General

Xin Zhao, Ph.D., Professor

School of Computer and Communication Engineering, University of Science and Technology Beijing (USTB), previously in the Institute of Automation, Chinese Academy of Sciences (CASIA).

Address: 30 Xueyuan Road, Haidian District, Beijing, P.R.China

Zip Code: 100083

Tel: +86-10-82544720

Email: xzhaopersonal[at]foxmail.com,

xinzhao[at]ustb.edu.cn

News

2024.05: Xin servers as the Lead Guest Editor of International Journal of Computer Vision (IJCV). [Website]

2024.03: Xin servers as an Associate Editor (AE) of Pattern Recognition (PR). [Website]

2024.02: 1 paper accepted to CVPR2024 and 1 paper accepted to Pattern Recognition (PR).

2024.02: Xin co-organizes The 3rd CVPR Workshop on Vision Datasets Understanding. [Website]

2024.02: 1 paper accepted to AAAI2024 and 1 paper accepted to ICASSP2024.

2023.10: 1 paper accepted to IJCV. [Project Page]

2023.09: 1 paper accepted to IJCV [Project Page] and 1 paper accepted to NeurIPS 2023 Datasets and Benchmarks track.

2023.07: 1 paper accepted to ICCV2023.

2022.09: 1 paper accepted to NeurIPS2022.

2022.06: 1 paper accepted to Neurocomputing. [Project Page]

2022.03: 1 paper accepted to CVPR2022. [Project Page]

2022.02: 1 paper accepted to IEEE TPAMI. [Project Page] [Arxiv]

2022.02: 1 paper accepted to Pattern Recognition (PR).

2021.12: 1 paper accepted to AAAI2022.

2021.06: 1 paper accepted to IEEE TIP. [Arxiv]

2020.10: Serve as a Senior Program Committee Member for IJCAI2021.

2020.03: 1 paper accepted to IEEE TCSVT.

2019.11: 1 paper accepted to IEEE TPAMI. [Project Page]

2019.11: 3 papers accepted to AAAI2020, 1 ORAL.


Education

2007-07--2013-06   University of Science and Technology of China (USTC)   Ph.D.


Experience

From the year 2013, Dr. Zhao has been the Assistant Professor, Associate Professor and Professor in the Institute of Automation, Chinese Academy of Sciences (CASIA) and the School of Computer and Communication Engineering, University of Science and Technology Beijing (USTB), respectively.

Publications

2024

1. Global and local multi-modal feature mutual learning for retinal vessel segmentation.
Xin Zhao, Jing Zhang, Qiaozhe Li, Tengfei Zhao, Yi Li, Zifeng Wu.
Pattern Recognition (PR): 2024.

2. PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution.
Honghao Chen, Xiangxiang Chu, Yongjian Ren, Xin Zhao, Kaiqi Huang.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): 2024.

3. DDAE: Towards Deep Dynamic Vision BERT Pretraining.
Honghao Chen, Xiangwen Kong, Xiangyu Zhang, Xin Zhao, Kaiqi Huang.
38th AAAI Conference on Artificial Intelligence (AAAI): 2024.

4. Robust single-particle cryo-EM image denoising and restoration.
Jing Zhang, Tengfei Zhao, ShiYu Hu, Xin Zhao*. (*Corresponding Author).
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): 2024. [Arxiv]

2023

Shiyu Hu, Xin Zhao*, Lianghua Huang, Kaiqi Huang. (*Corresponding Author).
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI): 2023. [Project Page] [Arxiv] [BibTex]

Xin Zhao, Shiyu Hu, Yipei Wang, Jing Zhang, Yimin Hu, Rongshuai Liu, Haibin Ling, Yin Li, Renshu Li, Kun Liu, Jiadong Li.
International Journal of Computer Vision (IJCV): 2023. [Project Page] [PDF]

Shiyu Hu, Xin Zhao*, Kaiqi Huang. (*Corresponding Author).
International Journal of Computer Vision (IJCV): 2023. [Project Page] [Arxiv]

Shiyue Cao, Yueqin Yin, Lianghua Huang, Yu Liu, Xin Zhao*, Deli Zhao, Kaiqi Huang. (*Corresponding Author).
International Conference on Computer Vision (ICCV): 2023.

Shiyu Hu, Dailing Zhang, Meiqi Wu, Xiaokun Feng, Xuchen Li, Xin Zhao, Kaiqi Huang.
Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks: 2023. [Project Page]

2022

1. Temporal-adaptive Sparse Feature Aggregation for Video Object Detection.
Fei He, Qiaozhe Li, Xin Zhao*, Kaiqi Huang. (*Corresponding Author).
Pattern Recognition (PR): 2022. [BibTex]

2. Revisiting instance search: A new benchmark using cycle self-training.
Yuqi Zhang, Chong Liu, Weihua Chen, Xianzhe Xu, Fan Wang, Hao Li, Shiyu Hu, Xin Zhao*. (*Corresponding Author).
Neurocomputing (Neu): 2022. [Project Page] [BibTex]

3. PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation.
Naiyu Gao, Fei He, Jian Jia, Yanhu Shan, Haoyang Zhang, Xin Zhao*, Kaiqi Huang. (*Corresponding Author).
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): 2022. [Project Page]

4. InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation.
Fei He, Haoyang Zhang, Naiyu Gao, Jian Jia, Yanhu Shan, Xin Zhao*, Kaiqi Huang. (*Corresponding Author).
Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS): 2022.

