The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction

Alexandros G Stergiou*, Dima Damen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

11 Downloads (Pure)

Abstract

Early action prediction deals with inferring the ongoing action from partially-observed videos, typically at the outset of the video. We propose a bottleneck-based attention model that captures the evolution of the action, through progressive sampling over fine-to-coarse scales. Our proposed Temporal Progressive (TemPr) model is composed of multiple attention towers, one for each scale. The predicted action label is based on the collective agreement considering confidences of these towers. Extensive experiments over four video datasets showcase state-of-the-art performance on the task of Early Action Prediction across a range of encoder architectures. We demonstrate the effectiveness and consistency of TemPr through detailed ablations. † † Code is available at: https://tinyurl.com/temprog
Original languageEnglish
Title of host publication2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages14709-14719
Number of pages11
ISBN (Electronic)9798350301298
ISBN (Print)9798350301304
DOIs
Publication statusPublished - 22 Aug 2023
EventIEEE/CVF Computer Vision and Pattern Recognition - Vancouver, Canada
Duration: 18 Jun 202323 Jun 2023

Publication series

NameIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherIEEE
ISSN (Print)1063-6919
ISSN (Electronic)2575-7075

Conference

ConferenceIEEE/CVF Computer Vision and Pattern Recognition
Abbreviated titleCVPR
Country/TerritoryCanada
CityVancouver
Period18/06/2323/06/23

Fingerprint

Dive into the research topics of 'The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction'. Together they form a unique fingerprint.

Cite this