ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Improved Human-Object Interaction Detection through On-the-Fly Stacked Generalization
Cited 2 time in scopus Download 9 time Share share facebook twitter linkedin kakaostory
저자
이건우, 윤기민, 조정찬
발행일
202103
출처
IEEE Access, v.9, pp.34251-34263
ISSN
2169-3536
출판사
IEEE
DOI
https://dx.doi.org/10.1109/ACCESS.2021.3061208
협약과제
20HS5100, (딥뷰-1세부) 실시간 대규모 영상 데이터 이해·예측을 위한 고성능 비주얼 디스커버리 플랫폼 개발, 배유석
초록
Human-object interaction (HOI) detection, which finds the relationships between humans and objects, is an important research area, but current HOI detection performance is unsatisfactory. One of the main problems is that CNN-based HOI detection algorithms fail to predict correct outputs for unseen test data based on a limited number of available training examples. Herein, we propose a novel framework for HOI detection called the on-the-fly stacked generalization deep neural network (OSGNet). OSGNet consists of three main components: (1) feature extraction modules, (2) HOI relationship detection networks, and (3) a meta-learner for combining the outputs of sub-models. Here, components (1) and (2) are considered to be sub-models. Any task-based feature extraction modules, such as classification or human pose estimation modules, can be used as sub-models. To achieve on-the-fly stacked generalization, the sub-models and meta-learner are trained simultaneously. The sub-models are trained to provide complementary information, and the meta-learner improves the generalization performance for unseen test data. Extensive experiments demonstrate that the proposed method achieves state-of-the-art accuracy, particularly in cases involving rare classes.
키워드
action recognition, Deep learning, human pose estimation, human-object interaction
KSP 제안 키워드
Action recognition, Deep neural network(DNN), Detection algorithm, Feature extractioN, Generalization performance, Human pose estimation, Human-Object Interaction, Interaction detection, Stacked generalization, Sub-models, Task-Based
본 저작물은 크리에이티브 커먼즈 저작자 표시 (CC BY) 조건에 따라 이용할 수 있습니다.
저작자 표시 (CC BY)