Saved in:
Bibliographic Details
Main Authors: Chu, Hailong, Li, Hongbing, Chu, Yunlong, Huang, Shutai, Zhang, Xingyue, Yan, Tinghe, Zhang, Jinsong, Zhang, Shuo, Li, Lei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.06683
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915917176242176
author Chu, Hailong
Li, Hongbing
Chu, Yunlong
Huang, Shutai
Zhang, Xingyue
Yan, Tinghe
Zhang, Jinsong
Zhang, Shuo
Li, Lei
author_facet Chu, Hailong
Li, Hongbing
Chu, Yunlong
Huang, Shutai
Zhang, Xingyue
Yan, Tinghe
Zhang, Jinsong
Zhang, Shuo
Li, Lei
contents Multimedia event extraction (M2E2) aims to predict triggers, ground arguments across text and images, and then assemble them into schema-consistent event records. Recent LLM-based approaches have shown strong potential for M2E2, but their intermediate event hypotheses often remain implicit, and event-argument linking is still tightly coupled with role binding. This leaves little opportunity to inspect or revise intermediate event hypotheses and makes predictions brittle to early errors. To bridge this gap, we present ECHO, a multi-agent framework that reframes M2E2 as iterative refinement over an explicit Multimedia Event Hypergraph (MEHG). Instead of relying on implicit linear generation, ECHO performs auditable atomic updates over a shared hypergraph, making intermediate event structures explicit and revisable. Furthermore, we introduce a Link-then-Bind strategy that decouples event-argument linking from role binding, reducing premature semantic commitment during structured prediction. Extensive experiments on the M2E2 benchmark show that ECHO consistently outperforms prior state-of-the-art approaches, achieving gains of 7.3 and 15.5 F1 points on event mention and argument role, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2603_06683
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ECHO: Event-Centric Hypergraph Operations via Multi-Agent Collaboration for Multimedia Event Extraction
Chu, Hailong
Li, Hongbing
Chu, Yunlong
Huang, Shutai
Zhang, Xingyue
Yan, Tinghe
Zhang, Jinsong
Zhang, Shuo
Li, Lei
Computer Vision and Pattern Recognition
Multimedia event extraction (M2E2) aims to predict triggers, ground arguments across text and images, and then assemble them into schema-consistent event records. Recent LLM-based approaches have shown strong potential for M2E2, but their intermediate event hypotheses often remain implicit, and event-argument linking is still tightly coupled with role binding. This leaves little opportunity to inspect or revise intermediate event hypotheses and makes predictions brittle to early errors. To bridge this gap, we present ECHO, a multi-agent framework that reframes M2E2 as iterative refinement over an explicit Multimedia Event Hypergraph (MEHG). Instead of relying on implicit linear generation, ECHO performs auditable atomic updates over a shared hypergraph, making intermediate event structures explicit and revisable. Furthermore, we introduce a Link-then-Bind strategy that decouples event-argument linking from role binding, reducing premature semantic commitment during structured prediction. Extensive experiments on the M2E2 benchmark show that ECHO consistently outperforms prior state-of-the-art approaches, achieving gains of 7.3 and 15.5 F1 points on event mention and argument role, respectively.
title ECHO: Event-Centric Hypergraph Operations via Multi-Agent Collaboration for Multimedia Event Extraction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.06683