@inproceedings{9dde5b86fe014de6889634d96e38f94d,
title = "Performance Improvement Method of the Video Visual Relation Detection with Multi-modal Feature Fusion",
abstract = "Video visual relation detection is a novel research problem that aims to detect instances of visual relations of interest in a video. In this paper, we propose a performance improvement method of the video visual relation detection with multi-modal feature fusion. First, we introduce a spatial feature extraction method that is designed to include the relative positions of objects itself and between objects in the image. Next, we suggest a relationship classifier that is designed to accommodate the complexity of the input features. Our proposed method achieves 6.65 mAP, and ranked the 2nd place in the visual relation detection task of Video Relation Understanding Challenge (VRU), the ACM Multimedia 2020.",
keywords = "component, formatting, insert, style, styling",
author = "Kim, {Kwang Ju} and Kim, {Pyong Kun} and Lim, {Kil Taek} and Lee, {Jong Taek}",
note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 4th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2022 ; Conference date: 21-02-2022 Through 24-02-2022",
year = "2022",
doi = "10.1109/ICAIIC54071.2022.9722699",
language = "English",
series = "4th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2022 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "87--91",
booktitle = "4th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2022 - Proceedings",
address = "United States",
}