Generating Adjacency Matrix for Video Relocalization

TL;DR

This paper introduces a similarity-metric based graph convolution approach for video relocalization, improving feature extraction by calculating similarity between frames, leading to better performance on benchmark datasets.

Contribution

The paper proposes a novel similarity-metric based graph convolution method that enhances intra- and inter-video feature extraction for video relocalization.

Findings

Outperforms state-of-the-art methods on ActivityNet v1.2 and Thumos14 datasets

Demonstrates improved accuracy in video relocalization tasks

Validates effectiveness of similarity-metric based adjacency matrices

Abstract

In this paper, we continue our work on video relocalization task. Based on using graph convolution to extract intra-video and inter-video frame features, we improve the method by using similarity-metric based graph convolution, whose weighted adjacency matrix is achieved by calculating similarity metric between features of any two different time steps in the graph. Experiments on ActivityNet v1.2 and Thumos14 dataset show the effectiveness of this improvement, and it outperforms the state-of-the-art methods.