ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Recognition of Meaningful Human Actions for Video Annotation Using EEG Based User Responses
Cited 7 time in scopus Download 5 time Share share facebook twitter linkedin kakaostory
저자
문진영, 권용진, 강규창, 배창석, 윤완철
발행일
201501
출처
International Conference on MultiMedia Modeling (MMM) 2015 (LNCS 8936), v.8936, pp.447-457
DOI
https://dx.doi.org/10.1007/978-3-319-14442-9_50
협약과제
14MS4500, (1세부) 실시간 대규모 영상 데이터 이해·예측을 위한 고성능 비주얼 디스커버리 플랫폼 개발, 박경
초록
To provide interesting videos, it is important to generate relevant tags and annotations that describe the whole video or its segment efficiently. Because generating annotations and tags is a time-consuming process, it is essential for analyzing videos without human intervention. Although there have been many studies of implicit human-centered tagging using bio-signals, most of them focus on affective tagging and tag relevance assessment. This paper proposes binary and unary classification models that recognize actions meaningful to users in videos, for example jumps in the figure skating program, using EEG features of band power (BP) values and asymmetry scores (AS). As a result, the binary and binary classification models achieved the best balanced accuracies of 52.86% and 50.06% respectively. The binary classification models showed high specificity on non-jump actions and the unary classification models showed high sensitivity on jump actions.
키워드
And implicit tagging, Classification, EEG, Human action recognition, Signal processing, Video, Video annotation
KSP 제안 키워드
Band Power, Binary Classification, Classification models, EEG features, High Sensitivity, High specificity, Signal Processing, Tag Relevance, Video Annotation, bio-signal, human action recognition