Skip to main navigation Skip to search Skip to main content

Learning multimodal representations for unseen activities

  • Indiana University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

11 Scopus citations

Abstract

We present a method to learn a joint multimodal representation space that enables recognition of unseen activities in videos. We first compare the effect of placing various constraints on the embedding space using paired text and video data. We also propose a method to improve the joint embedding space using an adversarial formulation, allowing it to benefit from unpaired text and video data. By using unpaired text data, we show the ability to learn a representation that better captures unseen activities. In addition to testing on publicly available datasets, we introduce a new, large-scale text/video dataset. We experimentally confirm that using paired and unpaired data to learn a shared embedding space benefits three difficult tasks (i) zero-shot activity classification, (ii) unsupervised activity discovery, and (iii) unseen activity captioning, outperforming the state-of-the-arts.

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages506-515
Number of pages10
ISBN (Electronic)9781728165530
DOIs
StatePublished - Mar 2020
Event2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020 - Snowmass Village, United States
Duration: Mar 1 2020 → Mar 5 2020

Publication series

NameProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020

Conference

Conference2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020
Country/TerritoryUnited States
CitySnowmass Village
Period03/1/20 → 03/5/20

Fingerprint

Dive into the research topics of 'Learning multimodal representations for unseen activities'. Together they form a unique fingerprint.

Cite this