FedVMR: A New Federated Learning method for Video Moment Retrieval

TL;DR

FedVMR introduces a federated learning approach for video moment retrieval, enabling privacy-preserving, large-scale training across decentralized data silos, which was previously unaddressed in this domain.

Contribution

This paper pioneers the application of federated learning to video moment retrieval, proposing FedVMR for secure, scalable training in decentralized environments.

Findings

Demonstrates effectiveness of FedVMR on benchmark datasets.

First to address federated learning in VMR.

Enables privacy-preserving large-scale VMR training.

Abstract

Despite the great success achieved, existing video moment retrieval (VMR) methods are developed under the assumption that data are centralizedly stored. However, in real-world applications, due to the inherent nature of data generation and privacy concerns, data are often distributed on different silos, bringing huge challenges to effective large-scale training. In this work, we try to overcome above limitation by leveraging the recent success of federated learning. As the first that is explored in VMR field, the new task is defined as video moment retrieval with distributed data. Then, a novel federated learning method named FedVMR is proposed to facilitate large-scale and secure training of VMR models in decentralized environment. Experiments on benchmark datasets demonstrate its effectiveness. This work is the very first attempt to enable safe and efficient VMR training in decentralized scene, which is hoped to pave the way for further study in the related research field.