Tianfu Wu
Biography
Tianfu Wu is an assistant professor in the Department of Electrical and Computer Engineering at the NC State university (NCSU). He is currently the PI of the laboratory of interpretable Visual Modeling, Computing and Learning (iVMCL). He received his Ph.D. in statistics from UCLA under the supervision by Prof. Song-Chun Zhu. His research focuses on computer vision, often motivated by the task of building explainable and improvable visual Turing test and robot autonomy through life-long communicative learning. To accomplish his research goals, he is interested in pursuing a unified framework for machines to ALTER (Ask, Learn, Test, Explain and Refine) recursively in a principled way.
Education
-
Ph.D.
2011
Statistics
University of California, Los Angeles
Funded Research
- Building the Paradigm of Big Model + Big Computational Platform for Universal Representation Learning and Deep Consensus Learning
- SEMA: Segmentation and Estimation of Missile Attitude
- ASTUTE: Automated Spectral and Temporal Understanding of Tiered Events
- Development: The Next-Generation Public Charging Infrastructure and Cyber-Information Network for Enhanced Inclusion and Independent Living of Power Mobility Device Users
- NRI: Fnd: A Novel Intervention Method to Promote Workers’ Safety Awareness and Mental Health During Human-Robot Collaboration
- RI:Small: Neural Architecture Search with Deep Compositional Grammatical Structures
- Learning Deep Grammar Networks for Visual Question Answering
- Learning Deep AND OR Grammar Networks for Object Tracking, Detection and Parsing: A Unified Framework
- Interdisciplinary Distinguished Seminar Series
Recent News
Aydin Aysu and Tianfu Wu Named Goodnight Early Career Innovators
Posted on April 26, 2022 | Filed Under: Awards
Congratulations to our two faculty members, Aydin Aysu and Tianfu Wu, for being recognized as a Goodnight Early Career Innovator!
Technique Improves AI Ability to Understand 3D Space Using 2D Images
Posted on January 27, 2022 | Filed Under: Research
The work would help autonomous vehicles navigate in relation to other vehicles.
This post was originally published in NC State News.
Researchers Fine-Tune Control Over AI Image Generation
Posted on June 2, 2021 | Filed Under: Research
ECE researchers fine-tune control over AI image generation with a new approach that allows AI to move or alter elements in an image while keeping them identifiably the same.
Recent Publications
- A Bottom-Up and Top-Down Integration Framework for Online Object Tracking (2021)
- Event driven sensor fusion (2021)
- High Speed Receiver Modeling Using Generative Adversarial Networks (2021)
- Learning Regional Attraction for Line Segment Detection (2021)
- Local Clustering with Mean Teacher for Semi-supervised learning (2021)
- Holistically-Attracted Wireframe Parsing (2020)
- AOGNets: Compositional Grammatical Architectures for Deep Learning (2019)
- Image Synthesis From Reconfigurable Layout and Style (2019)
- Jointly social grouping and identification in visual dynamics with causality-induced hierarchical Bayesian model (2019)
- Learning Attraction Field Representation for Robust Line Segment Detection (2019)