M-PACT: Michigan Platform for Activity Classification in Tensorflow
Eric Hofesmann and Madan Ravi Ganesh and Jason J. Corso

@article{dblp:journals/corr/abs-1804-05879,
author= {Eric Hofesmann and               Madan Ravi Ganesh and               Jason J. Corso},
title= {M-PACT: Michigan Platform for Activity Classification in Tensorflow},
journal= {CoRR},
volume= {abs/1804.05879},
year= {2018},
url= {https://github.com/MichiganCOG/M-PACT},
archiveprefix= {arXiv},
eprint= {1804.05879},
timestamp= {Mon, 13 Aug 2018 16:47:20 +0200},
biburl= {https://dblp.org/rec/bib/journals/corr/abs-1804-05879},
bibsource= {dblp computer science bibliography, https://dblp.org},
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.
},
keywords= {actvity recognition, weights, c3d, i3d, tsn, resnet, lstm},
terms= {},
license= {},
superseded= {}
}