that converts unaligned data into a modal-temporal graph . they use a dynamic pruning and read-out technique to efficiently process the graph fusion operation . |
| Outcome: | The proposed model performs state-of-the-art on multimodal sentiment analysis and emotion recognition benchmarks while utilizing significantly fewer model parameters. |
Adaptive Fusion Techniques for Multimodal Data (2021.eacl-main)
Copied to clipboard
| Challenge: | Effective fusion of data from multiple modalities is challenging due to the heterogeneous nature of multimodal data. |
| Approach: | They propose two adaptive fusion techniques that aim to combine multimodal data effectively. |
| Outcome: | The proposed networks can model context from other modalities better than existing methods. |
Unimodal and Crossmodal Refinement Network for Multimodal Sequence Fusion (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to modulate one modal feature to another are lacking in multimodal representation learning. |
| Approach: | They propose to use unimodal and crossmodal refinement networks to enhance uni and cross-modal representations by iterative updating of distributions with transformer-based attention layers to refine modality-specific learning. |
| Outcome: | The proposed network outperforms state-of-the-art techniques on MOSI and MOSEI datasets. |
Multimodal Multi-loss Fusion Network for Sentiment Analysis (2024.naacl-long)
Copied to clipboard
| Challenge: | This paper examines the optimal selection and fusion of feature encoders across multiple modalities and combines them in one neural network to improve sentiment detection. |
| Approach: | They propose to combine feature encoders across multiple modalities into one neural network to improve sentiment detection. |
| Outcome: | The proposed model achieves state-of-the-art performance for three datasets . it also shows that integrating context significantly improves model performance. |
CTFN: Hierarchical Learning for Multimodal Sentiment Analysis Using Coupled-Translation Fusion Network (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for multimodal sentiment analysis require all modalities as input, thus are sensitive to missing modality at predicting time. |
| Approach: | They propose to model bi-direction interplay via couple learning and exploit multiple bi-directional translations to exploit multimodal fusion embeddings. |
| Outcome: | The proposed framework achieves state-of-the-art or often competitive performance on two multimodal benchmarks with extensive ablation studies. |