Pith. sign in

REVIEW 4 cited by

MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2107.06779 v1 pith:FJUED35J submitted 2021-07-14 cs.CL cs.SDeess.AS

Jingwen Hu , Yuchen Liu , Jinming Zhao , Qin Jin This is my paper · ORCID
classification cs.CLcs.SDeess.AS
keywords multimodalinformationmmgcnconversationmodelcontextualemotiongraph
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Emotion recognition in conversation (ERC) is a crucial component in affective dialogue systems, which helps the system understand users' emotions and generate empathetic responses. However, most works focus on modeling speaker and contextual information primarily on the textual modality or simply leveraging multimodal information through feature concatenation. In order to explore a more effective way of utilizing both multimodal and long-distance contextual information, we propose a new model based on multimodal fused graph convolutional network, MMGCN, in this work. MMGCN can not only make use of multimodal dependencies effectively, but also leverage speaker information to model inter-speaker and intra-speaker dependency. We evaluate our proposed model on two public benchmark datasets, IEMOCAP and MELD, and the results prove the effectiveness of MMGCN, which outperforms other SOTA methods by a significant margin under the multimodal conversation setting.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. EmoEUS: Uncertainty Supervision for Multimodal Emotion Recognition in Conversation

    cs.MM 2026-07 conditional novelty 6.0 of 10

    Modeling each modality as a Gaussian and supervising its variance with the 2-Wasserstein distance to emotion cluster centers improves IEMOCAP/MELD accuracy by about 0.5-0.8 points over listed baselines.

  2. Grounding Emotion Recognition with Visual Prototypes: VEGA -- Revisiting CLIP in MERC

    cs.CV 2025-08 conditional novelty 6.0 of 10

    VEGA aligns multimodal emotion features with CLIP-derived visual emotion prototypes and reports SOTA on IEMOCAP and MELD.

  3. EII-SCL: Harnessing Emotional Inertia for Multimodal Emotion Recognition in Conversation

    cs.MM 2026-07 conditional novelty 5.0 of 10

    A plug-in contrastive loss using speaker-local 'emotional inertia' hard negatives improves multimodal emotion-recognition accuracy and F1 on IEMOCAP and MELD by about 0.5–2 points.

  4. Sync-TVA: A Graph-Attention Framework for Multimodal Emotion Recognition with Cross-Modal Fusion

    cs.MM 2025-07 conditional novelty 4.0 of 10

    Sync-TVA reports modest accuracy and weighted-F1 improvements over prior graph-based models on MELD and IEMOCAP, using modality-specific enhancement and cross-modal graph fusion.

Pith tools