M-PACT: An Open Source Platform for Repeatable Activity Classification Research

TL;DR

M-PACT is an open-source platform that simplifies activity classification research by providing modular, reproducible implementations of state-of-the-art models, enabling quick prototyping and consistent results.

Contribution

It introduces the first unified platform with four SOTA activity classification models, streamlining development and reproducibility in the field.

Findings

Provides four SOTA models in one platform

Enables reproducible activity recognition experiments

Facilitates rapid prototyping of new models

Abstract

There are many hurdles that prevent the replication of existing work which hinders the development of new activity classification models. These hurdles include switching between multiple deep learning libraries and the development of boilerplate experimental pipelines. We present M-PACT to overcome existing issues by removing the need to develop boilerplate code which allows users to quickly prototype action classification models while leveraging existing state-of-the-art (SOTA) models available in the platform. M-PACT is the first to offer four SOTA activity classification models, I3D, C3D, ResNet50+LSTM, and TSN, under a single platform with reproducible competitive results. This platform allows for the generation of models and results over activity recognition datasets through the use of modular code, various preprocessing and neural network layers, and seamless data flow. In this paper, we present the system architecture, detail the functions of various modules, and describe the basic tools to develop a new model in M-PACT.