https://scholars.lib.ntu.edu.tw/handle/123456789/607404
標題: | LifeConcept: An Interactive Approach for Multimodal Lifelog Retrieval through Concept Recommendation | 作者: | Ang W.-H Yen A.-Z Chu T.-T Huang H.-H HSIN-HSI CHEN |
關鍵字: | image retrieval;interactive system;multimodal retrieval;visual lifelogging;Benchmarking activity;Interactive approach;Interactive retrieval;Number of peoples;Recommendation methods;Retrieval process;Textual query;Visual concept;Semantics | 公開日期: | 2021 | 起(迄)頁: | 47-51 | 來源出版物: | LSC 2021 - Proceedings of the 4th Annual Lifelog Search Challenge | 摘要: | The major challenge in visual lifelog retrieval is the semantic gap between textual queries and visual concepts. This paper presents our work on the Lifelog Search Challenge 2021 (LSC'21), an annual comparative benchmarking activity for comparing approaches to interactive retrieval from multimodal lifelogs. We propose LifeConcept, an interactive lifelog search system that is aimed at accelerating the retrieval process and retrieving more precise results. In this work, we introduce several new features such as the number of people, location cluster, and object with color. Moreover, we obtain visual concepts from the images with computer vision models and propose a concept recommendation method to reduce the semantic gap. In this way, users can efficiently set up the related conditions for their requirements and search the desired images with appropriate query terms based on the suggestion. ? 2021 ACM. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85114276232&doi=10.1145%2f3463948.3469070&partnerID=40&md5=4b5984d012a7a9b0cd5e96461884602f https://scholars.lib.ntu.edu.tw/handle/123456789/607404 |
DOI: | 10.1145/3463948.3469070 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。