arXiv:1907.06987
A Short Note on the Kinetics-700 Human Action Dataset
원문 초록
We describe an extension of the DeepMind Kinetics human action dataset from 600 classes to 700 classes, where for each class there are at least 600 video clips from different YouTube videos. This paper details the changes introduced for this new release of the dataset, and includes a comprehensive set of statistics as well as baseline results using the I3D neural network architecture.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos
Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition
Make Your Training Flexible: Towards Deployment-Efficient Video Models
Temporal Action Localization with Cross Layer Task Decoupling and Refinement
KNN-MMD: Cross Domain Wireless Sensing via Local Distribution Alignment
Towards Universal Soccer Video Understanding
토론
이 논문과 연결된 포럼 글이 아직 없습니다.