CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding

TL;DR

CONE is a novel framework that improves long video temporal grounding by combining a query-guided window selection with a coarse-to-fine alignment strategy, significantly enhancing efficiency and accuracy.

Contribution

The paper introduces a plug-and-play CONE framework that leverages a query-guided sliding window and contrastive learning for better multi-modal alignment in long videos.

Findings

Achieves state-of-the-art results on two long VTG benchmarks.

Speeds up inference by 2x on Ego4D-NLQ and 15x on MAD.

Improves performance from 3.13% to 6.87% on MAD.

Abstract

This paper tackles an emerging and challenging problem of long video temporal grounding~(VTG) that localizes video moments related to a natural language (NL) query. Compared with short videos, long videos are also highly demanded but less explored, which brings new challenges in higher inference computation cost and weaker multi-modal alignment. To address these challenges, we propose CONE, an efficient COarse-to-fiNE alignment framework. CONE is a plug-and-play framework on top of existing VTG models to handle long videos through a sliding window mechanism. Specifically, CONE (1) introduces a query-guided window selection strategy to speed up inference, and (2) proposes a coarse-to-fine mechanism via a novel incorporation of contrastive learning to enhance multi-modal alignment for long videos. Extensive experiments on two large-scale long VTG benchmarks consistently show both substantial performance gains (e.g., from 3.13% to 6.87% on MAD) and state-of-the-art results. Analyses also reveal higher efficiency as the query-guided window selection mechanism accelerates inference time by 2x on Ego4D-NLQ and 15x on MAD while keeping SOTA results. Codes have been released at https://github.com/houzhijian/CONE.