Huaizu Jiang
Assistant Professor
Research interests
- Computer vision
- Computational photography
- Machine learning
Education
- PhD in Computer Science, University of Massachusetts, Amherst
- MEng in Intelligent System and Pattern Recognition, Xi'an Jiaotong University — China
- BEng in Electrical Engineering, Xi'an Jiaotong University — China
Biography
Huaizu Jiang is an assistant professor in the Khoury College of Computer Sciences at Northeastern University, based in Boston.
Jiang's research interests include computer vision, computational photography, machine learning, natural language processing, and artificial intelligence. He was previously a postdoctoral researcher at the California Institute of Technology.
Jiang's awards include the 2019-2020 NVIDIA Graduate Fellowship, 2019 Adobe Fellowship, and 2018 Outstanding Reviewer at IEEE/CVF CVPR. He has published at the IEEE/CVF Conference on Computer Vision and Pattern Recognition, the International Conference on Computer Vision, and the European Conference on Computer Vision (ECCV).
Recent publications
-
SMooDi: Stylized Motion Diffusion Model
Citation: Lei Zhong, Yiming Xie, Varun Jampani, Deqing Sun, Huaizu Jiang. (2024). SMooDi: Stylized Motion Diffusion Model ECCV (1), 405-421. https://doi.org/10.1007/978-3-031-73232-4_23 -
Zero-Shot Referring Expression Comprehension via Structural Similarity Between Images and Captions
Citation: Zeyu Han, Fangrui Zhu, Qianru Lao, Huaizu Jiang. (2024). Zero-Shot Referring Expression Comprehension via Structural Similarity Between Images and Captions CVPR, 14364-14375. https://doi.org/10.1109/CVPR52733.2024.01362 -
OmniControl: Control Any Joint at Any Time for Human Motion Generation
Citation: Yiming Xie, Varun Jampani, Lei Zhong, Deqing Sun, Huaizu Jiang. (2024). OmniControl: Control Any Joint at Any Time for Human Motion Generation ICLR. https://openreview.net/forum?id=gd0lAEtWso -
Pixel-Aligned Recurrent Queries for Multi-View 3D Object Detection
Citation: Yiming Xie, Huaizu Jiang, Georgia Gkioxari, Julian Straub. (2023). Pixel-Aligned Recurrent Queries for Multi-View 3D Object Detection ICCV, 18324-18334. https://doi.org/10.1109/ICCV51070.2023.01684 -
StereoVoxelNet: Real-Time Obstacle Detection Based on Occupancy Voxels from a Stereo Camera Using Deep Neural Networks
Citation: Hongyu Li, Zhengang Li, Neset Ünver Akmandor, Huaizu Jiang, Yanzhi Wang, Taskin Padir. (2023). StereoVoxelNet: Real-Time Obstacle Detection Based on Occupancy Voxels from a Stereo Camera Using Deep Neural Networks ICRA, 4826-4833. https://doi.org/10.1109/ICRA48891.2023.10160924 -
PlanarRecon: Realtime 3D Plane Detection and Reconstruction from Posed Monocular Videos
Citation: Yiming Xie, Matheus Gadelha, Fengting Yang, Xiaowei Zhou, Huaizu Jiang. (2022). PlanarRecon: Realtime 3D Plane Detection and Reconstruction from Posed Monocular Videos CVPR, 6209-6218. https://doi.org/10.1109/CVPR52688.2022.00612 -
Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions
Citation: Huaizu Jiang, Xiaojian Ma, Weili Nie, Zhiding Yu, Yuke Zhu, Anima Anandkumar. (2022). Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions CVPR, 19034-19043. https://doi.org/10.1109/CVPR52688.2022.01847 -
In Defense of Grid Features for Visual Question Answering
Citation: Huaizu Jiang, Ishan Misra, Marcus Rohrbach, Erik G. Learned-Miller, Xinlei Chen. (2020). In Defense of Grid Features for Visual Question Answering CVPR, 10264-10273. https://openaccess.thecvf.com/content_CVPR_2020/html/Jiang_In_Defense_of_Grid_Features_for_Visual_Question_Answering_CVPR_2020_paper.html -
Automatic Adaptation of Object Detectors to New Domains Using Self-Training
Citation: Aruni RoyChowdhury, Prithvijit Chakrabarty, Ashish Singh, SouYoung Jin, Huaizu Jiang, Liangliang Cao, Erik G. Learned-Miller. (2019). Automatic Adaptation of Object Detectors to New Domains Using Self-Training CVPR, 780-790. http://openaccess.thecvf.com/content_CVPR_2019/html/RoyChowdhury_Automatic_Adaptation_of_Object_Detectors_to_New_Domains_Using_Self-Training_CVPR_2019_paper.html
