Reproducibility Report: Contrastive Learning of Socially-aware Motion Representations

TL;DR

This paper is a reproducibility report that verifies the results of 'Social NCE,' a contrastive learning method for socially-aware motion representations, by reimplementing the original code and confirming its claims.

Contribution

It provides a detailed reproducibility analysis of Social NCE, demonstrating the effectiveness of their contrastive learning approach for social motion understanding.

Findings

Reproduced the original results successfully.

Confirmed the effectiveness of contrastive learning for social motion.

Validated the original methodology and results.

Abstract

The following paper is a reproducibility report for "Social NCE: Contrastive Learning of Socially-aware Motion Representations" {\cite{liu2020snce}} published in ICCV 2021 as part of the ML Reproducibility Challenge 2021. The original code was made available by the author \footnote{\href{https://github.com/vita-epfl/social-nce}{https://github.com/vita-epfl/social-nce}}. We attempted to verify the results claimed by the authors and reimplemented their code in PyTorch Lightning.