상세정보
학술대회
Learning a Video-Text Joint Embedding using Korean Tagged Movie Clips
- 발행일
- 202010
- 출처
- International Conference on Information and Communication Technology Convergence (ICTC) 2020, pp.1158-1160
- 협약과제
- 20ZH1200, 초실감 입체공간 미디어·콘텐츠 원천기술연구, 이태진
- 초록
- For intelligent multimedia services, video contents understanding is a major challenge. In the existing video retrieval approaches, manual descriptive sentence data is necessary for retrieving desired videos against user's search intent. To overcome these limitations, modeling visual concepts included in video and sentence is necessary to learn a mapping of video and text into a common vector space, where relevant videos and texts are close to each other. In this study, we construct a new dataset containing 250 Korean movies with manual text description in Korean. Also, video-text joint embedding model and its quantitative and qualitative search results are introduced. With our proposed model, video manual tagging is no longer necessary for video retrieval services.
- KSP 제안 키워드
- Embedding model, Intelligent Multimedia, Multimedia Service, Proposed model, Search intent, Search results, Video and text, Video contents, Video retrieval, vector space, visual concepts