Research
On Research
I am marching towards Synergetic & Holistic Intelligence.
My long term goal is to advance AI research and technologies in interrelated fields such as computer vision, machine learning, language understanding and robotics, to build intelligent systems, either virtual or embodied, to facilitate understanding multiple sensory inputs, to gain actionable insights from perception to cognition, to solve important real-world problems and to better serve our human race.
In the medium term, I am putting more emphasis on computer vision, machine learning and their applications, with a strong focus on accurate and efficient understanding of various types of objects and activities from sensory inputs such as images and videos. Over the past few years, I have explored a wide range of topics towards accurate and efficient visual understanding: from image-level classification, to instance-level object detection, to video-level detection and tracking, and more recently to spatio-temporal activity recognition and pixel-level segmentation etc. My team and I have been lucky to have won some international AI competitions and set new state-of-the-arts on major computer vision benchmarks. I am also fortunate to have been working on a broad spectrum of applied research projects with more than $10 million support, from research assistant, to team leader, and PI/Co-PI, with collaborators and support from industry, academic units and government agencies. This enables me to understand the true depth of challenges arose from real-world data and problems, or even in collaboration, management and technology transfer.
To emphasize, my current research focuses on accurate & efficient visual understanding and deep learning for AI systems & application, in particular I have recently worked in:
Computer Vision: classification, object detection, segmentation, activity recognition, etc.
Machine Learning: deep learning, weakly-supervised learning, transfer learning, efficient learning, etc.
AI Systems & Applications for Science, Engineering Education, Agriculture, Medicine, Finance, Art, Transportation, etc.
My research activities include multiple aspects to solve such problems and to advance AI research: projects, papers, competitions, organizing workshops, teaching and training students etc.
Please find more publication and technical reports on Google Scholar. Some of our codes and datasets are available at GitHub.
Papers etc. are also organized by three main themes here:
Abbreviations: [C]: Conference; [J] Journal; [W] Workshop; [TR]: Technical Report; [P]: Patent; [Comp]: Competition; [Proj]: Project; [Org] Program Organization; [SOTA]: State-of-the-art (at the time of publication).
Papers
Preprints:
[TR] Clique: Spatiotemporal Object Re-identification at the City Scale, Tiantu Xu, Kaiwen Shen, Yang Fu, Humphrey Shi, Felix Xiaozhu Lin, ArXiv Preprint, 2020
[TR] Deep Learning for 3D Point Cloud Understanding: A Survey, Haoming Lu, Humphrey Shi, ArXiv Preprint, 2020
[TR] Pyramid Attention Networks for Image Restoration, Yiqun Mei, Yuchen Fan, Yulun Zhang, Jiahui Yu, Yuqian Zhou, Ding Liu, Yun Fu, Humphrey Shi, ArXiv Preprint, 2020 (SOTA on multiple image restoration tasks)
[TR] Deep Affinity Net: Instance Segmentation via Affinity, Xingqian Xu, Mang Tik Chiu, Humphrey Shi, ArXiv Preprint, 2020 (SOTA on affinity-based instance segmentation)
[TR] A Simple Non-i.i.d. Sampling Approach for Efficient Training and Better Generalization, Bowen Cheng, Yunchao Wei, Jiahui Yu, Shiyu Chang, Jinjun Xiong, Wen-mei Hwu, Thomas S. Huang, Humphrey Shi, ArXiv Preprint, 2020
[TR] Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection, Bowen Cheng, Yunchao Wei, Rogerio Feris, Jinjun Xiong, Wen-mei Hwu, Thomas S. Huang, Humphrey Shi, ArXiv Preprint, 2018
2021 (CVPR x 3, AAAI x 3, TPAMI ...)
