Revisiting Multi-modal Emotion Learning with Broad State Space Models and Probability-guidance Fusion

• URL: http://arxiv.org/abs/2404.17858v2
• Date: Fri, 3 May 2024 02:28:10 GMT
• Title: Revisiting Multi-modal Emotion Learning with Broad State Space Models and Probability-guidance Fusion
• Authors: Yuntao Shou, Tao Meng, Fuchen Zhang, Nan Yin, Keqin Li,
• Abstract summary: We argue that long-range contextual semantic information should be extracted in the feature disentanglement stage and the inter-modal semantic information consistency should be maximized in the feature fusion stage. Inspired by recent State Space Models (SSMs), we propose a Broad Mamba, which does not rely on a self-attention mechanism for sequence modeling. We show that the proposed method can overcome the computational and memory limitations of Transformer when modeling long-distance contexts.
• Score: 14.14051929942914
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-modal Emotion Recognition in Conversation (MERC) has received considerable attention in various fields, e.g., human-computer interaction and recommendation systems. Most existing works perform feature disentanglement and fusion to extract emotional contextual information from multi-modal features and emotion classification. After revisiting the characteristic of MERC, we argue that long-range contextual semantic information should be extracted in the feature disentanglement stage and the inter-modal semantic information consistency should be maximized in the feature fusion stage. Inspired by recent State Space Models (SSMs), Mamba can efficiently model long-distance dependencies. Therefore, in this work, we fully consider the above insights to further improve the performance of MERC. Specifically, on the one hand, in the feature disentanglement stage, we propose a Broad Mamba, which does not rely on a self-attention mechanism for sequence modeling, but uses state space models to compress emotional representation, and utilizes broad learning systems to explore the potential data distribution in broad space. Different from previous SSMs, we design a bidirectional SSM convolution to extract global context information. On the other hand, we design a multi-modal fusion strategy based on probability guidance to maximize the consistency of information between modalities. Experimental results show that the proposed method can overcome the computational and memory limitations of Transformer when modeling long-distance contexts, and has great potential to become a next-generation general architecture in MERC.

Related papers

• Masked Graph Learning with Recurrent Alignment for Multimodal Emotion Recognition in Conversation [12.455034591553506]
  Multimodal Emotion Recognition in Conversation (MERC) can be applied to public opinion monitoring, intelligent dialogue robots, and other fields. Previous work ignored the inter-modal alignment process and the intra-modal noise information before multimodal fusion. We have developed a novel approach called Masked Graph Learning with Recursive Alignment (MGLRA) to tackle this problem.
  arXiv  Detail & Related papers  (2024-07-23T02:23:51Z)
• Coupled Mamba: Enhanced Multi-modal Fusion with Coupled State Space Model [18.19558762805031]
  This paper proposes the Coupled SSM model, for coupling state chains of multiple modalities while maintaining independence of intra-modality state processes. Experiments on CMU-EI, CH-SIMS, CH-SIMSV2 through multi-domain input verify the effectiveness of our model. Results demonstrate that Coupled Mamba model is capable of enhanced multi-modal fusion.
  arXiv  Detail & Related papers  (2024-05-28T09:57:03Z)
• U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation [63.31007867379312]
  We introduce U3M: An Unbiased Multiscale Modal Fusion Model for Multimodal Semantics. We employ feature fusion at multiple scales to ensure the effective extraction and integration of both global and local features. Experimental results demonstrate that our approach achieves superior performance across multiple datasets.
  arXiv  Detail & Related papers  (2024-05-24T08:58:48Z)
• AIMDiT: Modality Augmentation and Interaction via Multimodal Dimension Transformation for Emotion Recognition in Conversations [57.99479708224221]
  We propose a novel framework called AIMDiT to solve the problem of multimodal fusion of deep features. Experiments conducted using our AIMDiT framework on the public benchmark dataset MELD reveal 2.34% and 2.87% improvements in terms of the Acc-7 and w-F1 metrics.
  arXiv  Detail & Related papers  (2024-04-12T11:31:18Z)
• SurvMamba: State Space Model with Multi-grained Multi-modal Interaction for Survival Prediction [8.452410804749512]
  We propose a structured state space model named Mamba with multi-grained multi-modal interaction (SurvMamba) for survival prediction. SurvMamba is implemented with a Hierarchical Interaction Mamba (HIM) module that facilitates efficient intra-modal interactions at different granularities. An Interaction Fusion Mamba (IFM) module is used for cascaded inter-modal interactive fusion, yielding more comprehensive features for survival prediction.
  arXiv  Detail & Related papers  (2024-04-11T15:58:12Z)
• Joint Multimodal Transformer for Emotion Recognition in the Wild [49.735299182004404]
  Multimodal emotion recognition (MMER) systems typically outperform unimodal systems. This paper proposes an MMER method that relies on a joint multimodal transformer (JMT) for fusion with key-based cross-attention.
  arXiv  Detail & Related papers  (2024-03-15T17:23:38Z)
• MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments [82.67236400004826]
  We introduce the Multimodal Embodied Interactive Agent (MEIA), capable of translating high-level tasks expressed in natural language into a sequence of executable actions. MEM module enables MEIA to generate executable action plans based on diverse requirements and the robot's capabilities.
  arXiv  Detail & Related papers  (2024-02-01T02:43:20Z)
• Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding [54.49214267905562]
  We construct a transformer-based framework for multi-modal manipulation detection and grounding tasks. Our framework simultaneously explores modality-specific features while preserving the capability for multi-modal alignment. We propose an implicit manipulation query (IMQ) that adaptively aggregates global contextual cues within each modality.
  arXiv  Detail & Related papers  (2023-09-22T06:55:41Z)
• Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition [81.2011058113579]
  We argue that both the feature multimodality and conversational contextualization should be properly modeled simultaneously during the feature disentanglement and fusion steps. We propose a Contribution-aware Fusion Mechanism (CFM) and a Context Refusion Mechanism ( CRM) for multimodal and context integration. Our system achieves new state-of-the-art performance consistently.
  arXiv  Detail & Related papers  (2023-08-08T18:11:27Z)
• Fusion with Hierarchical Graphs for Mulitmodal Emotion Recognition [7.147235324895931]
  This paper proposes a novel hierarchical graph network (HFGCN) model that learns more informative multimodal representations. Specifically, the proposed model fuses multimodality inputs using a two-stage graph construction approach and encodes the modality dependencies into the conversation representation. Experiments showed the effectiveness of our proposed model for more accurate AER, which yielded state-of-the-art results on two public datasets.
  arXiv  Detail & Related papers  (2021-09-15T08:21:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.