Visual Understanding

Research Highlights (back to Research Overview)

Please find more publication and technical reports on Google Scholar. Some of our codes and datasets are available at GitHub.

Abbreviations: [C]: Conference; [J] Journal; [W] Workshop; [TR]: Technical Report; [B]: Book; [P]: Patent; [Comp]: Competition; [Proj]: Project; [Org] Program Organization; [SOTA]: State-of-the-art (at the time of publication)

Image Classification

• • [TR] Any-Precision Deep Neural Networks, Haichao Yu, Haoxiang Li, Honghui Shi, Thomas S. Huang, Gang Hua, ArXiv Preprint, 2019

  • [TR] Revisiting Pre-training: An Efficient Training Method for Image Classification, Bowen Cheng, Yunchao Wei, Honghui Shi, Shiyu Chang, Jinjun Xiong, Thomas S. Huang, ArXiv Preprint, 2018

  • [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 %)

  • [C] Galaxy Classification Using Deep Convolutional Neural Networks, Honghui Shi, Thomas Huang, GTC, 2015

  • [Comp] Galaxy Zoo - The Galaxy Challenge on Kaggle, Silver Medal (2014)

Object Detection

• • [TR] Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection, Bowen Cheng, Yunchao Wei, Honghui Shi, Rogerio Feris, Jinjun Xiong, Thomas Huang, ArXiv Preprint, 2018

  • [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] 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 %)

  • [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

  • [C] Effective Object Detection from Traffic Camera Videos, Honghui Shi, Zhichao Liu, Yuchen Fan, Xinchao Wang, Thomas Huang, IEEE Smart World Congress, 2017 (Invited paper)

  • [Comp] Nvidia AI City Challenge 1st Place (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, Beyond ImageNet Large Scale Visual Recognition Challenge @ CVPR, 2017

  • [Comp] ImageNet Video Object Detection and Tracking Challenge 2nd Place (2017)

  • [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, ArXiv Preprint, 2016

  • [Comp] ImageNet Video Object Detection Challenge 3rd Place (2015)

Segmentation

• • [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)

  • [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] Differential Treatment for Stuff and Things: A Simple Unsupervised DomainAdaptation 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 %)

  • [Proj] A Large-scale Dataset for Text Segmentation, Sponsored by Adobe Research

  • [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] 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] 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 %)

Activity Recognition

• • [Proj] Deep Intermodal Video Analytics (DIVA), sponsored by IARPA, 2017.10 - 2021.09

  • [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

  • [Comp] NIST/IARPA TRECVID Activity Recognition Challenge 1st Place (2018)

Visual Relationship, Reasoning, Grounding; Vision + Language

• • [Proj] Collaborative research on multimedia with Blender Lab at UIUC, 2020

  • [Proj] Collaborative research on visual reasoning with IBM Research, 2020

  • [Comp] Visual Relationship Detection - Google AI Open Images Challenge, Silver Medal (2018)

Human-Centered Vision

• • [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] 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] 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 %)

Low-Level Vision

• • [TR] Pyramid Attention Networks for Image Restoration, Yiqun Mei, Yuchen Fan, Yulun Zhang, Jiahui Yu, Yuqian Zhou, Ding Liu, Yun Fu, Thomas S. Huang, Humphrey Shi, ArXiv Preprint, 2020 (SOTA on multiple image restoration tasks)

  • [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

  • [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] 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