Saved in:
Bibliographic Details
Main Authors: Wang, Eileen, Arnaout, Hiba, Pratama, Dhita, Yang, Shuo, Liu, Dangyang, Yang, Jie, Poon, Josiah, Pan, Jeff, Han, Caren
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.01055
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912934594084864
author Wang, Eileen
Arnaout, Hiba
Pratama, Dhita
Yang, Shuo
Liu, Dangyang
Yang, Jie
Poon, Josiah
Pan, Jeff
Han, Caren
author_facet Wang, Eileen
Arnaout, Hiba
Pratama, Dhita
Yang, Shuo
Liu, Dangyang
Yang, Jie
Poon, Josiah
Pan, Jeff
Han, Caren
contents We present MMCOMET, the first multimodal commonsense knowledge graph (MMKG) that integrates physical, social, and eventive knowledge. MMCOMET extends the ATOMIC2020 knowledge graph to include a visual dimension, through an efficient image retrieval process, resulting in over 900K multimodal triples. This new resource addresses a major limitation of existing MMKGs in supporting complex reasoning tasks like image captioning and storytelling. Through a standard visual storytelling experiment, we show that our holistic approach enables the generation of richer, coherent, and contextually grounded stories than those produced using text-only knowledge. This resource establishes a new foundation for multimodal commonsense reasoning and narrative generation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_01055
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MMCOMET: A Large-Scale Multimodal Commonsense Knowledge Graph for Contextual Reasoning
Wang, Eileen
Arnaout, Hiba
Pratama, Dhita
Yang, Shuo
Liu, Dangyang
Yang, Jie
Poon, Josiah
Pan, Jeff
Han, Caren
Artificial Intelligence
We present MMCOMET, the first multimodal commonsense knowledge graph (MMKG) that integrates physical, social, and eventive knowledge. MMCOMET extends the ATOMIC2020 knowledge graph to include a visual dimension, through an efficient image retrieval process, resulting in over 900K multimodal triples. This new resource addresses a major limitation of existing MMKGs in supporting complex reasoning tasks like image captioning and storytelling. Through a standard visual storytelling experiment, we show that our holistic approach enables the generation of richer, coherent, and contextually grounded stories than those produced using text-only knowledge. This resource establishes a new foundation for multimodal commonsense reasoning and narrative generation.
title MMCOMET: A Large-Scale Multimodal Commonsense Knowledge Graph for Contextual Reasoning
topic Artificial Intelligence
url https://arxiv.org/abs/2603.01055