Papers by Kimihiro Hasegawa
ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding (2025.naacl-long)
Copied to clipboard
Kimihiro Hasegawa, Wiradee Imrattanatrai, Zhi-Qi Cheng, Masaki Asada, Susan Holm, Yuran Wang, Ken Fukuda, Teruko Mitamura
| Challenge: | Existing studies typically provide traditional, but less practical evaluation testbeds for multimodal systems. |
| Approach: | They propose a novel evaluation dataset, ProMQA, to measure the advancement of systems in application-oriented scenarios. |
| Outcome: | The proposed evaluation dataset reveals a significant gap between human and competitive multimodal models. |