Chuong Huynh
Scholar

Chuong Huynh

Google Scholar ID: KxvCz4oAAAAJ
University of Maryland, College Park
Computer VisionDeep LearningVision Language ModelImage Retrieval
Citations & Impact
All-time
Citations
223
 
H-index
5
 
i10-index
3
 
Publications
10
 
Co-authors
23
list available
Resume (English only)
Academic Achievements
  • Published papers include: 'CoLLM: A Large Language Model for Composed Image Retrieval', 'VeriGraph: Scene Graphs for Execution Verifiable Robot Planning', 'MaGGIe: Mask Guided Gradual Human Instance Matting', 'Composing Object Relations and Attributes for Image-Text Matching', 'SimpSON: Simplifying Photo Cleanup With Single-Click Distracting Object Segmentation Network', 'Progressive Semantic Segmentation', 'Context Learning for Bone Shadow Exclusion in CheXNet Accuracy Improvement'.
Research Experience
  • Research Intern, Vision Intelligence at Samsung Research America (May 2025 - recent); Applied Scientist Intern, Rufus Multimodal at Amazon.com (May 2024 - Dec 2024); Research Intern, Digital Media at Adobe Research (May 2023 - Dec 2023); Research Intern, Photoshop ART at Adobe Research (May 2022 - May 2023); Research Resident and Engineer, VinAI Research (now Qualcomm AI Research) (July 2019 - July 2021).
Education
  • Ph.D. in Computer Science from University of Maryland, College Park, advised by Prof. Abhinav Shrivastava; B.S. in Computer Science from University of Science, Vietnam National University, Ho Chi Minh City, supervised by Prof. Minh-Triet Tran.
Background
  • Research interests lie at the intersection of computer vision and user interaction. Leverages Large Language Models to advance image-text alignment and has previously developed cutting-edge techniques for highly detailed interactive segmentation and matting.
Miscellany
  • Reviewers: CVPR, ECCV, ICCV, ACCV, NeurIPS, TPAMI