AntPivot: Livestream Highlight Detection via Hierarchical Attention Mechanism

TL;DR

AntPivot introduces a hierarchical attention-based model for livestream highlight detection, effectively handling challenges like long durations and topic shifts, and demonstrates superior performance on a new annotated dataset.

Contribution

The paper presents a novel hierarchical attention architecture and a dynamic programming approach for livestream highlight detection, along with a new annotated dataset for evaluation.

Findings

AntPivot outperforms existing methods on the AntHighlight dataset.

Hierarchical attention effectively captures temporal clues in livestreams.

Dynamic programming improves highlight sequence detection accuracy.

Abstract

In recent days, streaming technology has greatly promoted the development in the field of livestream. Due to the excessive length of livestream records, it's quite essential to extract highlight segments with the aim of effective reproduction and redistribution. Although there are lots of approaches proven to be effective in the highlight detection for other modals, the challenges existing in livestream processing, such as the extreme durations, large topic shifts, much irrelevant information and so forth, heavily hamper the adaptation and compatibility of these methods. In this paper, we formulate a new task Livestream Highlight Detection, discuss and analyze the difficulties listed above and propose a novel architecture AntPivot to solve this problem. Concretely, we first encode the original data into multiple views and model their temporal relations to capture clues in a hierarchical attention mechanism. Afterwards, we try to convert the detection of highlight clips into the search for optimal decision sequences and use the fully integrated representations to predict the final results in a dynamic-programming mechanism. Furthermore, we construct a fully-annotated dataset AntHighlight to instantiate this task and evaluate the performance of our model. The extensive experiments indicate the effectiveness and validity of our proposed method.