PR-Net: Preference Reasoning for Personalized Video Highlight Detection

TL;DR

PR-Net introduces a preference reasoning framework that explicitly models diverse user interests for personalized video highlight detection, significantly improving accuracy over existing methods.

Contribution

The paper proposes a novel preference reasoning framework (PR-Net) that explicitly accounts for diverse user interests, enhancing personalized highlight prediction accuracy.

Findings

Outperforms state-of-the-art methods by 12% in mean accuracy precision

Effectively models diverse user preferences for personalized video highlights

Introduces a bi-directional contrastive loss for better metric learning

Abstract

Personalized video highlight detection aims to shorten a long video to interesting moments according to a user's preference, which has recently raised the community's attention. Current methods regard the user's history as holistic information to predict the user's preference but negating the inherent diversity of the user's interests, resulting in vague preference representation. In this paper, we propose a simple yet efficient preference reasoning framework (PR-Net) to explicitly take the diverse interests into account for frame-level highlight prediction. Specifically, distinct user-specific preferences for each input query frame are produced, presented as the similarity weighted sum of history highlights to the corresponding query frame. Next, distinct comprehensive preferences are formed by the user-specific preferences and a learnable generic preference for more overall highlight measurement. Lastly, the degree of highlight and non-highlight for each query frame is calculated as semantic similarity to its comprehensive and non-highlight preferences, respectively. Besides, to alleviate the ambiguity due to the incomplete annotation, a new bi-directional contrastive loss is proposed to ensure a compact and differentiable metric space. In this way, our method significantly outperforms state-of-the-art methods with a relative improvement of 12% in mean accuracy precision.