Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhou, Ao, Tu, Mingsheng, Wang, Luping, Sun, Tenghao, Cheng, Zifeng, Yin, Yafeng, Jiang, Zhiwei, Gu, Qing
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2508.16147
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912548856528896
author Zhou, Ao
Tu, Mingsheng
Wang, Luping
Sun, Tenghao
Cheng, Zifeng
Yin, Yafeng
Jiang, Zhiwei
Gu, Qing
author_facet Zhou, Ao
Tu, Mingsheng
Wang, Luping
Sun, Tenghao
Cheng, Zifeng
Yin, Yafeng
Jiang, Zhiwei
Gu, Qing
contents Social Media Popularity Prediction is a complex multimodal task that requires effective integration of images, text, and structured information. However, current approaches suffer from inadequate visual-textual alignment and fail to capture the inherent cross-content correlations and hierarchical patterns in social media data. To overcome these limitations, we establish a multi-class framework , introducing hierarchical prototypes for structural enhancement and contrastive learning for improved vision-text alignment. Furthermore, we propose a feature-enhanced framework integrating dual-grained prompt learning and cross-modal attention mechanisms, achieving precise multimodal representation through fine-grained category modeling. Experimental results demonstrate state-of-the-art performance on benchmark metrics, establishing new reference standards for multimodal social media analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16147
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cross-Modal Prototype Augmentation and Dual-Grained Prompt Learning for Social Media Popularity Prediction
Zhou, Ao
Tu, Mingsheng
Wang, Luping
Sun, Tenghao
Cheng, Zifeng
Yin, Yafeng
Jiang, Zhiwei
Gu, Qing
Information Retrieval
Social Media Popularity Prediction is a complex multimodal task that requires effective integration of images, text, and structured information. However, current approaches suffer from inadequate visual-textual alignment and fail to capture the inherent cross-content correlations and hierarchical patterns in social media data. To overcome these limitations, we establish a multi-class framework , introducing hierarchical prototypes for structural enhancement and contrastive learning for improved vision-text alignment. Furthermore, we propose a feature-enhanced framework integrating dual-grained prompt learning and cross-modal attention mechanisms, achieving precise multimodal representation through fine-grained category modeling. Experimental results demonstrate state-of-the-art performance on benchmark metrics, establishing new reference standards for multimodal social media analysis.
title Cross-Modal Prototype Augmentation and Dual-Grained Prompt Learning for Social Media Popularity Prediction
topic Information Retrieval
url https://arxiv.org/abs/2508.16147