Cross-modal Contrastive Learning with Asymmetric Co-attention Network for Video Moment Retrieval

TL;DR

This paper introduces a cross-modal contrastive learning approach with an asymmetric co-attention network for video moment retrieval, addressing information asymmetry and improving performance with fewer parameters.

Contribution

It proposes an asymmetric co-attention network combined with momentum contrastive loss to enhance video-text interaction and retrieval accuracy, with efficient parameter usage.

Findings

Outperforms state-of-the-art on TACoS dataset

Achieves comparable results on ActivityNet Captions

Uses fewer parameters than baseline models

Abstract

Video moment retrieval is a challenging task requiring fine-grained interactions between video and text modalities. Recent work in image-text pretraining has demonstrated that most existing pretrained models suffer from information asymmetry due to the difference in length between visual and textual sequences. We question whether the same problem also exists in the video-text domain with an auxiliary need to preserve both spatial and temporal information. Thus, we evaluate a recently proposed solution involving the addition of an asymmetric co-attention network for video grounding tasks. Additionally, we incorporate momentum contrastive loss for robust, discriminative representation learning in both modalities. We note that the integration of these supplementary modules yields better performance compared to state-of-the-art models on the TACoS dataset and comparable results on ActivityNet Captions, all while utilizing significantly fewer parameters with respect to baseline.