Zhimin Gao

Zhimin Gao

Auto-generated profile, based on publicly available information

Zhimin Gao

School of Information Engineering, Zhengzhou University, Zhengzhou, China

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

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

Representative Publications

View All Publications
3 April 2018 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
PWPichao WANG
Pichao WANG
WLWanqing Li
Wanqing Li
ZGZhimin Gao
Zhimin Gao
CTChang Tang
Chang Tang
POPhilip O. Ogunbona
Philip O. Ogunbona
This paper proposes three simple, compact yet effective representations of depth sequences, referred to respectively as dynamic depth images (DDI), dynamic depth normal images (DDNI), and dynamic depth motion normal images (DDMNI), for both isolated and continuous action recognition. These dynamic images are constructed from a segmented sequence of depth maps using hierarchical bidirectional rank pooling to effectively capture the spatial-temporal information. Specifically, DDI exploits the dynamics of postures over time, and DDNI and DDMNI exploit the 3-D structural information captured by depth maps. Upon the proposed representations, a convolutional neural network (ConvNet)-based method is developed for action recognition. The image-based representations enable us to fine-tune the existing ConvNet models trained on image data without training a large number of parameters from scratch. The proposed method achieved the state-of-art results on three large datasets, namely, the large-scale continuous gesture recognition dataset (means the Jaccard index 0.4109), the large-scale isolated gesture recognition dataset (59.21%), and the NTU RGB+D dataset (87.08% cross-subject and 84.22% cross-view) even though only the depth modality was used.

28 July 2020 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
LCLisha Cui
Lisha Cui
LPLu Pei
Lu Pei
XJXiaoheng Jiang
Xiaoheng Jiang
ZGZhimin Gao
Zhimin Gao
BZBing Zhou
Bing Zhou
MXMingliang Xu
Mingliang Xu
State-of-the-art object detectors usually progressively downsample the input image until it is represented by small feature maps, which loses the spatial information and compromises the representation of small objects. In this article, we propose a context-aware block net (CAB Net) to improve small object detection by building high-resolution and strong semantic feature maps. To internally enhance the representation capacity of feature maps with high spatial resolution, we delicately design the context-aware block (CAB). CAB exploits pyramidal dilated convolutions to incorporate multilevel contextual information without losing the original resolution of feature maps. Then, we assemble CAB to the end of the truncated backbone network (e.g., VGG16) with a relatively small downsampling factor (e.g., 8) and cast off all following layers. CAB Net can capture both basic visual patterns as well as semantical information of small objects, thus improving the performance of small object detection. Experiments conducted on the benchmark Tsinghua-Tencent 100K and the Airport dataset show that CAB Net outperforms other top-performing detectors by a large margin while keeping real-time speed, which demonstrates the effectiveness of CAB Net for small object detection.

1 January 2021 in IEEE Transactions on Cognitive and Developmental Systems
Verified
Journal Article
Closed access
XLXiangyu Li
Xiangyu Li
YHYonghong Hou
Yonghong Hou
PWPichao WANG
Pichao WANG
ZGZhimin Gao
Zhimin Gao
MXMingliang Xu
Mingliang Xu
WLWanqing Li
Wanqing Li
In this article, we propose a transformer-based RGB-D egocentric action recognition framework, called Trear. It consists of two modules: 1) interframe attention encoder and 2) mutual-attentional fusion block. Instead of using optical flow or recurrent units, we adopt a self-attention mechanism to model the temporal structure of the data from different modalities. Input frames are cropped randomly to mitigate the effect of the data redundancy. Features from each modality are interacted through the proposed fusion block and combined through a simple yet effective fusion operation to produce a joint RGB-D representation. Empirical experiments on two large egocentric RGB-D data sets: 1) THU-READ and 2) first-person hand action, and one small data set, wearable computer vision systems, have shown that the proposed method outperforms the state-of-the-art results by a large margin.

1 November 2021 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
SMShuangyan Miao
Shuangyan Miao
YHYonghong Hou
Yonghong Hou
ZGZhimin Gao
Zhimin Gao
MXMingliang Xu
Mingliang Xu
WLWanqing Li
Wanqing Li
This paper proposes a new graph convolutional operator called central difference graph convolution (CDGC) for skeleton based action recognition. It is not only able to aggregate node information like a vanilla graph convolutional operation but also gradient information. Without introducing any additional parameters, CDGC can replace vanilla graph convolution in any existing Graph Convolutional Networks (GCNs). In addition, an accelerated version of the CDGC is developed which greatly improves the speed of training. Experiments on two popular large-scale datasets NTU RGB+D 60 & 120 have demonstrated the efficacy of the proposed CDGC. Code is available at https://github.com/iesymiao/CD-GCN .

2 March 2023
Verified
Book Chapter
Closed access
PDF file
ZGZhimin Gao
Zhimin Gao
PWPeitao Wang
Peitao Wang
LPLu Pei
Lu Pei
XJXiaoheng Jiang
Xiaoheng Jiang
QLQidong Liu
Qidong Liu
WLWanqing Li
Wanqing Li

2 January 2021 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
XLXiangyu Li
Xiangyu Li
YHYonghong Hou
Yonghong Hou
PWPichao WANG
Pichao WANG
ZGZhimin Gao
Zhimin Gao
MXMingliang Xu
Mingliang Xu
WLWanqing Li
Wanqing Li