NICE: CVPR 2023 Challenge on Zero-shot Image Captioning
Abstract
In this report, we introduce NICE (New frontiers for zero-shot Image Captioning Evaluation) project and share the results and outcomes of 2023 challenge. This project is designed to challenge the computer vision community to develop robust image captioning models that advance the state-of-the-art both in terms of accuracy and fairness. Through the challenge, the image captioning models were tested using a new evaluation dataset that includes a large variety of visual concepts from many domains. There was no specific training data provided for the challenge, and therefore the challenge entries were required to adapt to new types of image descriptions that had not been seen during training. This report includes information on the newly proposed NICE dataset, evaluation methods, challenge results, and technical details of top-ranking entries. We expect that the outcomes of the challenge will contribute to the improvement of AI models on various vision-language tasks.
Cite
@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}
}
Comments
Tech report, project page https://nice.lgresearch.ai/