Towards in-store multi-person tracking using head detection and track heatmaps

May 16, 2020
Aibek Musaev, Jiangping Wang, Liang Zhu, Cheng Li, Yi Chen, Jialin Liu, Wanqi Zhang, Juan Mei, De Wang


  Access Model/Code and Paper
Hierarchically Fair Federated Learning

May 01, 2020
Jingfeng Zhang, Cheng Li, Antonio Robles-Kelly, Mohan Kankanhalli


  Access Model/Code and Paper
Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Document Matching

Apr 26, 2020
Liu Yang, Mingyang Zhang, Cheng Li, Michael Bendersky, Marc Najork

* arXiv preprint version. 10 pages 

  Access Model/Code and Paper
Downstream Model Design of Pre-trained Language Model for Relation Extraction Task

Apr 08, 2020
Cheng Li, Ye Tian


  Access Model/Code and Paper
Incorporating Expert Prior in Bayesian Optimisation via Space Warping

Mar 27, 2020
Anil Ramachandran, Sunil Gupta, Santu Rana, Cheng Li, Svetha Venkatesh

* Knowledge-Based Systems (2020) 105663 
* 21 Pages, 8 figures. To be published in Elsevier 

  Access Model/Code and Paper
DLSpec: A Deep Learning Task Exchange Specification

Feb 26, 2020
Abdul Dakkak, Cheng Li, Jinjun Xiong, Wen-Mei Hwu


  Access Model/Code and Paper
Incorporating Expert Prior Knowledge into Experimental Design via Posterior Sampling

Feb 26, 2020
Cheng Li, Sunil Gupta, Santu Rana, Vu Nguyen, Antonio Robles-Kelly, Svetha Venkatesh


  Access Model/Code and Paper
MLModelScope: A Distributed Platform for Model Evaluation and Benchmarking at Scale

Feb 19, 2020
Abdul Dakkak, Cheng Li, Jinjun Xiong, Wen-mei Hwu


  Access Model/Code and Paper
Non-rigid Registration Method between 3D CT Liver Data and 2D Ultrasonic Images based on Demons Model

Dec 31, 2019
Shuo Huang, Ke wu, Xiaolin Meng, Cheng Li


  Access Model/Code and Paper
DLBricks: Composable Benchmark Generation to Reduce Deep Learning Benchmarking Effort on CPUs

Nov 20, 2019
Cheng Li, Abdul Dakkak, Jinjun Xiong, Wen-mei Hwu


  Access Model/Code and Paper
The Design and Implementation of a Scalable DL Benchmarking Platform

Nov 19, 2019
Cheng Li, Abdul Dakkak, Jinjun Xiong, Wen-mei Hwu


  Access Model/Code and Paper
Benanza: Automatic $μ$Benchmark Generation to Compute "Lower-bound" Latency and Inform Optimizations of Deep Learning Models on GPUs

Nov 19, 2019
Cheng Li, Abdul Dakkak, Jinjun Xiong, Wen-mei Hwu


  Access Model/Code and Paper
DLBricks: Composable Benchmark Generation toReduce Deep Learning Benchmarking Effort on CPUs

Nov 18, 2019
Cheng Li, Abdul Dakkak, Jinjun Xiong, Wen-mei Hwu


  Access Model/Code and Paper
Benanza: Automatic uBenchmark Generation to Compute "Lower-bound" Latency and Inform Optimizations of Deep Learning Models on GPUs

Nov 16, 2019
Cheng Li, Abdul Dakkak, Jinjun Xiong, Wen-mei Hwu


  Access Model/Code and Paper
Self-Adaptive Network Pruning

Oct 20, 2019
Jinting Chen, Zhaocheng Zhu, Cheng Li, Yuming Zhao

* Published as a conference paper at ICONIP 2019 
* 10 pages, 5 figures, conference 

  Access Model/Code and Paper
Efficiently Embedding Dynamic Knowledge Graphs

Oct 15, 2019
Tianxing Wu, Arijit Khan, Huan Gao, Cheng Li

* 14 pages 

  Access Model/Code and Paper
AI Matrix: A Deep Learning Benchmark for Alibaba Data Centers

Sep 23, 2019
Wei Zhang, Wei Wei, Lingjie Xu, Lingling Jin, Cheng Li


  Access Model/Code and Paper
Bayesian Network Based Risk and Sensitivity Analysis for Production Process Stability Control

Sep 10, 2019
Wei Xie, Bo Wang, Cheng Li, Jared Auclair, Peter Baker

* 42 pages, 4 figures, under review, submitted to European Journal of Operational Research (EJOR) 

  Access Model/Code and Paper
Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild

Aug 20, 2019
Yu Rong, Ziwei Liu, Cheng Li, Kaidi Cao, Chen Change Loy

* To appear in ICCV 2019. Code and models are available at https://penincillin.github.io/dct_iccv2019 

  Access Model/Code and Paper
Across-Stack Profiling and Characterization of Machine Learning Models on GPUs

Aug 19, 2019
Cheng Li, Abdul Dakkak, Jinjun Xiong, Wei Wei, Lingjie Xu, Wen-mei Hwu


  Access Model/Code and Paper
Model-based Convolutional De-Aliasing Network Learning for Parallel MR Imaging

Aug 06, 2019
Yanxia Chen, Taohui Xiao, Cheng Li, Qiegen Liu, Shanshan Wang


  Access Model/Code and Paper
Learning Cross-Modal Deep Representations for Multi-Modal MR Image Segmentation

Aug 06, 2019
Cheng Li, Hui Sun, Zaiyi Liu, Meiyun Wang, Hairong Zheng, Shanshan Wang

* 9 pages, 5 figures 

  Access Model/Code and Paper
One-shot Face Reenactment

Aug 05, 2019
Yunxuan Zhang, Siwei Zhang, Yue He, Cheng Li, Chen Change Loy, Ziwei Liu

* To appear in BMVC 2019 as a spotlight presentation. Code and models are available at: https://github.com/bj80heyue/One_Shot_Face_Reenactment 

  Access Model/Code and Paper
Accelerating Experimental Design by Incorporating Experimenter Hunches

Jul 22, 2019
Cheng Li, Santu Rana, Sunil Gupta, Vu Nguyen, Svetha Venkatesh, Alessandra Sutti, David Rubin, Teo Slezak, Murray Height, Mazher Mohammed, Ian Gibson

* IEEE International Conference on Data Mining (ICDM) 2018 

  Access Model/Code and Paper
CLCI-Net: Cross-Level fusion and Context Inference Networks for Lesion Segmentation of Chronic Stroke

Jul 17, 2019
Hao Yang, Weijian Huang, Kehan Qi, Cheng Li, Xinfeng Liu, Meiyun Wang, Hairong Zheng, Shanshan Wang


  Access Model/Code and Paper
X-Net: Brain Stroke Lesion Segmentation Based on Depthwise Separable Convolution and Long-range Dependencies

Jul 16, 2019
Kehan Qi, Hao Yang, Cheng Li, Zaiyi Liu, Meiyun Wang, Qiegen Liu, Shanshan Wang


  Access Model/Code and Paper
Sparse Spectrum Gaussian Process for Bayesian Optimisation

Jun 21, 2019
Ang Yang, Cheng Li, Santu Rana, Sunil Gupta, Svetha Venkatesh


  Access Model/Code and Paper
Disentangling Content and Style via Unsupervised Geometry Distillation

May 11, 2019
Wayne Wu, Kaidi Cao, Cheng Li, Chen Qian, Chen Change Loy

* Accepted to ICLR 2019 Workshop 

  Access Model/Code and Paper