Center for Future Media
Innovation Center, Qingshuihe Campus
-
No. 2006, Xiyuan Ave, Chengdu, China
- fshen@uestc.edu.cn
- +86 61831687
I am a Professor in School of Computer Science and Engineering, University of Electronic Science and Technology of China. I received my PhD degree from School of Computer Science, Nanjing University of Science and Technology, China in 2014. From 2010 to 2012, I visited NICTA, Australian National University and ACVT, University of Adelaide, Australia, as a joint PhD student supervised by Prof. Chunhua Shen. I received my bachelor degree in Applied Mathematics from Shandong University in 2007.
My research focuses on computer vision and multimedia, especially learning based hashing algorithms and their applications in visual retrieval and recognition problems. I have published 100+ papers in CVPR, ICCV, MM, SIGIR, TPAMI, TIP, TMM, TCSVT, etc. I have applied for 102 patents (82 granted). I have served as a regular PC member for ICCV, ACM MM, AAAI, ICMR, ICPR, MMM, journal reviewer for IEEE TIP, TNNLS, TKDE, TMM, TCYB, TCSVT, guest editor for Neurocomputing, PRL, NPL, special issue chair for ACPR'17 and special session organizer for MMM'16, ICMICS'16. I am the recipient of Elsevier 2020, 2021, 2022 Most Cited Chinese Researchers, the Best Paper Award Honorable Mention at ACM SIGIR 2016 & ACM SIGIR 2017 and the World's FIRST 10K Best Paper Award - Platinum Award at IEEE ICME 2017.
欢迎想加入我们实验室的本科生、研究生给我发邮件（fshen@uest.edu.cn）联系！ 欢迎有意向申请我校博后、正式教职（副教授/副研究员/研究员），或者依托我校申请海优的联系我。
Experience
| Professor | University of Electronic Science and Technology of China, China | 2017.07 ~ present |
| Associate Professor | University of Electronic Science and Technology of China, China | 2016.08 ~ 2017.06 |
| Lecturer | University of Electronic Science and Technology of China, China | 2015.03 ~ 2016.07 |
| Joint Ph.D. | ACVT, University of Adelaide, Australia | 2011.06 ~ 2012.11 |
| Joint Ph.D. | NICTA, Australian National University, Australia | 2010.11 ~ 2011.05 |
| Ph.D. | Nanjing University of Science and Technology, China | 2007.09 ~ 2014.04 |
| Bachelor | Shandong University, China | 2003.09 ~ 2007.07 |
News
2 papers accepted by TCSVT. 2024.10
2 papers accepted by TMM. 2024.8
1 papers accepted by AAAI. 2024.3
1 papers accepted by TNNLS. 2024.1
1 papers accepted by CVPR. 2024.1
1 papers accepted by ACM MM. 2023.10
1 papers accepted by TIP. 2023.10
1 papers accepted by TCSVT. 2023.8
1 papers accepted by TIP. 2023.4
1 papers accepted by TMM. 2023.4
1 papers accepted by TNNLS. 2023.3
1 papers accepted by TNNLS. 2022.10
1 papers accepted by ACM MM. 2022.10
1 papers accepted by ACM SIGIR. 2022.7
ICME Best Student Paper, 2022.07
1 papers accepted by AAAI. 2022.6
1 papers accepted by TMM. 2022.6
1 papers accepted by TMM. 2022.3
1 papers accepted by TMM. 2022.1
2 papers accepted by CVPR. 2022.1
3 papers accepted by CVPR 2019. See here. 2019-02
5 papers accepted by ECCV 2018. See here. 2018-07
4 papers accepted by ACM MM 2018. See here. 2018-07
We rand the 2nd place at WebVision Challenge 2018! Congratulations, Shengju! 2018-06
Our paper on Binary Multi-View Clustering is accepted by TPAMI. 2018-06
Our paper on Unsupervised Deep Hashing is published on TPAMI. 2017-10
Our paper on zero-shot learning is published on TPAMI. 2017-10
Our ACM SIGIR 2017 paper titled "Classification by Retrieval: Binarizing Data and Classifier" won the Best Paper Award Honorable Mention! 2017-08
Highlighted work More projects...
