1 code implementation • 27 Apr 2022 • Shu Zhang, ran Xu, Caiming Xiong, Chetan Ramaiah
Current contrastive learning frameworks focus on leveraging a single supervisory signal to learn representations, which limits the efficacy on unseen data and downstream tasks.
no code implementations • 4 Mar 2022 • Xi Chen, Jiahuan Lv, Dehua Feng, Xuanqin Mou, Ling Bai, Shu Zhang, Zhiguo Zhou
Accurately identifying patient's status through medical images plays an important role in diagnosis and treatment.
1 code implementation • 7 Feb 2022 • Danhuai Guo, Shiyin Ge, Shu Zhang, Song Gao, Ran Tao, Yangang Wang
Spatial-query-by-sketch is an intuitive tool to explore human spatial knowledge about geographic environments and to support communication with scene database queries.
1 code implementation • 5 Jan 2022 • Shu Zhang, Zihao Li, Hong-Yu Zhou, Jiechao Ma, Yizhou Yu
The difficulties in both data acquisition and annotation substantially restrict the sample sizes of training datasets for 3D medical imaging applications.
no code implementations • 1 Jul 2021 • Chenglin Yu, Dingnan Cui, Muheng Shang, Shu Zhang, Lei Guo, Junwei Han, Lei Du, Alzheimer's Disease Neuroimaging Initiative
Though deep learning models can extract the nonlinear relationship, they could not select relevant genetic factors.
no code implementations • 3 Jun 2021 • Hong-Yu Zhou, Chengdi Wang, Haofeng Li, Gang Wang, Shu Zhang, Weimin Li, Yizhou Yu
Semi-Supervised classification and segmentation methods have been widely investigated in medical image analysis.
1 code implementation • 21 Apr 2021 • Jie Lian, Jingyu Liu, Shu Zhang, Kai Gao, Xiaoqing Liu, Dingwen Zhang, Yizhou Yu
Leveraging on constant structure and disease relations extracted from domain knowledge, we propose a structure-aware relation network (SAR-Net) extending Mask R-CNN.
no code implementations • 16 Dec 2020 • Shu Zhang, Jing-Shu Li, Yang-Jie Su, Yu-Mei Zhang, Zi-Yuan Li, Zheng-Yun You
The liquid-based detectors are widely used in particle and nuclear physics experiments.
Instrumentation and Detectors
no code implementations • 16 Dec 2020 • Shu Zhang, Jincheng Xu, Yu-Chun Chen, Jiechao Ma, Zihao Li, Yizhou Wang, Yizhou Yu
We demonstrate that with the novel pre-training method, the proposed MP3D FPN achieves state-of-the-art detection performance on the DeepLesion dataset (3. 48% absolute improvement in the sensitivity of FPs@0. 5), significantly surpassing the baseline method by up to 6. 06% (in MAP@0. 5) which adopts 2D convolution for 3D context modeling.
1 code implementation • 16 Jun 2020 • Yimin Hou, Shuyue Jia, Xiangmin Lun, Shu Zhang, Tao Chen, Fang Wang, Jinglei Lv
To conclude, the GCNs-Net filters EEG signals based on the functional topological relationship, which manages to decode relevant features for brain motor imagery.
no code implementations • 2 May 2020 • Yimin Hou, Shuyue Jia, Xiangmin Lun, Shu Zhang, Tao Chen, Fang Wang, Jinglei Lv
The introduced deep feature mining approach can precisely recognize human motion intents from raw EEG signals, which paves the road to translate the EEG based MI recognition to practical BCI systems.
1 code implementation • CVPR 2020 • Hoang Le, Feng Liu, Shu Zhang, Aseem Agarwala
We then develop a multi-scale neural network and show that when properly trained using our new dataset, this neural network can already handle dynamic scenes to some extent.
no code implementations • 13 Dec 2019 • Hongwei Xv, Xin Sun, Junyu Dong, Shu Zhang, Qiong Li
Low-shot learning indicates the ability to recognize unseen objects based on very limited labeled training samples, which simulates human visual intelligence.
1 code implementation • 10 Sep 2019 • Zihao Li, Shu Zhang, Junge Zhang, Kaiqi Huang, Yizhou Wang, Yizhou Yu
In this paper, we propose to incorporate domain knowledge in clinical practice into the model design of universal lesion detectors.
Ranked #6 on
Medical Object Detection
on DeepLesion
no code implementations • 9 Jun 2019 • Benlin Hu, Cheng Lei, Dong Wang, Shu Zhang, Zhenyu Chen
Deep learning models have a large number of freeparameters that need to be calculated by effective trainingof the models on a great deal of training data to improvetheir generalization performance.
1 code implementation • CVPR 2019 • Chenyou Fan, Xiaofan Zhang, Shu Zhang, Wensheng Wang, Chi Zhang, Heng Huang
In this paper, we propose a novel end-to-end trainable Video Question Answering (VideoQA) framework with three major components: 1) a new heterogeneous memory which can effectively learn global context information from appearance and motion features; 2) a redesigned question memory which helps understand the complex semantics of question and highlights queried subjects; and 3) a new multimodal fusion layer which performs multi-step reasoning by attending to relevant visual and textual hints with self-updated attention.
Ranked #7 on
Visual Question Answering
on MSVD-QA
no code implementations • 24 Apr 2017 • Shu Zhang, Hui Yu, Ting Wang, Junyu Dong, Honghai Liu
With the increasing demands of applications in virtual reality such as 3D films, virtual Human-Machine Interactions and virtual agents, the analysis of 3D human face analysis is considered to be more and more important as a fundamental step for those virtual reality tasks.
3 code implementations • ICCV 2017 • Rui Huang, Shu Zhang, Tianyu Li, Ran He
This paper proposes a Two-Pathway Generative Adversarial Network (TP-GAN) for photorealistic frontal view synthesis by simultaneously perceiving global structures and local details.
no code implementations • COLING 2016 • Hailong Cao, Tiejun Zhao, Shu Zhang, Yao Meng
We introduce a distribution based model to learn bilingual word embeddings from monolingual data.
no code implementations • 16 Nov 2016 • Shu Zhang, Ran He, Tieniu Tan
The occlusions incurred by random meshes severely degenerate the performance of face verification systems, which raises the MeshFace verification problem between MeshFace and daily photos.
no code implementations • 21 May 2016 • Shu Zhang, Qi Zhu, Amit Roy-Chowdhury
In this paper, we focus on this problem and propose a framework to adaptively select the "best" algorithm-parameter combination and the computation platform under performance and cost constraints at design time, and adapt the algorithms at runtime based on real-time inputs.