Zhao Sanyuan

Dr. Zhao Sanyuan

orcid

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

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

Representative Publications

View All Publications
6 October 2018
Verified
Book Chapter
Closed access
PDF file
HSHongmei Song
Hongmei Song
Wenguan WangWenguan Wang
Wenguan Wang
ZSZhao Sanyuan
Zhao Sanyuan
JSJianbing Shen
Jianbing Shen
KLKin-Man Lam
Kin-Man Lam

24 November 2022 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
YZYiyuan Zhang
Yiyuan Zhang
YKYuhao Kang
Yuhao Kang
ZSZhao Sanyuan
Zhao Sanyuan
JSJianbing Shen
Jianbing Shen
Visible-Infrared person Re-Identification (VI-ReID) conducts comprehensive identity analysis on non-overlapping visible and infrared camera sets for intelligent surveillance systems, which face huge instance variations derived from modality discrepancy. Existing methods employ different kinds of network structure to extract modality-invariant features. Differently, we propose a novel framework, named Dual-Semantic Consistency Learning Network (DSCNet), which attributes modality discrepancy to channel-level semantic inconsistency. DSCNet optimizes channel consistency from two aspects, fine-grained inter-channel semantics, and comprehensive inter-modality semantics. Furthermore, we propose Joint Semantics Metric Learning to simultaneously optimize the distribution of the channel-and-modality feature embeddings. It jointly exploits the correlation between channel-specific and modality-specific semantics in a fine-grained manner. We conduct a series of experiments on the SYSU-MM01 and RegDB datasets, which validates that DSCNet delivers superiority compared with current state-of-the-art methods. On the more challenging SYSU-MM01 dataset, our network can achieve 73.89% Rank-1 accuracy and 69.47% mAP value. Our code is available at https://github.com/bitreidgroup/DSCNet.


7 February 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
JCJianjian Cao
Jianjian Cao
XQXiameng Qin
Xiameng Qin
ZSZhao Sanyuan
Zhao Sanyuan
JSJianbing Shen
Jianbing Shen
Answering semantically complicated questions according to an image is challenging in a visual question answering (VQA) task. Although the image can be well represented by deep learning, the question is always simply embedded and cannot well indicate its meaning. Besides, the visual and textual features have a gap for different modalities, it is difficult to align and utilize the cross-modality information. In this article, we focus on these two problems and propose a graph matching attention (GMA) network. First, it not only builds graph for the image but also constructs graph for the question in terms of both syntactic and embedding information. Next, we explore the intramodality relationships by a dual-stage graph encoder and then present a bilateral cross-modality GMA to infer the relationships between the image and the question. The updated cross-modality features are then sent into the answer prediction module for final answer prediction. Experiments demonstrate that our network achieves the state-of-the-art performance on the GQA dataset and the VQA 2.0 dataset. The ablation studies verify the effectiveness of each module in our GMA network.

16 June 2018 in Machine Vision and Applications
Verified
Journal Article
Closed access
PDF file
ZLZhengchao Lei
Zhengchao Lei
ZSZhao Sanyuan
Zhao Sanyuan
HSHongmei Song
Hongmei Song
JSJianbing Shen
Jianbing Shen

9 April 2021 in Sensors
Verified
Journal Article
Open access
PDF file
Hao LiHao Li
Hao Li
ZSZhao Sanyuan
Zhao Sanyuan
WZWenjun Zhao
Wenjun Zhao
LZLibin Zhang
Libin Zhang
JSJianbing Shen
Jianbing Shen
Recent one-stage 3D detection methods generate anchor boxes with various sizes and orientations in the ground plane, then determine whether these anchor boxes contain any region of interest and adjust the edges of them for accurate object bounding boxes. The anchor-based algorithm calculates the classification and regression label for each anchor box during the training process, which is inefficient and complicated. We propose a one-stage, anchor-free 3D vehicle detection algorithm based on LiDAR point clouds. The object position is encoded as a set of keypoints in the bird’s-eye view (BEV) of point clouds. We apply the voxel/pillar feature extractor and convolutional blocks to map an unstructured point cloud to a single-channel 2D heatmap. The vehicle’s Z-axis position, dimension, and orientation angle are regressed as additional attributes of the keypoints. Our method combines SmoothL1 loss and IoU (Intersection over Union) loss, and we apply (cosθ,sinθ) as angle regression labels, which achieve high average orientation similarity (AOS) without any direction classification tricks. During the target assignment and bounding box decoding process, our framework completely avoids any calculations related to anchor boxes. Our framework is end-to-end training and stands at the same performance level as the other one-stage anchor-based detectors.