Challenge: Existing studies focus on learning contextual information in conversations, neglecting acoustic and vision topic information.
Approach: They propose a model-agnostic Topic-enriched Diffusion approach for capturing multimodal topic information in MCE tasks.
Outcome: The proposed approach improves over the state-of-the-art MCE models and the existing models.

Similar Papers

Multi-Condition Guided Diffusion Network for Multimodal Emotion Recognition in Conversation (2025.findings-naacl)

Copied to clipboard

Challenge: Current research emphasizes contextual factors, the speaker’s influence, and extracting complementary information across different modalities.
Approach: They propose a diffusion-based approach to address the challenges posed by redundant information and redundant information at the semantic level while robustly capturing shared semantics.
Outcome: The proposed model outperforms existing state-of-the-art models on two multimodal datasets and is generalizable and effective.
Multimodal Topic-Enriched Auxiliary Learning for Depression Detection (2020.coling-main)

Copied to clipboard

Challenge: Existing studies on depression detection rely on textual and visual content to determine whether a human being is depressed or non-depressed.
Approach: They propose a multimodal topic-enriched Auxiliary Learning approach that captures topic information from texts and images for depression detection.
Outcome: The proposed approach improves the performance of the primary task by using topic information from text and images.
Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modeling (2023.acl-long)

Copied to clipboard

Challenge: Existing research on multimodal relation extraction (MRE) faces internal-information over-utilization and external-information under-exploitation.
Approach: They propose a framework that implements internal-information screening and external-information exploiting to address these challenges.
Outcome: The proposed framework outperforms the current best model on the benchmark dataset.
MultiEMO: An Attention-Based Correlation-Aware Multimodal Fusion Framework for Emotion Recognition in Conversations (2023.acl-long)

Copied to clipboard

Challenge: Emotion Recognition in Conversations (ERC) is an increasingly popular task in the field of Natural Language Processing.
Approach: They propose a framework that captures cross-modal mapping relationships across modalities . they propose 'multiemotion-aware' framework that integrates multimodal cues into the model .
Outcome: The proposed framework outperforms state-of-the-art models in all emotion categories on two benchmark datasets.
Self-adaptive Context and Modal-interaction Modeling For Multimodal Emotion Recognition (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to predict emotion label for a given utterance lack modeling of diverse dependency ranges and inconsistent treatment of contribution for various modalities.
Approach: They propose a multimodal emotion recognition in conversation task that uses context and multiple modalities to predict emotion label for a given utterance.
Outcome: The proposed method outperforms the state-of-the-art methods on three multimodal datasets.
Emotion-Wheel-Guided Audio-Referred Text Representation for Multimodal Emotion Recognition in Conversation (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for Emotion Recognition in Conversation ignore their distinct communicative roles and information capacities and apply uniform penalties regardless of affective proximity.
Approach: They propose a modality-aware fusion strategy capturing linguistic features from text as the primary source and audio as a complementary component.
Outcome: The proposed method captures linguistic features from text as the primary source and audio as a complementary component and supervised contrastive loss to encode emotional proximity based on Russell’s circumplex model.
Neural Multimodal Topic Modeling: A Comprehensive Evaluation (2024.lrec-main)

Copied to clipboard

Challenge: Neural topic models can find coherent and diverse topics in textual data, but they are limited in dealing with multimodal datasets.
Approach: They propose two new topic modeling solutions and two new evaluation metrics for document multimodality.
Outcome: The proposed models generate coherent and diverse topics on a rich dataset.
UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition (2022.emnlp-main)

Copied to clipboard

Challenge: Existing studies study sentiment and emotion separately and do not fully exploit the complementary knowledge behind the two.
Approach: They propose a multimodal sentiment knowledge-sharing framework that unifies MSA and ERC tasks from features, labels, and models.
Outcome: The proposed framework achieves consistent improvements on four public benchmark datasets on MOSI, MOSEI, MELD, and IEMOCAP.
A Dual Contrastive Learning Framework for Enhanced Multimodal Conversational Emotion Recognition (2025.coling-main)

Copied to clipboard

Challenge: Existing methods struggle to capture emotion shifts due to label replication and fail to preserve positive independent modality contributions during fusion.
Approach: They propose a Dual Contrastive Learning Framework that enhances existing MERC models without additional data.
Outcome: The proposed framework outperforms existing models on two MERC benchmark datasets and shows that it reduces label dependence and enhances emotion-sensitive independent modality features.
Multimodal Emotion Recognition in Conversations: A Survey of Methods, Trends, Challenges and Prospects (2025.findings-emnlp)

Copied to clipboard

Challenge: Multimodal Emotion Recognition in Conversations (MERC) is a new way to enhance human-computer interaction.
Approach: This survey offers a systematic overview of Multimodal Emotion Recognition in Conversations . it examines motivations, core tasks, representative methods, and evaluation strategies .
Outcome: The survey examines the effectiveness of MERC and its evaluation strategies.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations