paper-with-me

Papers

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

2018-04-16 · Eric Hofesmann, Madan Ravi Ganesh, Jason J. Corso

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.

📄 PDF Abstract BibTeX arXiv:1804.05879

Code (1)

MichiganCOG/M-PACT 공식 구현 tf

Tasks

Action ClassificationActivity RecognitionClassificationGeneral Classification

Similar Papers 제목 키워드 기반

COMB: Common Open Modular robotic platform for Bees

2026-04-04 · Pranav Kedia, Marie Messerich, Tim Landgraf arxiv

Experimental access to real honeybee colonies requires robotic systems capable of operating within limited spatial constraints, tolerating hive-specific fouling and environmental conditions, and supporting both sensing a…

Image Stitching

Repeatability Corner Cases in Document Ranking: The Impact of Score Ties

2018-07-16 · Jimmy Lin, Peilin Yang

Document ranking experiments should be repeatable. However, the interaction between multi-threaded indexing and score ties during retrieval may yield non-deterministic rankings, making repeatability not as trivial as one…

Document RankingRetrieval

How to Solve Big Problems: Bespoke Versus Platform Strategies

2022-06-09 · Atif Ansar, Bent Flyvbjerg

How should government and business solve big problems? In bold leaps or in many smaller moves? We show that bespoke, one-off projects are prone to poorer outcomes than projects built on a repeatable platform. Repeatable …

NeoRacer: An Open, Standardized 1:12 Scale Autonomous Race Car for Benchmarking and Education

2026-07-29 · Koneshka Bandyopadhyay, Ansh Mehta, Bassel El Mabsout, Renato Mancuso arxiv

Many scientific fields rely on standard benchmarks and shared platforms to improve review and reproducibility, but autonomous systems research still lacks widely accepted open hardware. Where standardization has emerged,…

Hardware-triggered Time Synchronization of Roadside Multi-lidar, Multi-camera Measurement System for Accurate Data Alignment

2026-07-17 · Shiva Agrawal, Savankumar Bhanderi, Zhiran Yan, Gordon Elger arxiv

Accurate temporal alignment of heterogeneous sensors is necessary for reliable environment perception in roadside multi-lidar, multi-camera systems, particularly in dense urban traffic. For this purpose, an open-source, …