Search Results - "Maodi Hu"

View-Invariant Discriminative Projection for Multi-View Gait-Based Human Identification by Maodi Hu, Yunhong Wang, Zhaoxiang Zhang, Little, James J., Di Huang

“…Existing methods for multi-view gait-based identification mainly focus on transforming the features of one view to the features of another view, which is…”
Get full text

Incremental Learning for Video-Based Gait Recognition With LBP Flow by Maodi Hu, Yunhong Wang, Zhaoxiang Zhang, De Zhang, Little, James J.

“…Gait analysis provides a feasible approach for identification in intelligent video surveillance. However, the effectiveness of the dominant silhouette-based…”
Get full text

Gait-Based Gender Classification Using Mixed Conditional Random Field by Hu, Maodi, Wang, Yunhong, Zhang, Zhaoxiang, Zhang, De

“…This paper proposes a supervised modeling approach for gait-based gender classification. Different from traditional temporal modeling methods, male and female…”
Get full text

Estimation of view angles for gait using a robust regression method by Zhang, De, Wang, Yunhong, Zhang, Zhaoxiang, Hu, Maodi

“…The performance of most gait recognition methods would drop down if the viewpoint of test data is different from the viewpoint of training data. In this paper,…”
Get full text

Combining Spatial and Temporal Information for Gait Based Gender Classification by Maodi Hu, Yunhong Wang, Zhaoxiang Zhang, Yiding Wang

“…In this paper, we address the problem of gait based gender classification. The Gabor feature which is a new attempt for gait analysis, not only improves the…”
Get full text

Multi-view multi-stance gait identification by Maodi Hu, Yunhong Wang, Zhaoxiang Zhang, De Zhang

“…View transformation in gait analysis has attracted more and more attentions recently. However, most of the existing methods are based on the entire gait…”
Get full text

Confusion Region Mining for Crowd Counting by Zhu, Jiawen, Zhao, Wenda, Yao, Libo, He, You, Hu, Maodi, Zhang, Xiaoxing, Wang, Shuo, Li, Tao, Lu, Huchuan

“…Existing works mainly focus on crowd and ignore the confusion regions which contain extremely similar appearance to crowd in the background, while crowd…”
Get full text

KDPG-Enhanced MRC Framework for Scientific Entity Recognition in Survey Papers by Hu, Maodi, Qian, Li, Chang, Zhijun, Zhang, Zhixiong

“…Scientific survey papers play a pivotal role in advancing knowledge and scientific progress by providing concise summaries and analyses of research trends and…”
Get full text

Social Frequency Analysis of University Students via Digital Campus Cards by Yu Liu, Maodi Hu, Xiaoqing Lu

“…In a normal digital campus card system, three kinds of data have been collected, which are consuming records, entry records, and book borrowing records. Many…”
Get full text

Theoretical Model and Effects Analysis of Collective Synergistic Learning by Yu Liu, Ling Chen, Maodi Hu

“…Based on the e-Education framework of Collective Synergistic Learning, this study builds a Collective Synergistic Reading model in terms of reading ability…”
Get full text

A New Approach for Gender Classification Based on Gait Analysis by Maodi Hu, Yunhong Wang

“…In this paper, we propose a novel pattern to represent spatio-temporal information of gait appearance which is called Gait Principal Component Image (GPCI)…”
Get full text

Adaptive Background Modelling for Image Sequences with Cluttered Background by Maodi Hu, Yu Liu, Yiqiang Fan

“…Background subtraction is a key technique for video analysis applications. However, the existing algorithms do not work well in cluttered environments. In this…”
Get full text

Ethnicity classification based on fusion of face and gait by De Zhang, Yunhong Wang, Zhaoxiang Zhang, Maodi Hu

“…The recognition of ethnicity of an individual can be very useful in a video-based surveillance system. In this paper, we propose a multimodal biometric system…”
Get full text

Construction Model of AI-Ready for Scientific and Technological Intelligence Data Resources by Li, QIAN, LIU, Zhibo, HU Maodi, CHANG, Zhijun

“…[Purpose/Significance] The new quality productivity advancing AI technology, especially exemplified by large language models (LLMs), is rapidly updating and…”
Get full text

Parameter-Efficient Prompt Tuning Makes Generalized and Calibrated Neural Text Retrievers by Tam, Weng Lam, Liu, Xiao, Ji, Kaixuan, Xue, Lilong, Zhang, Xingjian, Dong, Yuxiao, Liu, Jiahua, Hu, Maodi, Tang, Jie

“…Prompt tuning attempts to update few task-specific parameters in pre-trained models. It has achieved comparable performance to fine-tuning of the full…”
Get full text