Recently, learning based hashing techniques have attracted broad research interests because they can support efficient storage and retrieval for high-dimensional data such as images, videos, documents, etc. However, a major difficulty of learning to hash lies in handling the discrete constraints imposed on the pursued hash codes, which typically makes hash optimizations very challenging (NP hard in general). The widely adopted relaxation scheme simplifies the optimization, however, tends to produce less effective codes.
In this project, we investigate how to directly learn binary codes via discrete optimization, namely discrete hashing. Discrete hashing has been shown to significantly boost the performance of hashing algorithms (e.g., Supervised Discrete Hashing) in large-scale similarity search.
Most binary coding and hashing algorithms were designed to deal with Approximate Nearest Neighbor (ANN) search. Studies have rarely been dedicated to Maximum Inner Product Search (MIPS), which actually plays a critical role in various vision and learning applications.
In this project, we investigate learning binary codes to exclusively handle the MIPS problem. The core problem is, the similaritis between two sets of data should be revealed by the inner products of their corresponding binary codes. We study this problem by proposing the Asymmetric Inner-product Bianry Coding algorithm for large-scale MIPS search, and the Discrete Collaborative Filtering algorithm for recommendation systems.
In the recent SIGIR paper, we study asymmetric hashing on the large-scale linear classification problem: classify examples by a linear transformation matrix from a large number of categories. This is a typical inner-product involving problem. We propose to respresent both the samples and classifiers using binary hash codese, which are simultaneously learned from the training data. Classifying an example thereby reduces to retrieving its nearest class codes in the Hamming spac, i.e., computing the Hamming distance between the binary codes of the example and classifiers and selecting the class with minimal Hamming distance.
Recent publications More papers...
-
Embracing Unimodal Aleatoric Uncertainty for Robust Multimodal Fusion,
Zixian Gao, Xun Jiang, Xing Xu, Fumin Shen, Yujie Li, Heng Tao Shen, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,
2024 [BibTeX]
@inproceedings{gao2024embracing, title={Embracing Unimodal Aleatoric Uncertainty for Robust Multimodal Fusion}, author={Gao, Zixian and Jiang, Xun and Xu, Xing and Shen, Fumin and Li, Yujie and Shen, Heng Tao}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={26876--26885}, year={2024} } -
Anti-Collapse Loss for Deep Metric Learning,
Xiruo Jiang, Yazhou Yao, Xili Dai, Fumin Shen, Liqiang Nie, Heng-Tao Shen, IEEE Transactions on Multimedia,
2024 [BibTeX]
@article{jiang2024anti, title={Anti-Collapse Loss for Deep Metric Learning}, author={Jiang, Xiruo and Yao, Yazhou and Dai, Xili and Shen, Fumin and Nie, Liqiang and Shen, Heng-Tao}, journal={IEEE Transactions on Multimedia}, year={2024}, publisher={IEEE} } -
Msflow: Multiscale flow-based framework for unsupervised anomaly detection,
Yixuan Zhou, Xing Xu, Jingkuan Song, Fumin Shen, Heng Tao Shen, IEEE Transactions on Neural Networks and Learning Systems,
2024 [BibTeX]
@article{zhou2024msflow, title={Msflow: Multiscale flow-based framework for unsupervised anomaly detection}, author={Zhou, Yixuan and Xu, Xing and Song, Jingkuan and Shen, Fumin and Shen, Heng Tao}, journal={IEEE Transactions on Neural Networks and Learning Systems}, year={2024}, publisher={IEEE} } -
