Skip to content

Add dataset: WebVid-CoVR (Image + Text → Video) #4948

Description

@deep9539

dataset link on Hugging dataset

https://imagine.enpc.fr/~ventural/covr/

Arxiv link

https://arxiv.org/abs/2308.14746

Description of the dataset

This task focuses on retrieving videos based on a multimodal query. The query consists of a static reference image (specifically, the middle frame of a video) paired with a text prompt that specifies an action, temporal change, or modification. The model must synthesize these two inputs to retrieve the correct corresponding video.

Metadata

Metadata

Assignees

No one assigned

    Labels

    new datasetIssues related to adding a new task or dataset

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions