Skip to content

Add dataset: Dense-WebVid-CoVR (Video + Text → Video) #4949

Description

@deep9539

dataset link on Hugging dataset

https://github.com/OmkarThawakar/BSE-CoVR

Arxiv link

https://arxiv.org/abs/2508.14039

Description of the dataset

This task evaluates dense, fine-grained compositional retrieval using video inputs. Given a source reference video and a text query detailing a specific modification or edit to the scene/action, the model must accurately retrieve the target video that matches the combined video-and-text context.

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