Jiancheng Yang
Shanghai Jiao Tong University
81 Papers
108 Citations
Jiancheng Yang is an academic researcher from Shanghai Jiao Tong University. The author has contributed to research in topics: Computer science & Medicine. The author has an hindex of 11, co-authored 43 publications.
Chat about Author
Papers
Modeling Point Clouds With Self-Attention and Gumbel Subset Sampling
Jiancheng Yang,Qiang Zhang,Bingbing Ni,Linguo Li,Jinxian Liu,Mengdie Zhou,Qi Tian +6 more
- 01 Jun 2019
TL;DR: This work develops Point Attention Transformers (PATs), using a parameter-efficient Group Shuffle Attention (GSA) to replace the costly Multi-Head Attention, and proposes an end-to-end learnable and task-agnostic sampling operation, named Gumbel Subset Sampling (GSS), to select a representative subset of input points.
535
MedMNIST v2: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification
Jiancheng Yang,Rui Shi,Donglai Wei,Zequan Liu,Lin Zhao,Bilian Ke,Hanspeter Pfister,Bingbing Ni +7 more
TL;DR: A large-scale MNIST-like dataset collection of standardized biomedical images, including 12 datasets for 2D and 6 datasets for 3D, and benchmark several baseline methods on MedMNIST v2, including 2D / 3D neural networks and open-source / commercial AutoML tools.
MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis
TL;DR: MedMNIST Classification Decathlon is designed to benchmark AutoML algorithms on all 10 datasets, and has compared several baseline methods, including open-source or commercial AutoML tools.
270
Deep Kinematics Analysis for Monocular 3D Human Pose Estimation
Jingwei Xu,Zhenbo Yu,Bingbing Ni,Jiancheng Yang,Xiaokang Yang,Wenjun Zhang +5 more
- 14 Jun 2020
TL;DR: It is shown that optimizing the kinematics structure of noisy 2D inputs is critical to obtain accurate 3D estimations and targeted ablation study shows that each former step is critical for the latter one to obtain promising results.
3D Human Action Representation Learning via Cross-View Consistency Pursuit
Linguo Li,Minsi Wang,Bingbing Ni,Hang Wang,Jiancheng Yang,Wenjun Zhang +5 more
- 01 Jun 2021
TL;DR: Li et al. as discussed by the authors proposed a cross-view contrastive learning framework for unsupervised 3D skeleton-based action representation (CrosSCLR), by leveraging multi-view complementary supervision signal.