AntPivot: Livestream Highlight Detection via Hierarchical Attention Mechanism
This addresses the need for efficient highlight extraction in livestreams for content creators and platforms, but it is incremental as it adapts existing techniques to a new domain.
The paper tackles the problem of detecting highlight segments in long livestreams, which are challenging due to extreme durations and irrelevant content, by proposing AntPivot, a novel architecture that uses hierarchical attention and dynamic programming, and constructs a new dataset AntHighlight, achieving effective results as shown in experiments.
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.