ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Performance Improvement of Video Classification using Generated Labeled Data
Cited 0 time in scopus Download 0 time Share share facebook twitter linkedin kakaostory
저자
이호재, 손정우, 김선중
발행일
202010
출처
International Conference on Information and Communication Technology Convergence (ICTC) 2020, pp.1417-1419
DOI
https://dx.doi.org/10.1109/ICTC49870.2020.9289479
협약과제
20ZH1200, 초실감 입체공간 미디어·콘텐츠 원천기술연구, 이태진
초록
As the development of deep learning techniques is growing, applications using deep learning have been spreading. Among various applications, images and videos related applications are the most common example of the practical deep learning application. The performances in those applications have been boosted by adopting deep learning techniques. To achieve performance, securing a large amount of data-oriented to target tasks is crucial. In this paper, we have designed the experiments to examine the effect of generated data on both where the dataset can be easily collected and hard to secure. We use state-of-the-art generative model, MCnet, to enlarge the Sexually Harmful Contents dataset and UCF-101. By training C3D with augmented data, we measure the classification performance. The generated labeled data have increased the performance by 7% on harmful content detection.
키워드
deep learning, generative model, video classification
KSP 제안 키워드
Classification Performance, Content Detection, Data-oriented, Deep learning application, Labeled data, Video classification, deep learning(DL), generative models, images and videos, performance improvement, state-of-The-Art