Shuyan Liu

Ms. Shuyan Liu

Big Data Research and Application Technology, China Aero-Polytechnology Establishment, Beijing, China
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 May 2022
Verified
Conference Paper
Closed access
YHYuhang Huang
Yuhang Huang
JZJunjie Zhang
Junjie Zhang
SLShuyan Liu
Shuyan Liu
QBQian Bao
Qian Bao
DZDan Zeng
Dan Zeng
WLWu Liu
Wu Liu
Dancing to music is an artistic behavior of humans, however, letting machines generate dances from music is still challenging. Most existing works have been made progress in tackling the problem of motion prediction conditioned by music, yet they rarely consider the importance of the musical genre. In this paper, we focus on generating long-term 3D dance from music with a specific genre. Specifically, we construct a pure transformer-based architecture to correlate motion features and music features. To utilize the genre information, we propose to embed the genre categories into the transformer decoder so that it can guide every frame. Moreover, different from previous inference schemes, we introduce the motion queries to output the dance sequence in parallel that significantly improves the efficiency. Extensive experiments on AIST++[1] dataset show that our model outperforms state-of-the-art methods with a much faster inference speed.

13 May 2023 in Mathematics
Verified
Journal Article
Open access
PDF file
LHLiu He
Liu He
SLShuyan Liu
Shuyan Liu
RARan An
Ran An
YZYudong Zhuo
Yudong Zhuo
JTJian Tao
Jian Tao
Remote sensing cross-modal text-image retrieval (RSCTIR) has recently attracted extensive attention due to its advantages of fast extraction of remote sensing image information and flexible human–computer interaction. Traditional RSCTIR methods mainly focus on improving the performance of uni-modal feature extraction separately, and most rely on pre-trained object detectors to obtain better local feature representation, which not only lack multi-modal interaction information, but also cause the training gap between the pre-trained object detector and the retrieval task. In this paper, we propose an end-to-end RSCTIR framework based on vision-language fusion (EnVLF) consisting of two uni-modal (vision and language) encoders and a muti-modal encoder which can be optimized by multitask training. Specifically, to achieve an end-to-end training process, we introduce a vision transformer module for image local features instead of a pre-trained object detector. By semantic alignment of visual and text features, the vision transformer module achieves the same performance as pre-trained object detectors for image local features. In addition, the trained multi-modal encoder can improve the top-one and top-five ranking performances after retrieval processing. Experiments on common RSICD and RSITMD datasets demonstrate that our EnVLF can obtain state-of-the-art retrieval performance.

16 December 2020
Verified
Conference Paper
Closed access
SLShuyan Liu
Shuyan Liu
JRJunda Ren
Junda Ren
ZCZhineng Chen
Zhineng Chen
KHKai Hu
Kai Hu
FXFen Xiao
Fen Xiao
XGXieping Gao
Xieping Gao
Breast cancer diagnosis in multi-gigapixel whole slide images (WSIs) is an important task that highly relevant to cancer grading and prognosis. In recent years, many computer-aided diagnosis methods were proposed and achieved promising performance. However, they mostly suffer from heavy computational burden that becomes a significant barrier to clinical practice. Efficient solutions are urgently demanded but still less studied. In this paper, we propose a novel framework named EffiDiag for a fast and lightweight breast cancer diagnosis. To this end, a loss-modified U-net is developed at first to enable a fast suspected cancer Region Of Interest (ROI) localization. Therefore the subsequent patch-based classification, which commonly executes at the finest magnification hundreds of thousands times per WSI for cancer identification, could be carried out on these ROIs only rather than the whole WSI for speedup. Meanwhile, a super-efficient convolutional neural network (CNN) is devised to optimize the classification speed and resource consumption per classification. Experiments on the Camelyonl6 benchmark demonstrate, by integrating the two contributions into a well-established approach, 47x inference acceleration is obtained with limited accuracy drop, yet with much less resource consumption even compared to popular lightweight networks.

1 December 2021
Verified
Conference Paper
Closed access
SLShuyan Liu
Shuyan Liu
YCYue Chen
Yue Chen
Due to the high complexity and dimensionality of stock price data, high volatility and uncertainty cause an over-fitting problem in predicting stock price. In this paper, we compare different combinations of variant Principal Component Analysis (PCA) methods and Recurrent Neural Network (RNN) based frameworks that can be applied to extract high-level features from a rich set of initial variables for producing 2-year ahead forecasts of the daily stock price of IBM and Wells Fargo. The objective of our comparative study is to find which combination performs best in forecasting different stock price data. The experimental results show that the best combination for IBM is 2-Directional 2-Dimensional PCA (2d2d-PCA) with Long Short-Term Memory (LSTM), which achieves accuracy of 91.77% based on R-Square (R 2 ) and for Wells Fargo is 2d2d-PCA with Gated Recurrent Unit (GRU), which achieves accuracy of 92.47%. Our comparative study indicates that the best combination of dimension reduction method and deep learning model is unfixed for predicting different stock price data. In addition, it is confirmed that GRU is an efficient model in predicting stock price; and 2d2d-PCA performs as well as PCA with respect to other dimension reduction methods with less error.