mlsanityData to 14 Oct 2026

ADMC: Attention-based Diffusion Model for Missing Modalities Feature Completion

arXiv 2507.05624 ↗First posted 8 Jul 2025cs.AIcited by 0

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

Multimodal emotion and intent recognition is essential for automated human-computer interaction, It aims to analyze users' speech, text, and visual information to predict their emotions or intent. One of the significant challenges is that missing modalities due to sensor malfunctions or incomplete data. Traditional methods that attempt to reconstruct missing information often suffer from over-coupling and imprecise generation processes, leading to suboptimal outcomes. To address these issues, we introduce an Attention-based Diffusion model for Missing Modalities feature Completion (ADMC). Our framework independently trains feature extraction networks for each modality, preserving their unique characteristics and avoiding over-coupling. The Attention-based Diffusion Network (ADN) generates missing modality features that closely align with authentic multimodal distribution, enhancing performance across all missing-modality scenarios. Moreover, ADN's cross-modal generation offers improved recognition even in full-modality contexts. Our approach achieves state-of-the-art results on the IEMOCAP and MIntRec benchmarks, demonstrating its effectiveness in both missing and complete modality scenarios.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 22 of its 40 references that are in the map. First posted on arXiv 8 Jul 2025.

Builds on

22 of 40 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023SUR-adapter: Enhancing Text-to-Image Pre-trained Diffusion Models with Large Language Models9 May
  2. 2021Palette: Image-to-Image Diffusion Models10 Nov

Other references · 20

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  6. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  7. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,127
  8. 2018Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalitiescited by 149
  9. 2014Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognitioncited by 111
  10. 2022GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversationcited by 87
  11. 2020Deep Partial Multi-View Learningcited by 71
  12. 2022EmoCaps: Emotion Capsule based Model for Conversational Emotion Recognitioncited by 48
8 more
  1. 2022MIntRec: A New Dataset for Multimodal Intent Recognitioncited by 41
  2. 2020TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysiscited by 40
  3. 2020Training Strategies to Handle Missing Modalities for Audio-Visual Expression Recognitioncited by 36
  4. 2019Learning Representations from Imperfect Time Series Data via Tensor Rank Regularizationcited by 30
  5. 2018Semi-supervised Deep Generative Modelling of Incomplete Multi-Modality Emotional Datacited by 29
  6. 2022Tag-assisted Multimodal Sentiment Analysis under Uncertain Missing Modalitiescited by 28
  7. 2023Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognitioncited by 18
  8. 2022Exploiting modality-invariant feature for robust multimodal emotion recognition with missing modalitiescited by 16

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Modality-Invariant Bidirectional Temporal Representation Distillation Network for Missing Multimodal Sentiment Analysis
  2. 2025Federated Dialogue-Semantic Diffusion for Emotion Recognition under Incomplete Modalities
  3. 2025Towards Robust Multimodal Emotion Recognition under Missing Modalities and Distribution Shifts
  4. 2025GSDNet: Revisiting Incomplete Multimodal-Diffusion from Graph Spectrum Perspective for Conversation Emotion Recognition
  5. 2025MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding
  6. 2026Modality Disentangled Learning for Incomplete Multimodal Emotion Recognition: A Primitive Memory Distillation Perspective
  7. 2024Enhancing Multimodal Sentiment Analysis for Missing Modality through Self-Distillation and Unified Modality Cross-Attention
  8. 2026Addressing Missing and Noisy Modalities in One Solution: Unified Modality-Quality Framework for Low-quality Multimodal Data