Hierarchical graph pattern understanding for zero-shot video object segmentation,
Gensheng Pei, Fumin Shen, Yazhou Yao, Tao Chen, Xian-Sheng Hua, Heng Tao Shen, IEEE Transactions on Image Processing,
2023 [BibTeX]
@article{pei2023hierarchical, title={Hierarchical graph pattern understanding for zero-shot video object segmentation}, author={Pei, Gensheng and Shen, Fumin and Yao, Yazhou and Chen, Tao and Hua, Xian-Sheng and Shen, Heng-Tao}, journal={IEEE Transactions on Image Processing}, volume={32}, pages={5909--5920}, year={2023}, publisher={IEEE} } -
Hierarchical Co-Attention Propagation Network for Zero-Shot Video Object Segmentation,
Gensheng Pei, Yazhou Yao, Fumin Shen, Dan Huang, Xingguo Huang, Heng Tao Shen, IEEE Transactions on Image Processing,
2023 [BibTeX]
@article{pei2023hierarchical, title={Hierarchical co-attention propagation network for zero-shot video object segmentation}, author={Pei, Gensheng and Yao, Yazhou and Shen, Fumin and Huang, Dan and Huang, Xingguo and Shen, Heng-Tao}, journal={IEEE Transactions on Image Processing}, volume={32}, pages={2348--2359}, year={2023}, publisher={IEEE} } -
Attention Map Guided Transformer Pruning for Occluded Person Re-Identification on Edge Device,
Junzhu Mao, Yazhou Yao, Zeren Sun, Xingguo Huang, Fumin Shen, Heng Tao Shen, IEEE TRANSACTIONS ON MULTIMEDIA,
2023 [BibTeX]
@article{mao2023attention, title={Attention map guided transformer pruning for occluded person re-identification on edge device}, author={Mao, Junzhu and Yao, Yazhou and Sun, Zeren and Huang, Xingguo and Shen, Fumin and Shen, Heng-Tao}, journal={IEEE Transactions on Multimedia}, volume={25}, pages={1592--1599}, year={2023}, publisher={IEEE} } -
Semi-supervised Video Paragraph Grounding with Contrastive Encoder,
Xun Jiang, Xing Xu, Jingran Zhang, Fumin Shen, Zuo Cao, Heng Tao Shen, CVPR,
2022 [BibTeX]
@inproceedings{jiang2022semi, title={Semi-supervised video paragraph grounding with contrastive encoder}, author={Jiang, Xun and Xu, Xing and Zhang, Jingran and Shen, Fumin and Cao, Zuo and Shen, Heng Tao}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={2466--2475}, year={2022} } -
PNP: Robust Learning from Noisy Labels by Probabilistic Noise Prediction,
Zeren Sun, Fumin Shen, Dan Huang, Qiong Wang, Xiangbo Shu, Yazhou Yao, Jinhui Tang, CVPR,
2022 [BibTeX]
@inproceedings{sun2022pnp, title={Pnp: Robust learning from noisy labels by probabilistic noise prediction}, author={Sun, Zeren and Shen, Fumin and Huang, Dan and Wang, Qiong and Shu, Xiangbo and Yao, Yazhou and Tang, Jinhui}, booktitle={proceedings of the IEEE/CVF conference on computer vision and pattern recognition}, pages={5311--5320}, year={2022} } -
A Generalized Method for Binary Optimization: Convergence Analysis and Applications,
Huan Xiong, Mengyang Yu, Li Liu, Fan Zhu, Jie Qin, Fumin Shen, Ling Shao, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,,
2022 [BibTeX]
@article{xiong2021generalized, title={A Generalized Method for Binary Optimization: Convergence Analysis and Applications}, author={Xiong, Huan and Yu, Mengyang and Liu, Li and Zhu, Fan and Qin, Jie and Shen, Fumin and Shao, Ling}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume={44}, number={9}, pages={4524--4543}, year={2021}, publisher={IEEE} } -
TBN: Convolutional Neural Network with Ternary Inputs and Binary Weights,
Diwen Wan, Fumin Shen, Li Liu, Fan Zhu, Jie Qin, Ling Shao, Heng Tao Shen, European Conference on Computer Vision (ECCV),
