Section: New Software and Platforms

LOUPE

Learnable mOdUle for Pooling fEatures

Keywords: Video analysis - Computer vision

Functional Description: LOUPE (Learnable mOdUle for Pooling fEatures) is a Tensorflow toolbox that implements several modules for pooling features such as NetVLAD, NetRVLAD, NetFV and Soft-DBoW. It also allows to use their Gated version. This toolbox was mainly use in the winning approach of the Youtube 8M Large Scale Video Understanding challenge

• Participants: Antoine Miech, Ivan Laptev and Josef Sivic

• Contact: Antoine Miech

• Publication: Learning from Video and Text via Large-Scale Discriminative Clustering

• URL: https://github.com/antoine77340/LOUPE