# WDMIR: Wavelet-Driven Multimodal Intent Recognition

arXiv: https://arxiv.org/abs/2506.10011 · HTML: https://mlsanity.com/paper/2506.10011/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 33 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [Tensor Fusion Network for Multimodal Sentiment Analysis](https://mlsanity.com/paper/1707.07250/) (2017)
- [MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2005.03545/) (2020)
- [MIntRec: A New Dataset for Multimodal Intent Recognition](https://mlsanity.com/paper/2209.04355/) (2022)
- [Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition](https://mlsanity.com/paper/2312.14667/) (2023)
- [Incorporating Dynamic Semantics into Pre-Trained Language Model for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2203.16369/) (2022)
- [Robust Time Series Denoising with Learnable Wavelet Packet Transform](https://mlsanity.com/paper/2206.06126/) (2022)
- [Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents](https://mlsanity.com/paper/2203.02898/) (2022)
- [SDIF-DA: A Shallow-to-Deep Interaction Framework with Data Augmentation for Multi-modal Intent Detection](https://mlsanity.com/paper/2401.00424/) (2023)
- [Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification](https://mlsanity.com/paper/2205.08772/) (2022)
- [Leveraging Entity Information for Cross-Modality Correlation Learning: The Entity-Guided Multimodal Summarization](https://mlsanity.com/paper/2408.03149/) (2024)
- [DASKT: A Dynamic Affect Simulation Method for Knowledge Tracing](https://mlsanity.com/paper/2502.10396/) (2025)

## Built on by (most cited first, 2 of 2)

- [Transformer-Driven Triple Fusion Framework for Enhanced Multimodal Author Intent Classification in Low-Resource Bangla](https://mlsanity.com/paper/2511.23287/) (2025)
- [Adaptive Modality Reliability Diagnosis and Restoration for Robust Multimodal Intent Recognition](https://mlsanity.com/paper/2608.03475/) (2026)

## Abstract (arXiv)

Multimodal intent recognition (MIR) seeks to accurately interpret user intentions by integrating verbal and non-verbal information across video, audio and text modalities. While existing approaches prioritize text analysis, they often overlook the rich semantic content embedded in non-verbal cues. This paper presents a novel Wavelet-Driven Multimodal Intent Recognition(WDMIR) framework that enhances intent understanding through frequency-domain analysis of non-verbal information. To be more specific, we propose: (1) a wavelet-driven fusion module that performs synchronized decomposition and integration of video-audio features in the frequency domain, enabling fine-grained analysis of temporal dynamics; (2) a cross-modal interaction mechanism that facilitates progressive feature enhancement from bimodal to trimodal integration, effectively bridging the semantic gap between verbal and non-verbal information. Extensive experiments on MIntRec demonstrate that our approach achieves state-of-the-art performance, surpassing previous methods by 1.13% on accuracy. Ablation studies further verify that the wavelet-driven fusion module significantly improves the extraction of semantic information from non-verbal sources, with a 0.41% increase in recognition accuracy when analyzing subtle emotional cues.