Skip to content

Changes

View changes from to


On December 2, 2024 at 10:01:56 PM UTC, Gravatar admin:
  • Updated description of NLVR2 from

    The NLVR2 dataset is a visual reasoning dataset that consists of pairs of related images along with a natural language statement. The task is to determine whether the statement accurately describes both images.
    to
    The dataset used in the paper is a set of sequential vision-and-language tasks, where each task consists of an image and a text input.


  • Added the following tags to NLVR2


  • Changed value of field defined_in to https://doi.org/10.48550/arXiv.2405.17613 in NLVR2


  • Changed value of field extra_authors to [{'extra_author': 'Stephanie Zhou', 'orcid': ''}, {'extra_author': 'Ally Zhang', 'orcid': ''}, {'extra_author': 'Iris Zhang', 'orcid': ''}, {'extra_author': 'Hua-jun Bai', 'orcid': ''}] in NLVR2


  • Changed value of field citation to ['https://doi.org/10.48550/arXiv.2303.14423'] in NLVR2


  • Changed value of field landing_page to https://arxiv.org/abs/1811.00491 in NLVR2


  • Deleted resource Original Metadata from NLVR2



Before browse our site, please accept our cookies policy