Early action recognition with category exclusion using policy-based reinforcement learning

The goal of early action recognition is to predict action label when the sequence is partially observed. The existing methods treat the early action recognition task as sequential classification problems on different observation ratios of an action sequence. Since these models are trained by differe...

Full description

Saved in:
Bibliographic Details
Main Authors: Weng, Junwu, Jiang, Xudong, Zheng, Wei-Long, Yuan, Junsong
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/141973
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English