Multi-Query Video Retrieval

TL;DR

This paper explores multi-query video retrieval, demonstrating that using multiple descriptions improves model evaluation, reduces dataset noise impact, and enhances retrieval performance and generalization in practical applications.

Contribution

It introduces the multi-query retrieval setting, showing its effectiveness in mitigating dataset noise and improving model training and evaluation.

Findings

Multi-query retrieval correlates better with human judgment.

Multi-query training improves model performance.

Mitigates dataset annotation noise.

Abstract

Retrieving target videos based on text descriptions is a task of great practical value and has received increasing attention over the past few years. Despite recent progress, imperfect annotations in existing video retrieval datasets have posed significant challenges on model evaluation and development. In this paper, we tackle this issue by focusing on the less-studied setting of multi-query video retrieval, where multiple descriptions are provided to the model for searching over the video archive. We first show that multi-query retrieval task effectively mitigates the dataset noise introduced by imperfect annotations and better correlates with human judgement on evaluating retrieval abilities of current models. We then investigate several methods which leverage multiple queries at training time, and demonstrate that the multi-query inspired training can lead to superior performance and better generalization. We hope further investigation in this direction can bring new insights on building systems that perform better in real-world video retrieval applications.