[C] Interpretable Visual Reasoning via Induced Symbolic Space, Zhonghao Wang, Kai Wang, Mo Yu, Jinjun Xiong, Wen-mei Hwu, Mark Hasegawa-Johnson, Humphrey Shi, ICCV, 2021 (SOTA on visual reasoning) (Joint work with IBM Research)
[C] Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach, Xingqian Xu, Zhifei Zhang, Zhaowen Wang, Brian Price, Zhonghao Wang, Humphrey Shi, CVPR, 2021 (acceptance rate 22.0 %)
[J] AlignSeg: Feature-Aligned Segmentation Networks, Zilong Huang, Yunchao Wei, Xinggang Wang, Wenyu Liu, Thomas Huang, Humphrey Shi, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021 (SOTA on semantic segmentation)
[W] MUSE: Illustrating Textual Attributes by Portrait Generation, Xiaodan Hu, Pengfei Yu, Kevin Knight, Heng Ji, Bo Li, Humphrey Shi, IEEE Workshop on AI for Art, 2021
[C] Any-Precision Deep Neural Networks, Haichao Yu, Haoxiang Li, Humphrey Shi, Thomas S. Huang, Gang Hua, AAAI, 2021 (Acceptance rate: 21.0%)
[C] High-Resolution Deep Image Matting, Haichao Yu, Ning Xu, Zilong Huang, Yuqian Zhou, Humphrey Shi, AAAI, 2021 (SOTA on image matting, Acceptance rate: 21.0%)
[C] CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentation, Yang Fu, Linjie Yang, Ding Liu, Thomas S. Huang, Humphrey Shi, AAAI, 2021 (Acceptance rate: 21.0%)
2020 (CVPR x 5, MICCAI, TPAMI, CCR, MLSys, AAAI ...)
[J] CCNet: Criss-Cross Attention for Semantic Segmentation, Zilong Huang, Xinggang Wang, Yunchao Wei, Lichao Huang, Humphrey Shi, Wenyu Liu, Thomas S. Huang, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020 (SOTA on semantic segmentation, top journal in computer science, impact factor 19.42)
[C] Motion Pyramid Networks for Accurate and Efficient Cardiac Motion Estimation, Hanchao Yu, Xiao Chen, Humphrey Shi, Terrence Chen, Thomas Huang, Shanhui Sun, MICCAI, 2020
[J] Deep Learning-based Automated Image Segmentation for Concrete Petrographic Analysis, Yu Song, Zilong Huang, Chuanyue Shen, Humphrey Shi, David A Lange, Cement and Concrete Research, 2020 (top journal for materials in civil engineering)
[W] Alleviating Semantic-level Shift: A Semi-supervised Domain Adaptation Method for Semantic Segmentation, Zhonghao Wang, Yunchao Wei, Rogerior Feris, Jinjun Xiong, Wen-Mei Hwu, Thomas S Huang, Honghui Shi, Visual Learning with Limited Labels @ CVPR, 2020 (SOTA on semi-supervised domain adaptation for semantic segmentation)
[W] The 1st Agriculture-Vision Challenge: Methods and Results, Mang Tik Chiu, Xingqian Xu, Kai Wang, Jennifer Hobbs, Naira Hovakimyan, Thomas S. Huang, Honghui Shi et. al., CVPR Workshops 2020
[C] Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation, Zhonghao Wang, Mo Yu, Yunchao Wei, Rogerio Feris, Jinjun Xiong, Wen-mei Hwu, Thomas Huang, Honghui Shi, CVPR, 2020 (SOTA on unsupervised domain adaptation for semantic segmentation, acceptance rate 22.0 %)
[C] FOAL: Fast Online Adaptive Learning for Cardiac Motion Estimation, Hanchao Yu, Shanhui Sun, Haichao Yu, Xiao Chen, Honghui Shi, Thomas Huang, Terrence Chen, CVPR, 2020 (fast & online adaptation method, acceptance rate 22.0 %)
[C] HigherHRNet: Scare-Aware Representation Learning for Bottom-Up Human Pose Estimation, Bowen Cheng, Bin Xiao, Jingdong Wang, Honghui Shi, Thomas Huang, Lei Zhang, CVPR, 2020 (SOTA on human pose estimation, acceptance rate 22.0 %)
