Litcius/Paper detail

MAR-Net: Motion-Assisted Reconstruction Network for Unsupervised Video Summarization

Yunzuo Zhang, Yameng Liu, Weili Kang, Yuxin Zheng

2023IEEE Signal Processing Letters14 citationsDOI

Abstract

Video summarization targets to extract the most important segments from a video by spatiotemporal analysis. Previous methods primarily learn content within videos based on appearance information, with a rare discussion on the effective utilization of motion information, which is equally essential to video understanding. In this letter, we expound upon a Motion-Assisted Reconstruction Network (MAR-Net), which synergistically models appearance and motion information within videos for unsupervised video summarization without any manual annotations. MAR-Net notably comprises a Bidirectional Modality Encoder (BiME) and a Video Context Navigator (VCN). By integrating uni-modal and cross-modal feature aggregation into a unified module, BiME allows for exploring sophisticated dependency relationships among features through a bidirectional attention mechanism. VCN can promote the semantic consistency between the cross-modal contexts and the input video by a consistency loss term, alleviating the noisy impact within the motion stream. Empirical results conducted on benchmark datasets demonstrate that MAR-Net outperforms other state-of-the-art methods.

Topics & Concepts

Automatic summarizationComputer scienceContext (archaeology)Consistency (knowledge bases)Artificial intelligenceBenchmark (surveying)Motion compensationEncoderFeature (linguistics)Computer visionMotion (physics)Pattern recognition (psychology)PaleontologyLinguisticsGeodesyOperating systemGeographyPhilosophyBiologyVideo Analysis and SummarizationAdvanced Vision and ImagingMusic and Audio Processing