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

arXiv: https://arxiv.org/abs/2507.05624 · HTML: https://mlsanity.com/paper/2507.05624/

## 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.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities](https://mlsanity.com/paper/1812.07809/) (2018)
- [Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition](https://mlsanity.com/paper/1402.1128/) (2014)
- [GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation](https://mlsanity.com/paper/2203.02177/) (2022)
- [Deep Partial Multi-View Learning](https://mlsanity.com/paper/2011.06170/) (2020)
- [EmoCaps: Emotion Capsule based Model for Conversational Emotion Recognition](https://mlsanity.com/paper/2203.13504/) (2022)
- [MIntRec: A New Dataset for Multimodal Intent Recognition](https://mlsanity.com/paper/2209.04355/) (2022)
- [TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2009.02902/) (2020)
- [Training Strategies to Handle Missing Modalities for Audio-Visual Expression Recognition](https://mlsanity.com/paper/2010.00734/) (2020)
- [Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization](https://mlsanity.com/paper/1907.01011/) (2019)
- [SUR-adapter: Enhancing Text-to-Image Pre-trained Diffusion Models with Large Language Models](https://mlsanity.com/paper/2305.05189/) (2023)
- [Semi-supervised Deep Generative Modelling of Incomplete Multi-Modality Emotional Data](https://mlsanity.com/paper/1808.02096/) (2018)
- [Tag-assisted Multimodal Sentiment Analysis under Uncertain Missing Modalities](https://mlsanity.com/paper/2204.13707/) (2022)
- [Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition](https://mlsanity.com/paper/2312.14667/) (2023)
- [Exploiting modality-invariant feature for robust multimodal emotion recognition with missing modalities](https://mlsanity.com/paper/2210.15359/) (2022)

## 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.