Title: An unsupervised video summarisation method based on temporal convolutional networks

Authors: Ke Jin; Hui Li; Haoran Li; Qichuang Liu; Rong Chen; Shikai Guo

Addresses: School of Information Science and Technology, Dalian Maritime University, Dalian, Liaoning, China ' School of Information Science and Technology, Dalian Maritime University, Dalian, Liaoning, China ' School of Information Science and Technology, Dalian Maritime University, Dalian, Liaoning, China ' School of Information Science and Technology, Dalian Maritime University, Dalian, Liaoning, China ' School of Information Science and Technology, Dalian Maritime University, Dalian, Liaoning, China ' School of Information Science and Technology, Dalian Maritime University, Dalian, Liaoning, China

Abstract: Video summarisation automatically selects a sparse subset of video frames that best represent the semantic content of the input video. Previous work mainly utilised Long Short-Term Memory (LSTM) networks to learn how to assess the importance of each video frame and then select appropriate frames to compose a video summary. However, these models still have shortcomings, such as limited memory capacity in handling long-term dependencies, and extended training time. Therefore, we present a deep video summarisation model, named TCN-SUM, which centres around Bi-TCN and models the frame sequence. TCN-SUM consists of three modules: frame selection module incorporates both Bidirectional Temporal Convolutional Network (Bi-TCN) and self-attention to model inter-frame dependencies, video reconstruction module reconstructs the original video based on the summary, and discriminator module measures the similarity between the original and reconstructed videos. Experimental studies on two benchmark data sets demonstrate that TCN-SUM outperforms state-of-the-art techniques, achieving superior performance in unsupervised approaches and showing competitiveness compared to supervised methods.

Keywords: Bi-TCN; video summarisation; self-attention; LSTM.

DOI: 10.1504/IJCAT.2025.148138

International Journal of Computer Applications in Technology, 2025 Vol.76 No.1/2, pp.1 - 16

Received: 11 Sep 2023
Accepted: 18 Jan 2024
Published online: 27 Aug 2025 *