[C] Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis, Mang Tik Chiu*, Xingqian Xu*, Yunchao Wei, Zilong Huang, Alexander Schwing, Robert Brunner, Hrant Khachatrian, Hovnatan Karapetyan, Ivan Dozier, Greg Rose, David Wilson, Adrian Tudor, Naira Hovakimyan, Thomas S. Huang, Honghui Shi, CVPR, 2020 (a novel dataset for agriculture, acceptance rate 22.0 %)
[C] Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining, Yiqun Mei, Yuchen Fan, Yuqian Zhou, Lichao Huang, Thomas S. Huang, Humphrey Shi, CVPR, 2020 (SOTA on image super-resolution, acceptance rate 22.0 %)
[C] When AWGN-based Denoiser Meets Real Noises, Yuqian Zhou, Jianbo Jiao, Haibin Huang, Yang Wang, Jue Wang, Honghui Shi, Thomas Huang, AAAI, 2020 (Acceptance rate: 20.6%)
[C] SkyNet: a Hardware-Efficient Method for Object Detection and Tracking on Embedded Systems, Xiaofan Zhang, Haoming Lu, Cong Hao, Jiachen Li, Bowen Cheng, Yuhong Li, Kyle Rupnow, Jinjun Xiong, Thomas Huang, Honghui Shi, Wen-mei Hwu, Deming Chen, MLSys, 2020 (Oral and Poster, acceptance rate 20.0 %)
2019 (ICCV x 2, CVPR x 2, AAAI x 2, BMVC ...)
[C] Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-ID, Yang Fu, Yunchao Wei, Guanshuo Wang, Yuqian Zhou, Honghui Shi, Thomas Huang, ICCV, 2019 (SOTA on cross dataset re-id, Oral, acceptance rate 4.3 %)
[C] SPGNet: Semantic Prediction Guidance for Scene Parsing, Bowen Cheng, Liang-Chieh Chen, Yunchao Wei, Yukun Zhu, Zilong Huang, Jinjun Xiong, Thomas Huang, Wen-mei Hwu, Honghui Shi, ICCV, 2019 (SOTA on Cityscapes, acceptance rate 25.0 %)
[C] Geometry-Aware Distillation for Indoor Semantic Segmentation, Jianbo Jiao, Yunchao Wei, Zequn Jie, Honghui Shi, Rynson W.H. Lau, Thomas S. Huang, CVPR, 2019 (acceptance rate 25.2 %)
[C] SpotTune: Transfer Learning through Adaptive Fine-tuning, Yunhui Guo, Honghui Shi, Abhishek Kumar, Kristen Grauman, Tajana Rosing, Rogerio Feris, CVPR, 2019 (SOTA on Visual Decathlon Challenge, acceptance rate 25.2 %)
[TR] SkyNet: A Champion Model for DAC-SDC on Low Power Object Detection, Xiaofan Zhang, Cong Hao, Haoming Lu, Jiachen Li, Yuhong Li, Yuchen Fan, Kyle Rupnow, Jinjun Xiong, Thomas Huang, Honghui Shi, Wen-mei Hwu, Deming Chen, DAC System Design Contest Technical Report, 2019
[C] Learning Object Detection from Scratch via Gated Feature Reuse , Zhiqiang Shen, Honghui Shi, Jiahui Yu, Hai Phan, Rogerio Feris, Liangliang Cao, Ding Liu, Xinchao Wang, Thomas S. Huang, Marios Savvides, BMVC, 2019
[C] A Novel Framework for 3D-2D Vertebra Matching, Hanchao Yu, Yang Fu, Haichao Yu, Yunchao Wei, Xinchao Wang, Jianbo Jiao, Zhangyang Wang, Bihan Wen, Matthew Bramlet, Thenkurussi Kesavadas, Honghui Shi, Thomas Huang, IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), 2019 (invited paper)
[C] Weakly Supervised Scene Parsing with Point-based Distance Metric Learning, Rui Qian, Yunchao Wei, Honghui Shi, Jiachen Li, Jiaying Liu, Thomas Huang, AAAI, 2019 (acceptance rate 16.2 %)
[C] Horizontal Pyramid Matching for Person Re-ID. Yang Fu, Yunchao Wei, Yuqian Zhou, Honghui Shi, Gao Huang, Xinchao Wang, Zhiqiang Yao, Thomas Huang, AAAI, 2019 (SOTA on person re-id, acceptance rate 16.2 %)
2018 (ECCV x 2, CVPR ...)
