arxivst stuff from arxiv that you should probably bookmark

An Analysis of Action Recognition Datasets for Language and Vision Tasks

Abstract · Apr 24, 2017 10:38 ·

horse labels actions hoi verb action riding cs-cl cs-cv

Arxiv Abstract

  • Spandana Gella
  • Frank Keller

A large amount of recent research has focused on tasks that combine language and vision, resulting in a proliferation of datasets and methods. One such task is action recognition, whose applications include image annotation, scene under- standing and image retrieval. In this survey, we categorize the existing ap- proaches based on how they conceptualize this problem and provide a detailed review of existing datasets, highlighting their di- versity as well as advantages and disad- vantages. We focus on recently devel- oped datasets which link visual informa- tion with linguistic resources and provide a fine-grained syntactic and semantic anal- ysis of actions in images.

Read the paper (pdf) »