Skip to main navigation Skip to search Skip to main content

Text-Derived Knowledge Helps Vision: A Simple Cross-modal Distillation for Video-based Action Anticipation

  • Stony Brook University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Anticipating future actions in a video is useful for many autonomous and assistive technologies. Most prior action anticipation work treat this as a vision modality problem, where the models learn the task information primarily from the video features in the action anticipation datasets. However, knowledge about action sequences can also be obtained from external textual data. In this work, we show how knowledge in pretrained language models can be adapted and distilled into vision-based action anticipation models. We show that a simple distillation technique can achieve effective knowledge transfer and provide consistent gains on a strong vision model (Anticipative Vision Transformer) for two action anticipation datasets (3.5% relative gain on EGTEA-GAZE+ and 7.2%

Original languageEnglish
Title of host publicationEACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Findings of EACL 2023
PublisherAssociation for Computational Linguistics (ACL)
Pages1837-1852
Number of pages16
ISBN (Electronic)9781959429470
StatePublished - 2023
Event17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Findings of EACL 2023 - Dubrovnik, Croatia
Duration: May 2 2023May 6 2023

Publication series

NameEACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Findings of EACL 2023

Conference

Conference17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Findings of EACL 2023
Country/TerritoryCroatia
CityDubrovnik
Period05/2/2305/6/23

Fingerprint

Dive into the research topics of 'Text-Derived Knowledge Helps Vision: A Simple Cross-modal Distillation for Video-based Action Anticipation'. Together they form a unique fingerprint.

Cite this