[W] Object-Centric Spatio-Temporal Activity Detection and Recognition, Mandis Beigi, Lisa M Brown, Quanfu Fan, John Henning, Chung-Ching Lin, Honghui Shi, Chiao-fe Shu, Rogerio Feris, NIST TRECVID Workshop, 2018
[C] Revisiting RCNN: On Awakening the Classification Power of Faster RCNN, Bowen Cheng, Yunchao Wei, Honghui Shi, Rogerio Feris, Jinjun Xiong, Thomas Huang, ECCV, 2018 (SOTA on PASCAL VOC, COCO, acceptance rate 31.8 %)
[C] TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection, Yunchao Wei, Zhiqiang Shen, Bowen Cheng, Honghui Shi, Jinjun Xiong, Jiashi Feng, Thomas Huang, ECCV, 2018 (acceptance rate 31.8 %)
[W] Geometry-aware Traffic Flow Analysis by Detection and Tracking, Honghui Shi, Zhonghao Wang, Xinchao Wang, Yang Zhang, Thomas Huang, Oral Presentation @ Nvidia AI City Challenge , CVPR Workshops, 2018
[C] Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation, Yunchao Wei, Huaxin Xiao, Honghui Shi, Zequn Jie, Jiashi Feng, Thomas S. Huang, CVPR, 2018 (Spotlight Oral, acceptance rate 6.7 %)
Before 2018 (have mainly worked on interdisciplinary research projects and several competitions)
[TR] Learning Object Detectors from Scratch with Gated Recurrent Feature Pyramids, Zhiqiang Shen, Honghui Shi, Rogerio Feris, Liangliang Cao, Shuicheng Yan, Ding Liu, Xinchao Wang, Xiangyang Xue, Thomas S. Huang, ArXiv Preprint, 2017
[W] Improving Context Modeling for Video Object Detection and Tracking, Yunchao Wei, Mengdan Zhang, Jianan Li, Yunpeng Chen, Jiashi Feng, Honghui Shi, Jian Dong, Shuicheng Yan, Oral Presentation @ Beyond ImageNet Large Scale Visual Recognition Challenge, CVPR Workshops, 2017
[W] Effective Object Detection from Traffic Camera Videos, Honghui Shi, Zhichao Liu, Yuchen Fan, Xinchao Wang, Thomas Huang, IEEE Smart World Congress, 2017 (Invited paper)
[W] Balanced Two-Stage Residual Networks for Image Super-Resolution, Yuchen Fan, Honghui Shi, Jiahui Yu, Ding Liu, Wei Han, Haichao Yu, Zhangyang Wang, Xinchao Wang, Thomas S. Huang, CVPR Workshops, 2017
[C] Computed Tomography Super-Resolution Using Convolutional Neural Networks, Haichao Yu, Ding Liu, Honghui Shi, Hanchao Yu, Zhangyang Wang, Xinchao Wang, Brent Cross, Matthew Bramlet, Thomas S. Huang, ICIP, 2017
[C] Epitomic Image Super-Resolution, Yingzhen Yang, Zhangyang Wang, Zhaowen Wang, Shiyu Chang, Ding Liu, Honghui Shi, Thomas S Huang, AAAI, 2016
[TR] Seq-NMS for Video Object Detection, Wei Han, Pooya Khorrami, Tom Le Paine, Prajit Ramachandran, Mohammad Babaeizadeh, Honghui Shi, Jianan Li, Shuicheng Yan, Thomas S. Huang, ImageNet VID Challenge Technical Report, 2016
[W] Seq-NMS and Rescoring for Video Object Detection, Pooya Khorrami, Tom Le Paine, Wei Han, Prajit Ramachandran, Mohammad Babaeizadeh, Honghui Shi, Thomas S. Huang, Poster Presentation @ ImageNet Challenge, ICCV Workshops, 2015
[C] Galaxy Classiο¬cation Using Deep Convolutional Neural Networks, Honghui Shi and Thomas Huang, GPU Technology Conference (GTC), 2015