5. QueryProp: Object Query Propagation for High-Performance Video Object Detection.
Fei He, Naiyu Gao, Jian Jia, Xin Zhao*, Kaiqi Huang. (*Corresponding Author).
36th AAAI Conference on Artificial Intelligence (AAAI): 2022.

2021

1. GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild.
Lianghua Huang#Xin Zhao#, Kaiqi Huang. (#Equal Contribution).
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI): 2021. [Project Page] [Arxiv] [BibTex] [ESI Highly Cited Papers, Hot Papers]

2. Learning Category- and Instance-Aware Pixel Embedding for Fast Panoptic Segmentation.
Naiyu Gao, Yanhu Shan, Xin Zhao*, Kaiqi Huang. (*Corresponding Author).
IEEE Transactions on Image Processing (TIP): 2021. [Arxiv] [BibTex]

3. SSAP: Single-Shot Instance Segmentation With Affinity Pyramid.
Naiyu Gao, Yanhu Shan, Yupei Wang, Xin Zhao, Kaiqi Huang.
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT): 2021. [BibTex]

2020

1. Recurrent Prediction with Spatio-temporal Attention for Crowd Attribute Recognition.
Qiaozhe Li, Xin Zhao, Ran He, Kaiqi Huang.
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT): 2020. [BibTex]

2. GlobalTrack: A Simple and Strong Baseline for Long-term Tracking.
Lianghua Huang, Xin Zhao*, Kaiqi Huang. (*Corresponding Author).
34rd AAAI Conference on Artificial Intelligence (AAAI): 2020. [Project Page]

3. Temporal Context Enhanced Feature Aggregation for Video Object Detection.
Fei He, Naiyu Gao, Qiaozhe Li, Senyao Du, Xin Zhao, Kaiqi Huang.
34rd AAAI Conference on Artificial Intelligence (AAAI): 2020.

4. TANet: Robust 3D Object Detection from Point Clouds with Triple Attention.
Zhe Liu, Xin Zhao, Tengteng Huang, Ruolan Hu, Yu Zhou, Xiang Bai.
34rd AAAI Conference on Artificial Intelligence (AAAI): 2020. [Project Page]

2019

1. Focal Boundary Guided Salient Object Detection.
Yupei Wang, Xin Zhao, Xuecai Hu, Yin Li, Kaiqi Huang.
IEEE Transactions on Image Processing (TIP): 2019. [BibTex]

2. Deep Crisp Boundaries: From Boundaries to Higher-level Tasks.
Yupei Wang, Xin Zhao, Yin Li, Kaiqi Huang.
IEEE Transactions on Image Processing (TIP): 2019. [Project Page] [Arxiv] [BibTex]

3. Bridging the Gap Between Detection and Tracking: A Unified Approach.
Lianghua Huang, Xin Zhao*, Kaiqi Huang. (*Corresponding Author).
International Conference on Computer Vision (ICCV): 2019.

4. SSAP: Single-Shot Instance Segmentation with Affinity Pyramid.
Naiyu Gao, Yanhu Shan, Yupei Wang, Xin Zhao*, Yinan Yu, Ming Yang, Kaiqi Huang. (*Corresponding Author).
International Conference on Computer Vision (ICCV): 2019.

5. Pedestrian Attribute Recognition by Joint Visual-semantic Reasoning and Knowledge Distillation.
Qiaozhe Li, Xin Zhao, Ran He, Kaiqi Huang.
International Joint Conference on Artificial Intelligence (IJCAI): 2019.

6. 3D Object Detection Using Scale Invariant and Feature Reweighting Networks.
Xin Zhao, Zhe Liu, Ruolan Hu, Kaiqi Huang.
33rd AAAI Conference on Artificial Intelligence (AAAI): 2019.

7. Visual-semantic Graph Reasoning for Pedestrian Attribute Recognition.
Qiaozhe Li, Xin Zhao, Ran He, Kaiqi Huang.
33rd AAAI Conference on Artificial Intelligence (AAAI): 2019.

8. VisDrone-SOT2019: The Vision Meets Drone Single Object Tracking Challenge Results.
Dawei Du et al..
International Conference on Computer Vision Workshop (ICCVW): 2019.

9. VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results.
Dawei Du et al..
International Conference on Computer Vision Workshop (ICCVW): 2019.

2018

1. Iterative Residual Network For Structured Edge Detection.
Yupei Wang, Xin Zhao, Kaiqi Huang.
IEEE International Conference on Image Processing (ICIP): 2018.

