An Analysis of Action Recognition Datasets for Language and Vision Tasks
This is an incremental survey that helps researchers in computer vision and natural language processing by organizing and evaluating datasets for action recognition tasks.
The paper surveys existing datasets for action recognition in language-vision tasks, categorizing approaches and reviewing dataset diversity, advantages, and disadvantages, with a focus on recent datasets linking visual information to linguistic resources for fine-grained analysis.
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.