AdSum: Two-stream Audio-visual Summarization for Automated Video Advertisement Clipping

TL;DR

This paper presents AdSum, a novel two-stream audio-visual model for automated video advertisement clipping, framing it as a shot selection problem and demonstrating superior performance over existing methods.

Contribution

Introduces a new two-stream audio-visual fusion model and a dedicated ad-specific dataset, AdSum204, for automated video ad clipping tailored to advertising needs.

Findings

Model outperforms state-of-the-art methods on multiple metrics

Developed the first ad-specific dataset for video summarization

Demonstrated the importance of audio in ad video summarization

Abstract

Advertisers commonly need multiple versions of the same advertisement (ad) at varying durations for a single campaign. The traditional approach involves manually selecting and re-editing shots from longer video ads to create shorter versions, which is labor-intensive and time-consuming. In this paper, we introduce a framework for automated video ad clipping using video summarization techniques. We are the first to frame video clipping as a shot selection problem, tailored specifically for advertising. Unlike existing general video summarization methods that primarily focus on visual content, our approach emphasizes the critical role of audio in advertising. To achieve this, we develop a two-stream audio-visual fusion model that predicts the importance of video frames, where importance is defined as the likelihood of a frame being selected in the firm-produced short ad. To address the lack of ad-specific datasets, we present AdSum204, a novel dataset comprising 102 pairs of 30-second and 15-second ads from real advertising campaigns. Extensive experiments demonstrate that our model outperforms state-of-the-art methods across various metrics, including Average Precision, Area Under Curve, Spearman, and Kendall. The dataset and code are available at https://github.com/ostadabbas/AdSum204.