Shuhui Jiang

Ph.D.

Electrical & Computer Engineering,

Northeastern University, USA

shjiang0531 [AT] gmail [DOT] com

shjiang[AT] ece [DOT] neu [DOT] edu

Biography [Linkedin][resume]

I received my Ph.D. degree from the School of Electrical and Computer Engineering, Northeastern University (Boston, USA). I am in SMILE Lab, supervised by Prof. Yun Raymond Fu. I received my Master's and Bachelor's degrees from the School of Electrical and Communication, Xi'an Jiaotong University (Xi'an, China) in 2014. I am in SMILES Lab, supervised by Prof. Xueming Qian. I joined Shiseido Americas Corporation, Technology Acceleration Hub, as a senior computer vision engineer in 2018. I joined AEDIT as a computer vision engineer in 2020. I was a summer intern in Adobe Research in 2016 and Expedia in 2017.

Research Interests

My research interest lies in broad topics in Artificial Intelligence (AI), especially computer vision, machine learning, and multimedia. One of my major research focuses is developing AI technologies for fashion, beauty, design, and art. I am also interested in large-scale social media analysis and personalized recommendations. My work won the Best Paper Award of ACM Transactions on Multimedia Computing Communications and Applications (TOMM) in 2019 and been selected as the best paper candidate of ACM Multimedia (ACM MM) 2017.

  • Fashion style classification, retrieval, recommendation and generation.

  • Deep learning (e.g., Auto-Encoder, CNN, Siamese Network, GAN).

  • Large-scale data mining and personalized recommendation on social media.

  • Cross-domain and cross-modality transfer learning.

  • Robust feature representation learning

News [More]

  • 02/22 I was invited to the Technical Program Committee (TPC) of ACM MM 2022.

  • 01/22 I was invited to the Technical Program Committee (TPC) of MIPR.

  • 01/22 I was invited as the reviewer of IEEE TAI.

  • 10/21 I got one paper accepted by IEEE FG. Congratulations to all the authors.

  • 01/21 I got one paper accepted by TNNLS. Congratulations to all the authors.

  • 12/20 I was invited as the reviewer for ACM TKDD

  • 06/20 I was invited to the program committee of ACM Multimedia.

  • 05/20 I was invited to the program committee of MLSP 2020

  • 05/20 I was invited to the program committee of ICMLA 2020

Work Experience

  • Computer vision engineer in AEDIT since 2020. AI for beauty.

  • Senior computer vision engineer in Shiseido Americas Corporation, Technology Acceleration Hub from 2018 to 2020. AI for fashion and beauty.

  • Deep learning research intern in Imagination Lab in Adobe Research, San Jose, CA from May to August in 2016. I worked with Zhaowen Wang, Hailin Jin and Aaron Hertzmann.

  • Data science intern in Data Science team in Expedia, Bellevue, WA from May to August in 2017.

  • Research assistant at Northeastern University.

Teaching Experience (Teaching Assistant)

    • EECE3468 Noise & Stochastic Processes, 2017, 2018 Spring

    • EECE5639 Computer Vision, 2016 Spring

    • EECE7323 Numerical Optimization Method, 2016 Fall

Selected Publication [Google Scholar] [DBLP]

  • Book Chapter

Shuhui Jiang and Yun Fu. "Style classification by Deep Learning", Deep Learning through Sparse and Low-Rank Modeling, Elsevier, 2017

  • Journals:

[J-1]Shuhui Jiang, Jun Li and Yun Fu, "Deep Learning for Fashion Style Generation", IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021.

[J-2]Shuhui Jiang, Zhengming Ding and Yun Fu, "Heterogeneous Recommendation via Deep Low-rank Sparse Collective Factorization", The IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019.

[J-3]Shuhui Jiang, Haiyi Mao and Yun Fu, "Deep Decision Tree Transfer Boosting", IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2019.

[J-4]Shuhui Jiang, Zhaowen Wang, Aaron Hertzmann, Hailin Jin, and Yun Fu. "Visual Font Pairing", IEEE Transactions. on Multimedia (TMM), 2019.

[J-5]Shuhui Jiang, Yue Wu, Yun Fu, "Deep Bi-directional Cross-triplet Embedding for Online Clothing Shopping", ACM Transactions on Multimedia Computing Communications and Applications (TOMM), 2018.

[J-6]Shuhui Jiang, Yu Kong and Yun Fu, "Deep Geo-constrained Auto-Encoder for Non-landmark GPS Estimation", IEEE Transactions on Big Data (TBD), 2017.

[J-7]Shuhui Jiang, Ming Shao, Chengcheng Jia and Yun Fu, "Learning Consensus Representation for Weak Style Classification", The IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017.

[J-8]Shuhui Jiang, Xueming Qian, Tao Mei and Yun Fu, "Personalized Travel Sequence Recommendation on Multi-Source Big Social Media", IEEE Transactions on Big Data (TBD), 2016.

[J-9]Shuhui Jiang, Xueming Qian*, Jialie Shen, Yun Fu, and Tao Mei, “Author Topic Model-based Collaborative Filtering for Personalized POI Recommendations”, IEEE Transactions. on Multimedia (TMM), 2015.

  • Conferences:

[C-1] Huixian Zhang, Shuhui Jiang, and Yun Fu, Stylized Text-to-Fashion Image Generation, ACM Multimedia (ACM MM), IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2021.

[C-2] Shuhui Jiang, Zhengming Ding and Yun Fu, Deep Low-rank Sparse Collective Factorization for Cross-Domain Recommendation, ACM Multimedia (ACM MM), in Mountain View, CA USA from 23 to 27 October 2017. (Best paper candidate, 4 out of 864, Full paper, Oral presentation.)

[C-3]Shuhui Jiang and Yun Fu, Fashion Style Generator, In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI) in Melbourne, Australia in August 19 to 25 August 2017. (Oral and poster presentation. 660 out of 2540.)

[C-4]Shuhui Jiang, Yue Wu, and Yun Fu, Deep Bi-directional Cross-triplet Embedding for Cross-Domain Clothing Retrieval,

In Proceedings of the 24th ACM on Multimedia Conference (ACM MM) in Amsterdam, Netherlands, from 15 to 19 October 2016. pp. 52-56. (Short paper, poster presentation. 141 out of 675.)

[C-5]Shuhui Jiang, Ming Shao, Chengcheng Jia, Yun Fu, "Consensus Style Centralizing Auto-encoder for Weak Style Classification". In Proceedings of the thirtieth AAAI Conference on Artificial Intelligence (AAAI) in Phoenix, Arizona, USA, February 14 to 17, 2017. pp. 1223-1229. (Oral presentation. 549 out of 2132.)

  • Patents:

[P-1] Shuhui Jiang, Aneesh Bhat, Kai Ho Edgar Cheung, Yun Fu. “System and Method for Image Transformation”. U.S. Patent App. 63/047,335 (Shiseido)

[P-2] Zhaowen Wang, Hailin Jin, Aaron Hertzmann, Shuhui Jiang, “Automatically Pairing Fonts Using Asymmetric Metric Learning". US Patent 11,003,831 (Adobe)

[P-3] Jiang, Xueming Qian, Ke Lan, Jing Li and Fan Li, “Social Media User Multimedia Data Management”. NO. ZL 2001 1 0364974.4