ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 4D Effect Classification by Encoding CNN Features
Cited 1 time in scopus Download 2 time Share share facebook twitter linkedin kakaostory
저자
시아다리, 한미경, 윤현진
발행일
201709
출처
International Conference on Image Processing (ICIP) 2017, pp.1812-1816
DOI
https://dx.doi.org/10.1109/ICIP.2017.8296594
협약과제
17ZF1200, 실감콘텐츠 산업 활성화를 위한 XD미디어 핵심 기술 개발, 한미경
초록
4D effects are physical effects simulated in sync with videos, movies, and games to augment the events occurring in a story or a virtual world. Types of 4D effects commonly used for the immersive media may include seat motion, vibration, flash, wind, water, scent, thunderstorm, snow, and fog. Currently, the recognition of physical effects from a video is mainly conducted by human experts. Although 4D effects are promising in giving immersive experience and entertainment, this manual production has been the main obstacle to faster and wider application of 4D effects. In this paper, we utilize pretrained models of Convolutional Neural Networks (CNNs) to extract local visual features and propose a new representation method that combines extracted features into video level features. Classification tasks are conducted by employing Support Vector Machine (SVM). Comprehensive experiments are performed to investigate different architecture of CNNs and different type of features for 4D effect classification task and compare baseline average pooling method with our proposed video level representation. Our framework outperforms the baseline up to 2-3% in terms of mean average precision (mAP).
키워드
4D Effect, Classification, Convolutional Neural Networks (CNNs), Video Representation
KSP 제안 키워드
CNN features, Classification task, Convolution neural network(CNN), Immersive experience, Immersive media, Manual production, Pooling method, Representation method, Support VectorMachine(SVM), Video Representation, Virtual world