chulwoopack
Assistant Professor in EECS at South Dakota State University. Research Topic: Computer Vision, Document Analysis, Image Processing, Deep Learning
South Dakota State UniversityBrookings, SD
Pinned Repositories
adaptivedownscaling
ChartQA
chulwoopack.github.io
docstrum
document_complexity
Analyze document image complexity based on segmentation results
gravity-map
Visual Domain Knowledge-based Multimodal Zoning Textual Region Localization in Noisy Historical Document Images
NCT_LAB
Voronoi_SegNews
Zone2OCR
Mapping a set of zones generated by a segmentation algorithm to the regions generated by OCR engine
aida
Creates image snippets from page images of historic newspaper pages, processes those snippets to prepare them for feature extraction, extracts feature values, and then determines if an image snippets contains poetic content using a Multilayer Perception Artificial Neural Network trained on feature values.
chulwoopack's Repositories
chulwoopack/docstrum
chulwoopack/gravity-map
Visual Domain Knowledge-based Multimodal Zoning Textual Region Localization in Noisy Historical Document Images
chulwoopack/Voronoi_SegNews
chulwoopack/Zone2OCR
Mapping a set of zones generated by a segmentation algorithm to the regions generated by OCR engine
chulwoopack/document_complexity
Analyze document image complexity based on segmentation results
chulwoopack/adaptivedownscaling
chulwoopack/ChartQA
chulwoopack/chulwoopack.github.io
chulwoopack/deepclustering
chulwoopack/github-pages-with-jekyll
chulwoopack/Image_Binarization
chulwoopack/InternetArchive
chulwoopack/NCT_LAB
chulwoopack/clipseg
chulwoopack/depth-camera-web-demo
chulwoopack/k-clip
Do You See What I See
chulwoopack/lab.js
Online research made easy
chulwoopack/Mask_RCNN_SegDog
chulwoopack/MLP_using_DLR
chulwoopack/MultiMAE
MultiMAE: Multi-modal Multi-task Masked Autoencoders, ECCV 2022
chulwoopack/pytorch-stable-diffusion
Stable Diffusion implemented from scratch in PyTorch
chulwoopack/vae
chulwoopack/voronoi_based_docu_complexity_analysis
chulwoopack/vpt
❄️🔥 Visual Prompt Tuning [ECCV 2022] https://arxiv.org/abs/2203.12119