About Me

Man M. Ho

Research Fellow
Scientific Computing and Imaging Institute (SCI)
University of Utah
Salt Lake City, UT

Contact: man.ho (at) sci.utah.edu
Personal: manminhho.cs (at) gmail.com

This is a webpage for my done/ongoing projects and photos. My interests lie in Computer Vision, Deep Learning, Histopathology Imaging, and Photography. Also, I love taking/editing/retouching photographs. Please check my [CV] for more details.

News

2024/04: F2FLDM preprint is out
2024/04: Extended version of DISC was accepted to SynData4CV @ CVPR 2024
2024/02: HistoEM was accepted to Modern Pathology
2024/02: DISC was accepted to ISBI 2024

My projects are related to

Computational Photography:

Image/Video Color/Style Transfer

Colorization

Restoration

Manipulation

Smartphone Photo Scanning

Pathology Imaging:

Cancer Diagnosis and Prognosis

Transfer Learning

Semi-Supervised Learning

Data Shortage

Selected Publications

	F2FLDM: Latent Diffusion Models with Histopathology Pre-Trained Embeddings for Unpaired Frozen Section to FFPE Translation Man M. Ho, Shikha Dubey, Yosep Chong, Beatrice S. Knudsen, and Tolga Tasdizen In arXiv Preprint, 2024.
Description: Developed LDMs with Parameter-Efficient Fine-Tuning (PEFT) and Histopathology Pre-Trained Embeddings for translating low-quality frozen section images to high-quality FFPE images, taking generative model hallucinations into account and improving classification performance from 81.99% to 94.64% AUCROC on low-quality frozen slides, while the performance on high-quality FFPE images reached 94.63%.
	DISC: Latent Diffusion Models with Self-Distillation from Separated Conditions for Prostate Cancer Grading Man M. Ho, Elham Ghelichkhan, Yosep Chong, Yufei Zhou, Beatrice S. Knudsen, and Tolga Tasdizen In IEEE International Symposium on Biomedical Imaging (ISBI), 2024. Extended version accepted to SynData4CV @ CVPR 2024.
Description: Developed Latent Diffusion Models (LDMs) to generate high-fidelity histopathology images for training prostate cancer grading models. Introduced the DISC framework to enhance the accuracy of GG patterns from LDMs trained on imprecise annotations.
	Deep Photo Scan: Semi-Supervised Learning for dealing with the real-world degradation in Smartphone Photo Scanning Man M. Ho, Jinjia Zhou In Winter Conference on Applications of Computer Vision (WACV), 2022.
Description: A promising baseline for learned smartphone-scanned photo restoration.
	Deep Preset: Blending and Retouching Photos with Color Style Transfer Man M. Ho, Jinjia Zhou In Winter Conference on Applications of Computer Vision (WACV), 2021.
Description: Proposed a novel color style. Lightroom Preset now can be any well-retouched photos.
	RR-DnCNN v2.0: Enhanced Restoration-Reconstruction Deep Neural Network for Down-Sampling Based Video Coding Man M. Ho, Jinjia Zhou, Gang He In IEEE Transactions on Image Processing (TIP), 2021.
Description: Investigated the effect of compression degradation for training. Proposed a new learned down-sampling-based video coding framework.

Other Publications

HistoEM: A Pathologist-Guided and Explainable Workflow Using Histogram Embedding for Gland Classification
Alessandro Ferrero, Elham Ghelichkhan, Hamid Manoochehri, Man M. Ho, Daniel J. Albertson, Benjamin J. Brintz, Tolga Tasdizen, Ross T. Whitaker, and Beatrice S. Knudsen
In Modern Pathology, 2024

CLASS-M: Adaptive stain separation-based contrastive learning with pseudo-labeling for histopathological image classification
Bodong Zhang, Hamid Manoochehri, Man M. Ho, Fahimeh Fooladgar, Yosep Chong, Beatrice S. Knudsen, Deepika Sirohi, and Tolga Tasdizen
In arXiv preprint, 2023.

	Interactive Image Manipulation with Complex Text Instructions Ryugo Morita, Zhiqiang Zhang, Man M. Ho, Jinjia Zhou In Winter Conference on Applications of Computer Vision (WACV), 2023.
	On Pre-chewing Compression Degradation for Learned Video Compression Man M. Ho, Heming Sun, Zhiqiang Zhang, Jinjia Zhou In IEEE International Conference on Visual Communications and Image Processing (VCIP), 2022.
	Text-guided Image Manipulation based on Sentence-aware and Word-aware Network Zhiqiang Zhang, Chen Fu, Man M. Ho, Jinjia Zhou, Ning Jiang, Wenxin Yu In IEEE International Conference on Multimedia and Expo (ICME), 2022. Presented at AI for Content Creation Workshop (AI4CC) - CVPRW, 2022.
	Semantic-driven Colorization Man M. Ho, Lu Zhang, Alexander Raake, Jinjia Zhou In ACM SIGGRAPH European Conference on Visual Media Production (CVMP), 2021.
	Japanese Coins and Banknotes Recognition for Visually Impaired People Huyen T. T. Bui, Man M. Ho, Xiao Peng, Jinjia Zhou In VizWiz Workshop, 2020.
	SR-CL-DMC: P-frame coding with Super-Resolution, Color Learning, and Deep Motion Compensation (Top-5 performance among teams which have submitted a factsheet on P-frame Track, CLIC2020) Man M. Ho, Jinjia Zhou, Gang He, Muchen Li, Lei Li In Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020.
	Down-Sampling Based Video Coding with Degradation-Aware Restoration-Reconstruction Deep Neural Network (Oral - Best Paper Runner-up Award) Man M. Ho (Minh-Man Ho), Gang He, Zheng Wang, Jinjia Zhou In International Conference on Multimedia Modeling (MMM), 2020.
	Respecting Low-level Components of Content with Skip Connections and Semantic Information in Image Style Transfer (Oral) Man M. Ho (Minh-Man Ho), Jinjia Zhou, Yibo Fan In ACM SIGGRAPH European Conference on Visual Media Production (CVMP), 2019.

Awards and Honors

2020/07, "Hosei University Science and Engineering Departments Education/Research Promotion Fund Academic Achievement Award 2020".
2020/01, "Best Paper Runner-up Award" at MMM2020, Deajeon, Korea.
2018/08, "Key Contributor" by EyeQ Tech, Vietnam.
2018/08, "Squad of the month" by EyeQ Tech, Vietnam.
2016/12, “The Five-Virtue Student” by Vietnam National University, University of Information Technology.

Professional Experience

I have served as a reviewer for:

CVPRW 2020

BMVC 2020, 2021

WACV 2021, 2022, 2023, 2024, 2025

ECCV 2024

ICCV 2021 (assistant)

Neural Computing and Applications (NCAA)