2018 [BibTeX]
@inproceedings{'wan2018eccv', author = {Diwen Wan and Fumin Shen and Li Liu and Fan Zhu and Jie Qin and Ling Shao and Heng Tao Shen}, booktitle = {Proceeding of European Conference on Computer Vision (ECCV)}, title = {TBN: Convolutional Neural Network with Ternary Inputs and Binary Weights}, year = {2018} } -
Generative Domain-Migration Hashing for Sketch-to-Image Retrieval,
Jingyi Zhang, Fumin Shen, Li Liu, Fan Zhu, Mengyang Yu, Ling Shao, Heng Tao Shen, Luc Van Gool, European Conference on Computer Vision (ECCV),
2018 [BibTeX]
@inproceedings{'zhang2018eccv', author = {Jingyi Zhang and Fumin Shen and Li Liu and Fan Zhu and Mengyang Yu and Ling Shao and Heng Tao Shen and Luc Van Gool}, booktitle = {Proceeding of European Conference on Computer Vision (ECCV)}, title = {Generative Domain-Migration Hashing for Sketch-to-Image Retrieval}, year = {2018} } -
Binary Multi-View Clustering, Zheng Zhang, Li Liu, Fumin Shen, Heng Tao Shen and Ling Shao, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI),
2018 [PDF, Code, BibTeX]
@article{'zhang2018tpami', author = {Zheng Zhang and Li Liu and Fumin Shen and Heng Tao Shen and Ling Shao}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)}, title = {Binary Multi-View Clustering}, year = {2018} } -
Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization, Fumin Shen, Yan Xu, Li Liu, Yang Yang, Zi Huang, Heng Tao Shen IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI),
2018 [PDF, Code, BibTeX]
@article{'shen2018tpami', author = {Fumin Shen and Yan Xu and Li Liu and Yang Yang and Zi Huang and Heng Tao Shen}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)}, title = {Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization}, year = {2018} } -
Zero-shot Learning Using Synthesised Unseen Visual Data with Diffusion Regularisation,Yang Long, Li Liu, Fumin Shen, Ling Shao, Xuelong Li, IEEE
Transactions on Pattern Analysis and Machine Intelligence (TPAMI),
2017 [PDF, BibTeX]
@inproceedings{'long2017tpami', author = {Yang Long, Li Liu, Fumin Shen, Ling Shao, Xuelong Li}, article={IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)}, title = {Zero-shot Learning Using Synthesised Unseen Visual Data with Diffusion Regularisation}, year = {2017} } -
Classification by Retrieval: Binarizing Data and Classifier, Fumin Shen, Yadong Mu, Yang Yang, Wei Liu, Li Liu, Jingkuan Song, Heng Tao Shen, ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR),
2017 [PDF, BibTeX]
@inproceedings{'shen2017sigir', author = {Fumin Shen and Yadong Mu and Yang Yang and Wei Liu and Li Liu and Jingkuan Song and Heng Tao Shen}, booktitle={ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR}, title = {Learning Binary Codes and Binary Weights for Efficient Classification}, year = {2017} }
Awards
吴文俊人工智能科学技术奖-自然科学奖一等奖, 2023.03
Best Student Paper Award, The IEEE International Conference on Multimedia & Expo (ICME), 2022.07
Best Paper Award Honorable Mention, ACM SIGIR conference on Research and Development in Information Retrieval (SIGIR), 2017.08
World's FIRST 10K Best Paper Award – Platinum Award, The IEEE International Conference on Multimedia & Expo (ICME), 2017.07
Best Paper Award Honorable Mention, ACM SIGIR conference on Research and Development in Information Retrieval (SIGIR), 2016.07
- Outstanding Doctoral Dissertation, Nanjing University of Science & Technology, China, 2015.05
- Full Master and Ph.D. scholarship, Nanjing University of Science & Technology, China, 2007-2014