Weakly-Supervised Multi-Level Attentional Reconstruction Network for Grounding Textual Queries in Videos

TL;DR

This paper introduces MARN, a weakly-supervised model for localizing video segments based on textual queries, using only video-sentence pairs and attention mechanisms to improve accuracy without requiring detailed annotations.

Contribution

The paper proposes a novel multi-level attentional reconstruction network that leverages intra- and inter-proposal information for weakly-supervised video grounding, improving over existing methods.

Findings

MARN outperforms existing weakly-supervised methods on Charades-STA and ActivityNet-Captions datasets.

The proposed proposal sampling and attention mechanisms enhance proposal representation and localization accuracy.

The model effectively utilizes intra- and inter-proposal clues to improve grounding performance.

Abstract

The task of temporally grounding textual queries in videos is to localize one video segment that semantically corresponds to the given query. Most of the existing approaches rely on segment-sentence pairs (temporal annotations) for training, which are usually unavailable in real-world scenarios. In this work we present an effective weakly-supervised model, named as Multi-Level Attentional Reconstruction Network (MARN), which only relies on video-sentence pairs during the training stage. The proposed method leverages the idea of attentional reconstruction and directly scores the candidate segments with the learnt proposal-level attentions. Moreover, another branch learning clip-level attention is exploited to refine the proposals at both the training and testing stage. We develop a novel proposal sampling mechanism to leverage intra-proposal information for learning better proposal representation and adopt 2D convolution to exploit inter-proposal clues for learning reliable attention map. Experiments on Charades-STA and ActivityNet-Captions datasets demonstrate the superiority of our MARN over the existing weakly-supervised methods.