Exploiting Multi-Modal Interactions: A Unified Framework
Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence. Pages 1120-1124.
Abstract
Given an imagebase with tagged images, four types of tasks an be executed, i.e., content-based image retrieval, image annotation, text-based image retrieval, and query expansion. For any of these tasks the similarity on the concerned type of objects is essential. In this paper, we propose a framework to tackle these four tasks from a unified view. The essence of the framework is to estimate similarities by exploiting the interactions between objects of different modality. Experiments show that the proposed method can improve similarity estimation, and based on the improved similarity estimation, some simple methods can achieve better performances than some state-of-the-art techniques.Ming Li, Xiao-Bing Xue, Zhi-Hua Zhou
@inproceedings{ijcai2009p189,
title = {Exploiting Multi-Modal Interactions: A Unified Framework},
author = {Li, Ming and Xue, Xiao-Bing and Zhou, Zhi-Hua},
booktitle = {Proceedings of the Twenty-First International Joint Conference on
Artificial Intelligence, {IJCAI-09}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Hiroaki Kitano},
pages = {1120--1124},
year = {2009},
url = {https://ijcai.org/proceedings/2009/189},
}
TY - CPAPER TI - Exploiting Multi-Modal Interactions: A Unified Framework AU - Li, Ming AU - Xue, Xiao-Bing AU - Zhou, Zhi-Hua T2 - Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence, IJCAI-09 PB - International Joint Conferences on Artificial Intelligence PY - 2009 SP - 1120 EP - 1124 UR - https://ijcai.org/proceedings/2009/189 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
