Learning a Text-Video Embedding from Incomplete and Heterogeneous Data

TL;DR

This paper introduces a Mixture-of-Embedding-Experts model that learns robust text-video embeddings from heterogeneous and incomplete data sources, improving video retrieval performance.

Contribution

The paper presents a novel MEE model capable of handling missing modalities and learning from diverse datasets, advancing text-video embedding methods.

Findings

Significant improvements in video retrieval accuracy.

Outperforms previous methods on MPII and MSR-VTT datasets.

Effective handling of incomplete and heterogeneous data sources.

Abstract

Joint understanding of video and language is an active research area with many applications. Prior work in this domain typically relies on learning text-video embeddings. One difficulty with this approach, however, is the lack of large-scale annotated video-caption datasets for training. To address this issue, we aim at learning text-video embeddings from heterogeneous data sources. To this end, we propose a Mixture-of-Embedding-Experts (MEE) model with ability to handle missing input modalities during training. As a result, our framework can learn improved text-video embeddings simultaneously from image and video datasets. We also show the generalization of MEE to other input modalities such as face descriptors. We evaluate our method on the task of video retrieval and report results for the MPII Movie Description and MSR-VTT datasets. The proposed MEE model demonstrates significant improvements and outperforms previously reported methods on both text-to-video and video-to-text retrieval tasks. Code is available at: https://github.com/antoine77340/Mixture-of-Embedding-Experts