NICE：CVPR 2023 零样本图像描述挑战赛
计算机视觉与模式识别
2023-09-12 v3
摘要
在本报告中，我们介绍 NICE（零样本图像描述评估新前沿）项目并分享 2023 年挑战赛的结果与成果。该项目旨在挑战计算机视觉界开发鲁棒的图像描述模型，在准确率和公平性上推进最先进水平。通过挑战赛，图像描述模型使用一个包含来自众多领域的大量视觉概念的新评估数据集进行了测试。挑战赛未提供特定训练数据，因此参赛方案必须适应训练期间未见过的新类型图像描述。本报告包含新提出的 NICE 数据集、评估方法、挑战赛结果以及排名靠前方案的技术细节。我们期望挑战赛的成果将有助于改进各种视觉-语言任务上的 AI 模型。
引用
@article{arxiv.2309.01961,
title = {NICE: CVPR 2023 Challenge on Zero-shot Image Captioning},
author = {Taehoon Kim and Pyunghwan Ahn and Sangyun Kim and Sihaeng Lee and Mark Marsden and Alessandra Sala and Seung Hwan Kim and Bohyung Han and Kyoung Mu Lee and Honglak Lee and Kyounghoon Bae and Xiangyu Wu and Yi Gao and Hailiang Zhang and Yang Yang and Weili Guo and Jianfeng Lu and Youngtaek Oh and Jae Won Cho and Dong-jin Kim and In So Kweon and Junmo Kim and Wooyoung Kang and Won Young Jhoo and Byungseok Roh and Jonghwan Mun and Solgil Oh and Kenan Emir Ak and Gwang-Gook Lee and Yan Xu and Mingwei Shen and Kyomin Hwang and Wonsik Shin and Kamin Lee and Wonhark Park and Dongkwan Lee and Nojun Kwak and Yujin Wang and Yimu Wang and Tiancheng Gu and Xingchang Lv and Mingmao Sun},
journal= {arXiv preprint arXiv:2309.01961},
year = {2023}
}
备注
Tech report, project page https://nice.lgresearch.ai/