Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning

TL;DR

This paper introduces a novel weakly-supervised dense video captioning method using complementary masking to implicitly align event locations with captions, simplifying localization without explicit annotations.

Contribution

The proposed approach employs a dual-mode captioning and mask generation module to implicitly align event locations and captions, reducing complexity compared to existing explicit methods.

Findings

Outperforms existing weakly-supervised methods

Achieves competitive results with fully-supervised approaches

Effective implicit alignment of event locations and captions

Abstract

Weakly-Supervised Dense Video Captioning (WSDVC) aims to localize and describe all events of interest in a video without requiring annotations of event boundaries. This setting poses a great challenge in accurately locating the temporal location of event, as the relevant supervision is unavailable. Existing methods rely on explicit alignment constraints between event locations and captions, which involve complex event proposal procedures during both training and inference. To tackle this problem, we propose a novel implicit location-caption alignment paradigm by complementary masking, which simplifies the complex event proposal and localization process while maintaining effectiveness. Specifically, our model comprises two components: a dual-mode video captioning module and a mask generation module. The dual-mode video captioning module captures global event information and generates descriptive captions, while the mask generation module generates differentiable positive and negative masks for localizing the events. These masks enable the implicit alignment of event locations and captions by ensuring that captions generated from positively and negatively masked videos are complementary, thereby forming a complete video description. In this way, even under weak supervision, the event location and event caption can be aligned implicitly. Extensive experiments on the public datasets demonstrate that our method outperforms existing weakly-supervised methods and achieves competitive results compared to fully-supervised methods.