Skip to Main content Skip to Navigation
Conference papers

Localizing Moments in Video with Natural Language

Abstract : We consider retrieving a specific temporal segment, or moment, from a video given a natural language text description. Methods designed to retrieve whole video clips with natural language determine what occurs in a video but not when. To address this issue, we propose the Moment Context Network (MCN) which effectively localizes natural language queries in videos by integrating local and global video features over time. A key obstacle to training our MCN model is that current video datasets do not include pairs of localized video segments and referring expressions, or text descriptions which uniquely identify a corresponding moment. Therefore, we collect the Distinct Describable Moments (DiDeMo) dataset which consists of over 10,000 unedited, personal videos in diverse visual settings with pairs of localized video segments and referring expressions. We demonstrate that MCN outperforms several baseline methods and believe that our initial results together with the release of DiDeMo will inspire further research on localizing video moments with natural language.
Document type :
Conference papers
Complete list of metadata

Cited literature [53 references]  Display  Hide  Download

https://hal.inria.fr/hal-01678699
Contributor : Josef Sivic <>
Submitted on : Tuesday, January 9, 2018 - 1:05:52 PM
Last modification on : Tuesday, May 4, 2021 - 2:06:03 PM

Links full text

Identifiers

  • HAL Id : hal-01678699, version 1
  • ARXIV : 1708.01641

Collections

Citation

Lisa Anne Hendricks, Oliver Wang, Eli Shechtman, Josef Sivic, Trevor Darrell, et al.. Localizing Moments in Video with Natural Language. IEEE International Conference on Computer Vision - ICCV 2017, Oct 2017, Venice, Italy. ⟨hal-01678699⟩

Share

Metrics

Record views

359