Salvato in:
Dettagli Bibliografici
Autori principali: Zhao, Haochen, Kong, Yuyao, Xu, Yongxiu, Gou, Gaopeng, Xu, Hongbo, Wang, Yubin, Zhang, Haoliang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.23299
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912930638856192
author Zhao, Haochen
Kong, Yuyao
Xu, Yongxiu
Gou, Gaopeng
Xu, Hongbo
Wang, Yubin
Zhang, Haoliang
author_facet Zhao, Haochen
Kong, Yuyao
Xu, Yongxiu
Gou, Gaopeng
Xu, Hongbo
Wang, Yubin
Zhang, Haoliang
contents Despite progress in multimodal sarcasm detection, existing datasets and methods predominantly focus on single-image scenarios, overlooking potential semantic and affective relations across multiple images. This leaves a gap in modeling cases where sarcasm is triggered by multi-image cues in real-world settings. To bridge this gap, we introduce MMSD3.0, a new benchmark composed entirely of multi-image samples curated from tweets and Amazon reviews. We further propose the Cross-Image Reasoning Model (CIRM), which performs targeted cross-image sequence modeling to capture latent inter-image connections. In addition, we introduce a relevance-guided, fine-grained cross-modal fusion mechanism based on text-image correspondence to reduce information loss during integration. We establish a comprehensive suite of strong and representative baselines and conduct extensive experiments, showing that MMSD3.0 is an effective and reliable benchmark that better reflects real-world conditions. Moreover, CIRM demonstrates state-of-the-art performance across MMSD, MMSD2.0 and MMSD3.0, validating its effectiveness in both single-image and multi-image scenarios. Dataset and code are publicly available at https://github.com/ZHCMOONWIND/MMSD3.0.
format Preprint
id arxiv_https___arxiv_org_abs_2510_23299
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MMSD3.0: A Multi-Image Benchmark for Real-World Multimodal Sarcasm Detection
Zhao, Haochen
Kong, Yuyao
Xu, Yongxiu
Gou, Gaopeng
Xu, Hongbo
Wang, Yubin
Zhang, Haoliang
Computer Vision and Pattern Recognition
Multimedia
Despite progress in multimodal sarcasm detection, existing datasets and methods predominantly focus on single-image scenarios, overlooking potential semantic and affective relations across multiple images. This leaves a gap in modeling cases where sarcasm is triggered by multi-image cues in real-world settings. To bridge this gap, we introduce MMSD3.0, a new benchmark composed entirely of multi-image samples curated from tweets and Amazon reviews. We further propose the Cross-Image Reasoning Model (CIRM), which performs targeted cross-image sequence modeling to capture latent inter-image connections. In addition, we introduce a relevance-guided, fine-grained cross-modal fusion mechanism based on text-image correspondence to reduce information loss during integration. We establish a comprehensive suite of strong and representative baselines and conduct extensive experiments, showing that MMSD3.0 is an effective and reliable benchmark that better reflects real-world conditions. Moreover, CIRM demonstrates state-of-the-art performance across MMSD, MMSD2.0 and MMSD3.0, validating its effectiveness in both single-image and multi-image scenarios. Dataset and code are publicly available at https://github.com/ZHCMOONWIND/MMSD3.0.
title MMSD3.0: A Multi-Image Benchmark for Real-World Multimodal Sarcasm Detection
topic Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2510.23299