2. Densely Cascaded Shadow Detection Network via Deeply Supervised Parallel Fusion.
Yupei Wang, Xin Zhao, Yin Li, Xuecai Hu, Kaiqi Huang.
International Joint Conference on Artificial Intelligence (IJCAI): 2018.

3. Densely Connected Single-Shot Detector.
Pei Xu, Xin Zhao, Kaiqi Huang.
International Conference on Pattern Recognition (ICPR): 2018.

2017

1. Deep Crisp Boundaries.
Yupei Wang, Xin Zhao, Kaiqi Huang.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR): 2017.

2. Locality-Sensitive Deconvolution Networks with Gated Fusion for RGB-D Indoor Semantic Segmentation.
Yanhua Cheng, Rui Cai, Zhiwei Li, Xin Zhao, Kaiqi Huang.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR): 2017.

3. Adversarial Learning Based Saliency Detection.
Xuecai Hu, Xin Zhao, Kaiqi Huang, Tieniu Tan.
Asian Conference on Pattern Recognition (ACPR): 2017.

2016

1. LEARNING TEMPORALLY CORRELATED REPRESENTATIONS USING LSTMS FOR VISUAL TRACKING.
Qiaozhe Li, Xin Zhao, and Kaiqi Huang.
IEEE International Conference on Image Processing (ICIP): 2016.

2. Semi-Supervised Multimodal Deep Learning for RGB-D Object Recognition.
Yanhua Cheng, Xin Zhao, Rui Cai, Zhiwei Li, Kaiqi Huang, Yong Rui.
International Joint Conference on Artificial Intelligence (IJCAI): 2016.

2015

1. Semi-supervised learning and feature evaluation for RGB-D object recognition.
Yanhua Cheng, Xin Zhao, Kaiqi Huang, Tieniu Tan.
Computer Vision and Image Understanding (CVIU): 2015.

2. Query Adaptive Similarity Measure for RGB-D Object Recognition.
Yanhua Cheng, Rui Cai, Chi Zhang, Zhiwei Li, Xin Zhao, Kaiqi Huang and Yong Rui.
International Conference on Computer Vision (ICCV): 2015.

3. Convolutional fisher kernels for RGB-D object recognition.
Yanhua Cheng, Rui Cai, Xin Zhao, and Kaiqi Huang.
International Conference on 3D Vision (3DV): 2015.

4. 3D object retrieval with multimodal views.
Y. Gao et al..
Proceedings of the 2015 Eurographics Workshop on 3D Object Retrieval: 2015.

Before~2014

1. Semi-supervised Learning for RGB-D Object Recognition.
Yanhua Cheng, Xin Zhao, Kaiqi Huang, Tieniu Tan.
International Conference on Pattern Recognition (ICPR): 2014.

2. Feature Coding via Vector Difference for Image Classification.
Xin Zhao, Yinan Yu, Yongzhen Huang, Kaiqi Huang, Tieniu Tan.
IEEE International Conference on Image Processing (ICIP): 2012.

3. Semantic Windows in Sliding Window Based Object Detection.
Junge Zhang, Xin Zhao, Yongzhen Huang, Kaiqi Huang, Tieniu Tan.
International Conference on Pattern Recognition (ICPR): 2012.

4. Local Hypersphere Coding Based on Edges between Visual Words.
Weiqiang Ren, Yongzhen Huang, Xin Zhao, Kaiqi Huang, Tieniu Tan.
Asian Conference on Computer Vision (ACCV): 2012.

5. Global and Local Training for Moving Object Classification in Surveillance-Oriented Scene.
Xin Zhao, Jianwei Ding, Kaiqi Huang, Tieniu Tan.
Asian Conference on Pattern Recognition (ACPR): 2011.

6. Online Codebook Reweighting Using Pairwise Constraints for Image Classification.
Xin Zhao, Weiqiang Ren, Kaiqi Huang, Tieniu Tan.
Asian Conference on Pattern Recognition (ACPR): 2011.

7. A Comparison Study on Kernel Based Online Learning for Moving Object Classification.
Xin Zhao, Kaiqi Huang, Tieniu Tan.
Third Chinese Conference on Intelligent Video Surveillance (IVS): 2011.

8. Robust Moving Object Segmentation with Two Stage Optimization.
Jianwei Ding, Xin Zhao, Kaiqi Huang, Tieniu Tan.
Asian Conference on Pattern Recognition (ACPR): 2011.


Professional Services

2024, Associate Editor of Pattern Recognition (PR)

2024, Lead Guest Editor of International Journal of Computer Vision (IJCV)

2018 ~ Now, Reviewer of  CVPR, ICCV, ECCV, ICML, NeurIPS, AAAI, IJCAI, ICLR, WACV

2016 ~ Now, Reviewer of  IEEE TPAMI, IEEE TIP, IEEE TMM, IEEE TCSVT, IEEE TSMC, Pattern Recognition (PR), Neural Networks (NeuNet), Computer Vision and Image Understanding (CVIU), Neurocomputing (Neu)