Progressive Teacher-student Learning for Early Action Prediction

Xionghui Wang, Jian-Fang Hu, Jianhuang Lai, Jianguo Zhang, Wei-Shi Zheng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

81 Citations (Scopus)
195 Downloads (Pure)


The goal of early action prediction is to recognize actions from partially observed videos with incomplete action executions, which is quite different from action recognition. Predicting early actions is very challenging since the partially observed videos do not contain enough action information for recognition. In this paper, we aim at improving early action prediction by proposing a novel teacherstudent learning framework. Our framework involves a teacher model for recognizing actions from full videos, a student model for predicting early actions from partial videos, and a teacher-student learning block for distilling progressive knowledge from teacher to student, crossing different tasks. Extensive experiments on three public action datasets show that the proposed progressive teacher-student learning framework can consistently improve performance of early action prediction model. We have also reported the state-of-the-art performances for early action prediction on all of these sets.
Original languageEnglish
Title of host publication2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Number of pages10
ISBN (Electronic)9781728132938
ISBN (Print)9781728132945
Publication statusPublished - 9 Jan 2020
EventConference on Computer Vision and Pattern Recognition 2019 - Long Beach, United States
Duration: 16 Jun 201920 Jun 2019

Publication series

ISSN (Print)2575-7075
ISSN (Electronic)1063-6919


ConferenceConference on Computer Vision and Pattern Recognition 2019
Abbreviated titleCVPR 2019
Country/TerritoryUnited States
CityLong Beach
Internet address


  • Action Recognition
  • Deep Learning
  • Video Analytics
  • Vision Applications and Systems

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Progressive Teacher-student Learning for Early Action Prediction'. Together they form a unique fingerprint.

Cite this