English

A-CAP: Anticipation Captioning with Commonsense Knowledge

Computer Vision and Pattern Recognition 2023-04-14 v1

Abstract

Humans possess the capacity to reason about the future based on a sparse collection of visual cues acquired over time. In order to emulate this ability, we introduce a novel task called Anticipation Captioning, which generates a caption for an unseen oracle image using a sparsely temporally-ordered set of images. To tackle this new task, we propose a model called A-CAP, which incorporates commonsense knowledge into a pre-trained vision-language model, allowing it to anticipate the caption. Through both qualitative and quantitative evaluations on a customized visual storytelling dataset, A-CAP outperforms other image captioning methods and establishes a strong baseline for anticipation captioning. We also address the challenges inherent in this task.

Keywords

Cite

@article{arxiv.2304.06602,
  title  = {A-CAP: Anticipation Captioning with Commonsense Knowledge},
  author = {Duc Minh Vo and Quoc-An Luong and Akihiro Sugimoto and Hideki Nakayama},
  journal= {arXiv preprint arXiv:2304.06602},
  year   = {2023}
}

Comments

Accepted to CVPR 2023

R2 v1 2026-06-28T10:04:51.962Z