CONQUER: Contextual Query-aware Ranking for Video Corpus Moment Retrieval

TL;DR

CONQUER introduces a novel approach for video moment retrieval by effectively utilizing query context through multi-modal fusion and joint representation, improving localization accuracy in large video corpora.

Contribution

The paper presents a new model, CONQUER, that enhances video moment retrieval by integrating query context into multi-modal fusion and joint video-query representation learning.

Findings

Improved performance on TVR and DiDeMo datasets.

Effective query-aware multi-modal fusion enhances localization.

Joint representation captures query-specific multi-modal signals.

Abstract

This paper tackles a recently proposed Video Corpus Moment Retrieval task. This task is essential because advanced video retrieval applications should enable users to retrieve a precise moment from a large video corpus. We propose a novel CONtextual QUery-awarE Ranking~(CONQUER) model for effective moment localization and ranking. CONQUER explores query context for multi-modal fusion and representation learning in two different steps. The first step derives fusion weights for the adaptive combination of multi-modal video content. The second step performs bi-directional attention to tightly couple video and query as a single joint representation for moment localization. As query context is fully engaged in video representation learning, from feature fusion to transformation, the resulting feature is user-centered and has a larger capacity in capturing multi-modal signals specific to query. We conduct studies on two datasets, TVR for closed-world TV episodes and DiDeMo for open-world user-generated videos, to investigate the potential advantages of fusing video and query online as a joint representation for moment retrieval.