Technical Report for SoccerNet Challenge 2022 -- Replay Grounding Task

TL;DR

A unified network Faster-TAD proposed by us for temporal action detection is applied to get the results of replay grounding and the output of the model is refined to get the final submission.

Abstract

In order to make full use of video information, we transform the replay grounding problem into a video action location problem. We apply a unified network Faster-TAD proposed by us for temporal action detection to get the results of replay grounding. Finally, by observing the data distribution of the training data, we refine the output of the model to get the final submission.

Figures (2)

• Figure 1: Example of caption. It is set in Roman so that mathematics (always set in Roman: $B \sin A = A \sin B$) may be included without an ugly clash.
• Figure 2: Example of a short caption, which should be centered.