Projects
[Proj] Collaborative research on multimedia with Blender Lab at UIUC (2020-2021)
[Proj] Collaborative research on visual reasoning with IBM Research (2020-Present)
[Proj] Automated Cerebral Aneurysm Segmentation & Applications in Resident Training, sponsored by Jump ARCHES (2020-Present)
[Proj] Automated Retinopathy of Prematurity Detection and Analysis, sponsored by Jump ARCHES (2020-Present)
[Proj] A Large-scale Dataset for Text Segmentation, Sponsored by Adobe Research (2020-Present)
[Proj] Cement Phase Segmentation, collaborated with UIUC Civil Engineering (2018-2020)
[Proj] Multiphoton Image Analysis for Cancer Diagnosis, sponsored by Mayo Clinic & UIUC (2018-2019)
[Proj] AI for Education, sponsored by New Oriental Education Technology (2018-2019)
[Proj] Deep Pattern Analysis in Agricultural Images, sponsored by IntelinAir (2018-2020)
[Proj] Deep Intermodal Video Analytics (DIVA), sponsored by IARPA, (2017-2021)
[Proj] Intelligent Learning Advisor, sponsored by IBM Research (2017-2021)
[Proj] Multi-Task Learning for Medical Image Analysis, sponsored by Siemens (2016-2019)
[Proj] Multi-modal Medical Image Understanding, sponsored by Jump ARCHES (2016-2018)
[Proj] Deep Learning in Financial Modeling and Strategy, sponsored by Jump Trading (2015-2018)
[Proj] Galaxy Classification, collaborated with UIUC Astronomy (2014-2015)
[Proj] Gravitational Lens Detection, collaborated with UIUC Astronomy (2014-2015)
Competitions
[Comp] IEEE/ACM DAC System Design Contest 1st Place (2019)
[Comp] NIST/IARPA TRECVID Activity Recognition Challenge 1st Place for both tracks (2018)
[Comp] Visual Relationship Detection - Google AI Open Images Challenge, Silver Medal (2018)
[Comp] Nvidia AI City Challenge 3rd Place (2018)
[Comp] CVPR Look Into Person Challenge 1st Place for all three tracks(2018)
[Comp] ImageNet Video Object Detection and Tracking Challenge 2nd Place for all four tracks(2017)
[Comp] Nvidia AI City Challenge 1st Place (2017)
[Comp] ImageNet Video Object Detection Challenge 3rd Place (2015)
[Comp] Galaxy Zoo - The Galaxy Challenge on Kaggle, Silver Medal (2014)
Workshops
[Org] IEEE International Conference of Humanized Computing and Communication with Artificial Intelligence (HCCAI), Irvine, California, 2020
[Org] The 2nd Workshop on Real-World Computer Vision from Inputs with Limited Quality (RLQ), ECCV, 2020
[Org] The 1st International Workshop and Prize Challenge on Agriculture-Vision: Challenges and Opportunities for Computer Vision in Agriculture, CVPR 2020 (with Microsoft, Google, IBM, Intelinair, MIT, UIUC, Purdue, Stanford etc.)
[Org] The 1st Workshop on Real-World Recognition from Low-Quality Images and Videos (RLQ), ICCV, 2019
[Org] The 1st Workshop on Weakly Supervised Learning for Real-World Computer Vision Applications & The 1st Learning from Imperfect Data (LID) Challenge, CVPR, 2019