Tan Yu

I am currently a staff machine learning engineer in TikTok,  focusing on the ranking model for search ads in TikTok.  Perviously,  I was  a senior research scientist in Cognitive Computing Lab, Baidu USA, Seattle, led by Dr. Li Ping. My research focuses on short-video and image search for advertising, vision understanding backbone, cross-modal understanding and fine-grained recognition. 

Before that, I completed my PhD study in Nanyang Technological University under the supervision of Professor Junsong Yuan.  During that period, I completed a deep learning research internship in Snapchat Research, working with Dr. Zhou Ren, Dr. Yuncheng Li, Dr. En-Hsu Yen and Dr. Ning Xu and a deep learning research intern in Adobe Research, with Dr. Chen Fang and Dr. Hailin Jin. 

If you are interested in working with me as a research intern, please feel free to drop me an email through tyu008 at ucr dot edu or tyu008 at ntu dot edu dot sg.

Selected Publications

Tan Yu, Jun Li, Yunfeng Cai, Ping Li, Constructing Orthogonal Convolutions in an Explicit Manner, ICLR'22

Tan Yu, Yunfeng Cai, Ping Li, Efficient Compact Bilinear Pooling via Kronecker Product, AAAI'22

Tan Yu, Jie Liu, Yi Yang, Yi Li, Hongliang Fei, Ping Li,  EGM: Enhanced Graph-based Model  for Large-scale Video Advertisement Search KDD'22 

Tan Yu, Hongliang Fei, Ping Li, Cross-probe BERT for Fast Cross-modal Search, SIGIR'22 (short)

Haoliang Liu, Tan Yu, Ping Li, Sensitivity-aware Distance Measurement for Boosting Metric Learning, SDM'22 

Tan Yu, Xu Li, Yunfeng Cai, Mingming Sun, Ping Li, S^2-MLP: Spatial-Shift MLP Architecture for Vision, WACV'22

Tan Yu, Hongliang Fei, Ping Li, U-BERT for Fast and Scalable Text-Image Retrieval, ICTIR'22

Jiaheng Liu, Tan Yu, Hanyu Peng, Mingming Sun, Ping Li,  Cross-Lingual Cross-Modal Consolidation for Effective Multilingual Video Corpus Moment Retrieval,  NAACL'22 (findings)

Haoliang Liu, Tan Yu, Ping Li,  Inflate and Shrink:Enriching and Reducing Interactions for Fast Text-Image Retrieval, EMNLP'21 (oral) 

Tan Yu, Xu Li, Yunfeng Cai, Mingming Sun, Ping Li, Rethinking token-mixing MLP for MLP-based Vision Backbone, BMVC'21

Shuo Chen, Tan Yu, and Ping Li, MVT: Multi-view Vision Transformer for 3D Object Recognition, BMVC'21

Tan Yu, Yi Yang, Yi Li, Lin Liu, Hongliang Fei, Ping Li, Heterogeneous Attention Network for Effective and Efficient Cross-modal Retrieval SIGIR'21

Tan Yu, Xiaoyun Li, Ping Li, Fast and Compact Bilinear Pooling by Shifted Random Maclaurin, AAAI’21 

Tan Yu, Xuemeng Yang, Yan Jiang, Hongfang Zhang, Weijie  Zhao, Ping  Li,  TIRA in Baidu Image Advertising, ICDE'21

Tan Yu, Jingjing Meng,  Ming Yang, Junsong Yuan, 3D Object Representation Learning: A Set-to-set Matching Perspective, TIP'21

Hongliang Fei, Tan Yu, and Ping Li, Cross-lingual Cross-modal Pretraining for Multimodal Retrieval, NAACL'21 (short)

Huang Fang,  Guanhua Fang, Tan Yu, and Ping Li, Efficient Greedy Coordinate Descent via Variable Partitioning, UAI'21

Tan Yu and Ping Li, Multiple Exemplars Learning for Fast Image Retrieval,  CIKM’21

Tan Yu, Yi Yang, Yi Li, Lin Liu, Mingming Sun and Ping Li, Multi-modal Dictionary BERT for Cross-modal Video Search in Baidu Advertising, CIKM’21

Tan Yu, Yi Yang, Hongliang Fei, Yi Li, Xiaodong Chen and Ping Li,  Assorted Attention Network for Cross-Lingual Language-to-Vision Retrieval, CIKM’21

Tan Yu, Xiaokang Li, Jianwen Xie, Ruiyang Yin, Qing Xu and Ping Li, MixBERT for  Image-Ad Relevance Scoring in Advertising, CIKM’21 (short)

Tan Yu, Yunfeng Cai, Ping Li, Toward Faster and Simpler Matrix Normalization via Rank-1 Update, ECCV'20

Tan Yu, Yi Yang, Yi Li, Xiaodong Chen, Mingming Sun, Ping Li, Combo-attention Network for Baidu Video Advertising, KDD'20  Oral

Tan Yu, Jingjing Meng, Chen Fang, and Hailin Jin, Junsong Yuan,  Product Quantization Network for Fast Visual Search, IJCV'20

Tan Yu, Zhou Ren, Yuncheng Li, Enxu Yan, Ning Xu, Junsong Yuan, Temporal Structure Mining for Weakly Supervised Action Detection, ICCV'19

Tan Yu, Junsong Yuan, Chen Fang, and Hailin Jin, Product Quantization Network for Fast Image Retrieval, ECCV'18

Tan Yu, Jingjing Meng, and Junsong Yuan, Multi-view Harmonized Bilinear Network for 3D Object Recognition, CVPR'18(Spotlight)

Tan Yu, Zhenzhen Wang, and Junsong Yuan,  Compressive Quantization for Fast Object Instance Search in Videos,  ICCV'17

Tan Yu, Yuwei Wu, and Junsong Yuan,  HOPE: Hierarchical Object Prototype Encoding for Efficient Object Instance Search in Videos, CVPR'17

Tan Yu, Jingling Meng, and Junsong Yuan,  Is My Object in This Video? Reconstruction-based Object Search in Video, IJCAI'17 Codes Features

Tan Yu, Yuwei Wu, Das Bhattacharjee Sreyasee, and Junsong Yuan,  Efficient Object Instance Search Using Fuzzy Object Matching, AAAI'17

Professional Services

I am a reviewer for several CV conferences and journals, CVPR, ICCV,  ECCV, IJCAI, AAAI, WACV, ICME, ICIP, TPAMI, TIP, TCSVT, TMM.