Saved in:
Bibliographic Details
Main Authors: Yang, Dingkang, Li, Mingcheng, Qu, Linhao, Yang, Kun, Zhai, Peng, Wang, Song, Zhang, Lihua
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.04955
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908064646430720
author Yang, Dingkang
Li, Mingcheng
Qu, Linhao
Yang, Kun
Zhai, Peng
Wang, Song
Zhang, Lihua
author_facet Yang, Dingkang
Li, Mingcheng
Qu, Linhao
Yang, Kun
Zhai, Peng
Wang, Song
Zhang, Lihua
contents Understanding human intentions (e.g., emotions) from videos has received considerable attention recently. Video streams generally constitute a blend of temporal data stemming from distinct modalities, including natural language, facial expressions, and auditory clues. Despite the impressive advancements of previous works via attention-based paradigms, the inherent temporal asynchrony and modality heterogeneity challenges remain in multimodal sequence fusion, causing adverse performance bottlenecks. To tackle these issues, we propose a Multimodal fusion approach for learning modality-Exclusive and modality-Agnostic representations (MEA) to refine multimodal features and leverage the complementarity across distinct modalities. On the one hand, MEA introduces a predictive self-attention module to capture reliable context dynamics within modalities and reinforce unique features over the modality-exclusive spaces. On the other hand, a hierarchical cross-modal attention module is designed to explore valuable element correlations among modalities over the modality-agnostic space. Meanwhile, a double-discriminator strategy is presented to ensure the production of distinct representations in an adversarial manner. Eventually, we propose a decoupled graph fusion mechanism to enhance knowledge exchange across heterogeneous modalities and learn robust multimodal representations for downstream tasks. Numerous experiments are implemented on three multimodal datasets with asynchronous sequences. Systematic analyses show the necessity of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2407_04955
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Asynchronous Multimodal Video Sequence Fusion via Learning Modality-Exclusive and -Agnostic Representations
Yang, Dingkang
Li, Mingcheng
Qu, Linhao
Yang, Kun
Zhai, Peng
Wang, Song
Zhang, Lihua
Computer Vision and Pattern Recognition
Understanding human intentions (e.g., emotions) from videos has received considerable attention recently. Video streams generally constitute a blend of temporal data stemming from distinct modalities, including natural language, facial expressions, and auditory clues. Despite the impressive advancements of previous works via attention-based paradigms, the inherent temporal asynchrony and modality heterogeneity challenges remain in multimodal sequence fusion, causing adverse performance bottlenecks. To tackle these issues, we propose a Multimodal fusion approach for learning modality-Exclusive and modality-Agnostic representations (MEA) to refine multimodal features and leverage the complementarity across distinct modalities. On the one hand, MEA introduces a predictive self-attention module to capture reliable context dynamics within modalities and reinforce unique features over the modality-exclusive spaces. On the other hand, a hierarchical cross-modal attention module is designed to explore valuable element correlations among modalities over the modality-agnostic space. Meanwhile, a double-discriminator strategy is presented to ensure the production of distinct representations in an adversarial manner. Eventually, we propose a decoupled graph fusion mechanism to enhance knowledge exchange across heterogeneous modalities and learn robust multimodal representations for downstream tasks. Numerous experiments are implemented on three multimodal datasets with asynchronous sequences. Systematic analyses show the necessity of our approach.
title Asynchronous Multimodal Video Sequence Fusion via Learning Modality-Exclusive and -Agnostic Representations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.04955