End-to-End Concept Word Detection for Video Captioning, Retrieval, and Question Answering 论文

2017引用 228
DOI
Multimodal Machine Learning ApplicationsHuman Pose and Action RecognitionDomain Adaptation and Few-Shot Learning
人工智能Domain Adaptation and Few-Shot LearningMultimodal Machine Learning ApplicationsHuman Pose and Action Recognition
相关技术:Multimodal Machine Learning ApplicationsDomain Adaptation and Few-Shot LearningHuman Pose and Action Recognition
关系图谱

End-to-End Concept Word Detection for Video Captioning, Retrieval, and Question Answering · 作者

G

Gunhee Kim

J

Jongwook Choi

H

Hyungjin Ko

Y

Youngjae Yu