8000 How can I train a spatio-temporal action detection network only for action recognition? · Issue #1443 · open-mmlab/mmaction2 · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
How can I train a spatio-temporal action detection network only for action recognition? #1443
Closed
@Aarontncl

Description

@Aarontncl

Now I have an action recognition dataset and I want to combine temporal and object-related information for better recognition performance. I wonder how can I train the provided spatio-temporal action detection network in mmaction2 on the action recognition dataset and use it to perform action recognition?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions

      0