Weakly-Supervised Multi-Level Attentional Reconstruction Network for Grounding Textual Queries in Videos
This addresses the challenge of localizing video segments from text queries in real-world scenarios where temporal annotations are unavailable, representing an incremental improvement over existing weakly-supervised methods.
The paper tackles the problem of temporally grounding textual queries in videos without temporal annotations by proposing a weakly-supervised model called MARN, which uses video-sentence pairs and achieves superior performance on Charades-STA and ActivityNet-Captions datasets.
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.