Computational Infrastructure Journal Papers — Redirected
This page has been reorganized. The original “Computational Infrastructure” dimension covered both machine learning methods and data engineering topics. To provide more focused organization, the content has been split into two dedicated pages:
Computer Vision & ML
Papers on segmentation architectures (flood-filling networks, affinity-based methods), image alignment, and deep learning approaches for connectomics reconstruction.
Go to Computer Vision & ML Journal Papers
Includes papers such as:
- Januszewski et al. (2018) — Flood-Filling Networks
- Funke et al. (2019) — Structured Loss for Image Segmentation
Data Storage & Pipelines
Papers on connectomics data management, annotation systems (CAVE, CATMAID, VAST, neuPrint), file formats (OME-Zarr, cloud-optimized storage), versioning infrastructure, and pipeline engineering.
Go to Data Storage & Pipelines Journal Papers
Includes papers such as:
- Dorkenwald et al. (2023) — CAVE: Connectome Annotation Versioning Engine
- Macrina et al. (2021) — Petascale Neural Circuit Reconstruction (pipeline engineering)
- Scheffer et al. (2020) — Hemibrain (data release and neuPrint)
- Moore et al. (2021) — OME-Zarr cloud-optimized file format
- Saalfeld et al. (2009) — CATMAID collaborative annotation toolkit
- Ackerman et al. (2022) — BossDB cloud-native data management