EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval

TL;DR

EgoCVR introduces a new egocentric video benchmark for fine-grained composed video retrieval, highlighting the need for better temporal understanding and proposing a re-ranking method that improves retrieval performance.

Contribution

The paper presents EgoCVR, a large-scale egocentric video benchmark for fine-grained retrieval, and proposes a simple, training-free re-ranking framework to enhance retrieval accuracy.

Findings

Existing methods lack high-quality temporal understanding.

The proposed re-ranking framework significantly improves retrieval results.

EgoCVR provides a challenging benchmark for future research.

Abstract

In Composed Video Retrieval, a video and a textual description which modifies the video content are provided as inputs to the model. The aim is to retrieve the relevant video with the modified content from a database of videos. In this challenging task, the first step is to acquire large-scale training datasets and collect high-quality benchmarks for evaluation. In this work, we introduce EgoCVR, a new evaluation benchmark for fine-grained Composed Video Retrieval using large-scale egocentric video datasets. EgoCVR consists of 2,295 queries that specifically focus on high-quality temporal video understanding. We find that existing Composed Video Retrieval frameworks do not achieve the necessary high-quality temporal video understanding for this task. To address this shortcoming, we adapt a simple training-free method, propose a generic re-ranking framework for Composed Video Retrieval, and demonstrate that this achieves strong results on EgoCVR. Our code and benchmark are freely available at https://github.com/ExplainableML/EgoCVR.