학술논문
NICE: CVPR 2023 Challenge on Zero-shot Image Captioning
Document Type
Working Paper
Author
Kim, Taehoon; Ahn, Pyunghwan; Kim, Sangyun; Lee, Sihaeng; Marsden, Mark; Sala, Alessandra; Kim, Seung Hwan; Han, Bohyung; Lee, Kyoung Mu; Lee, Honglak; Bae, Kyounghoon; Wu, Xiangyu; Gao, Yi; Zhang, Hailiang; Yang, Yang; Guo, Weili; Lu, Jianfeng; Oh, Youngtaek; Cho, Jae Won; Kim, Dong-jin; Kweon, In So; Kim, Junmo; Kang, Wooyoung; Jhoo, Won Young; Roh, Byungseok; Mun, Jonghwan; Oh, Solgil; Ak, Kenan Emir; Lee, Gwang-Gook; Xu, Yan; Shen, Mingwei; Hwang, Kyomin; Shin, Wonsik; Lee, Kamin; Park, Wonhark; Lee, Dongkwan; Kwak, Nojun; Wang, Yujin; Wang, Yimu; Gu, Tiancheng; Lv, Xingchang; Sun, Mingmao
Source
Subject
Language
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.
Comment: Tech report, project page https://nice.lgresearch.ai/
Comment: Tech report, project page https://nice.lgresearch.ai/