Circulant temporal encoding for video retrieval and temporal alignment

TL;DR

This paper introduces a circulant temporal encoding method for efficient video retrieval and alignment, enabling accurate localization of matching segments and robust global temporal alignment of videos in a computationally efficient manner.

Contribution

It proposes a novel circulant matrix-based encoding for joint appearance and temporal order representation, improving efficiency and accuracy in video retrieval and alignment tasks.

Findings

Significant reduction in computational complexity.

Accurate localization of matching video segments.

Robust global temporal alignment of multiple videos.

Abstract

We address the problem of specific video event retrieval. Given a query video of a specific event, e.g., a concert of Madonna, the goal is to retrieve other videos of the same event that temporally overlap with the query. Our approach encodes the frame descriptors of a video to jointly represent their appearance and temporal order. It exploits the properties of circulant matrices to efficiently compare the videos in the frequency domain. This offers a significant gain in complexity and accurately localizes the matching parts of videos. The descriptors can be compressed in the frequency domain with a product quantizer adapted to complex numbers. In this case, video retrieval is performed without decompressing the descriptors. We also consider the temporal alignment of a set of videos. We exploit the matching confidence and an estimate of the temporal offset computed for all pairs of videos by our retrieval approach. Our robust algorithm aligns the videos on a global timeline by maximizing the set of temporally consistent matches. The global temporal alignment enables synchronous playback of the videos of a given scene.