Multi-modal Representation Learning for Video Advertisement Content Structuring

TL;DR

This paper introduces a multi-modal encoder for video advertisement structuring, leveraging caption, speech, and visual data to improve segmentation and labeling accuracy, achieving state-of-the-art results in a multimedia challenge.

Contribution

It proposes a novel multi-modal representation learning framework combined with boundary matching and proposal refinement for enhanced video advertisement structuring.

Findings

Significant performance improvement over baselines.

Effective use of multi-modal content like caption and speech.

Achieved Rank 1 in ACM Multimedia 2021 Grand Challenge.

Abstract

Video advertisement content structuring aims to segment a given video advertisement and label each segment on various dimensions, such as presentation form, scene, and style. Different from real-life videos, video advertisements contain sufficient and useful multi-modal content like caption and speech, which provides crucial video semantics and would enhance the structuring process. In this paper, we propose a multi-modal encoder to learn multi-modal representation from video advertisements by interacting between video-audio and text. Based on multi-modal representation, we then apply Boundary-Matching Network to generate temporal proposals. To make the proposals more accurate, we refine generated proposals by scene-guided alignment and re-ranking. Finally, we incorporate proposal located embeddings into the introduced multi-modal encoder to capture temporal relationships between local features of each proposal and global features of the whole video for classification. Experimental results show that our method achieves significantly improvement compared with several baselines and Rank 1 on the task of Multi-modal Ads Video Understanding in ACM Multimedia 2021 Grand Challenge. Ablation study further shows that leveraging multi-modal content like caption and speech in video advertisements significantly improve the performance.