Avatar

Chih-Hui (John) Ho

何智輝

San Diego, US

chh279(at)eng.ucsd.edu

bill83221(at)gmail.com

Linkedin

CV

Resume

Google Scholar


Home

About

Education

Publication

Work Experience

Research Projects

Academic service

Volunteer


About        

I am an applied AI researcher in Articul8, building domain specific multi-modal GenAI. I received my PhD from University of California San Diego (UCSD) Statistical Visual Computing Lab (SVCL), advised by Prof. Nuno Vasconcelos. My areas of research interest are GenAI, computer vision, deep learning (See publication page). I was an research intern in Mitsubishi Electric Research Laboratories (MERL) and Amazon AWS AI. Before joining SVCL, I recieved my master degree in UCSD CSE and bachelor degee from National Chiao Tung University in Taiwan. Before joining UCSD, I worked as a research assistant in Computer Vision Research Center in NCTU. I was an exchange student in University of Illinois at Urbana Champaign during my junior year and was a research intern in Cornell University.

News

  • 08/2024: I will be serving as a Program Committee for AAAI 2025
  • 08/2024: One paper accepted at IEEE Transactions on Communications. Paper available here
  • 03/2024: Complete PhD Defense. Presentation is available here
  • 03/2024: Two paper accepted at CVPR24
  • 07/2023: One paper accepted at ICCV23
  • 06/2023-09/2023: Research Internship in MERL. Thank you MERL !!
  • 06/2023: I will be serving as a reviewer of NeurIPS2023
  • 03/2023: I will be serving as a reviewer of ICCV2023
  • 01/2023: I will be serving as a reviewer of CVPR2023
  • 11/2022: Glad to receive 2022 NeurIPS Scholar Award. Thank you NeurIPS !!
  • 08/2022: 1 paper accepted in Neurips 2022
  • 08/2022: 1 paper accepted in ECCV Workshop 2022
  • 07/2022: Glad to be selected as an outstanding reviewer at ICML2022
  • 06/2022: Glad to receive Amazon Post-Internship Fellowship. Thank you Amazon !!
  • 06/2022: 1 paper accepted in CVPR Workshop 2022
  • 05/2022: I will be serving as a reviewer of NeurIPS022
  • 04/2022: I will be serving as a reviewer of ECCV2022
  • 02/2022: I will be serving as a reviewer of ICML2022
  • 11/2021: I will be serving as a reviewer of TPAMI2021
  • 06/2021-09/2021: Applied Scientist Internship in Amazon AWS. Thank you Amazon !!
  • 05/2021: Glad to be selected as CVPR2021 outstanding reviewer
  • 05/2021: I will be serving as a reviewer of NeurIPS2021
  • 05/2021: Selected as Qualcomm Innovation Fellowship Finalist. Thank you Qualcomm !!
  • 01/2021: I will be serving as a reviewer of ICCV2021
  • 01/2021: I will be serving as a reviewer of ICML2021
  • 10/2020: 1 paper accepted in NeurIPS 2020
  • 10/2020: I will be serving as a reviewer of CVPR2021
  • 07/2020: 1 paper accepted in ECCV 2020
  • 07/2020: I will be serving as a reviewer of ECCV2020 Workshop on Imbalance Problems in Computer Vision (IPCV)
  • 06/2020: I will be serving as a reviewer of WACV (2021), NIPS (2020), ACCV (2020)
  • 03/2020: 1 paper accepted in CVPR 2020
  • 08/2019: 1 preprint paper published on arxiv
  • 06/2019: Graduating with master degree from UCSD Computer Science Engineering (CSE) department.
  • 05/2019: I passed the preliminary exam in UCSD Electrical and Computer Engineering (ECE).
  • 03/2019: 2 papers accepted in CVPR 2019, Long Beach, California

Selected publications

ProTeCt: Prompt Tuning for Taxonomic Open Set Classification
Chih-Hui Ho*, Tz-Ying Wu* , Nuno Vasconcelos
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, United States, 2024
[Paper] [Code] [Website]
Long-Tailed Anomaly Detection with Learnable Class Names
Chih-Hui Ho, Kuan-Chuan Peng, Nuno Vasconcelos
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, United States, 2024
[Paper] [Supplemental] [Dataset] [Website]
Toward Unsupervised Realistic Visual Question Answering
Chih-Hui Ho*, Yuwei Zhang* , Nuno Vasconcelos
International Conference on Computer Vision (2023)
[Paper] [Supplemental] [Code] [Website]
DISCO: Adversarial Defense with Local Implicit Functions
Chih-Hui Ho, Nuno Vasconcelos
Neural Information Processing Systems (NeurIPS), New Orleans, US 2022
[Paper] [Supplementary material] [Code]
YORO - Lightweight End to End Visual Grounding
Chih-Hui Ho, Srikar Appalaraju, Bhavan Jasani, R. Manmatha, Nuno Vasconcelos
European Conference On Computer Vision Workshop (ECCVW), Tel-Aviv, Israel, 2022
[Paper] [Supplementary material] [Code]
Black-Box Test-Time Shape REFINEment for Single View 3D Reconstruction

Brandon Leung, Chih-Hui Ho, Nuno Vasconcelos

IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), New Orleans, Louisiana, United States, 2022
[Paper] [Supplementary material] [Website] [Code] [Dataset] [ArXiv]
Contrastive Learning with Adversarial Examples
Chih-Hui Ho, Nuno Vasconcelos
Neural Information Processing Systems (NeurIPS) Vancouver, Canada, 2020 (online)
[PDF] [Supplementary material] [Code] [Video]
A New Technique of Camera Calibration: A Geometric Approach Based on Principal Lines
Jen-Hui Chuang, Chih-Hui Ho, Ardian Umam, HsinYi Chen, Mu-Tien Lu, Jenq-Neng Hwang, Tai-An Chen
IEEE Transactions on Image Processing, 2021
[Paper] [Arxiv]
PIEs: Pose Invariant Embeddings
Chih-Hui Ho, Pedro Morgado, Amir Persekian, Nuno Vasconcelos
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, California, United States, 2019
[Webpage] [Paper] [Supplementary material] [Code]
Catastrophic Child’s Play: Easy to Perform, Hard to Defend Adversarial Attacks
Chih-Hui Ho*, Brandon Leung*, Erik Sandstrom, Yen Chang, Nuno Vasconcelos (*indicate equal contribution)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, California, United States, 2019
[Webpage] [Paper] [Supplementary material]