Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
A Light CNN for Deep Face Representation With Noisy Labels
- Xiang Wu, R. He, Zhenan Sun, T. Tan
- Computer ScienceIEEE Transactions on Information Forensics and…
- 9 November 2015
Experimental results show that the proposed framework can utilize large-scale noisy data to learn a Light model that is efficient in computational costs and storage spaces and achieves state-of-the-art results on various face benchmarks without fine-tuning.
A Framework for Evaluating the Effect of View Angle, Clothing and Carrying Condition on Gait Recognition
- Shiqi Yu, Daoliang Tan, T. Tan
- Computer Science18th International Conference on Pattern…
- 20 August 2006
A framework consisting of a large gait database, a large set of well designed experiments and some evaluation metrics to evaluate gait recognition algorithms is proposed.
Session-based Recommendation with Graph Neural Networks
In the proposed method, session sequences are modeled as graph-structured data and GNN can capture complex transitions of items, which are difficult to be revealed by previous conventional sequential methods.
An SVD-based watermarking scheme for protecting rightful ownership
A novel watermarking algorithm based on singular value decomposition (SVD) is proposed and results show that the newwatermarking method performs well in both security and robustness.
A survey on visual surveillance of object motion and behaviors
- Weiming Hu, T. Tan, Liang Wang, S. Maybank
- Computer ScienceIEEE Transactions on Systems, Man, and…
- 1 August 2004
This paper reviews recent developments and general strategies of the processing framework of visual surveillance in dynamic scenes, and analyzes possible research directions, e.g., occlusion handling, a combination of two and three-dimensional tracking, and fusion of information from multiple sensors, and remote surveillance.
Predicting the Next Location: A Recurrent Model with Spatial and Temporal Contexts
RNN is extended and a novel method called Spatial Temporal Recurrent Neural Networks (ST-RNN) is proposed, which can model local temporal and spatial contexts in each layer with time-specific transition matrices for different time intervals and distance-specific transitions for different geographical distances.
Silhouette Analysis-Based Gait Recognition for Human Identification
- Liang Wang, T. Tan, Huazhong Ning, Weiming Hu
- Computer Science, EngineeringIEEE Trans. Pattern Anal. Mach. Intell.
- 1 December 2003
A simple but efficient gait recognition algorithm using spatial-temporal silhouette analysis is proposed that implicitly captures the structural and transitional characteristics of gait.
Deep semantic ranking based hashing for multi-label image retrieval
- F. Zhao, Yongzhen Huang, Liang Wang, T. Tan
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 25 January 2015
In this work, deep convolutional neural network is incorporated into hash functions to jointly learn feature representations and mappings from them to hash codes, which avoids the limitation of semantic representation power of hand-crafted features.
Efficient iris recognition by characterizing key local variations
- Li Ma, T. Tan, Yunhong Wang, Dexin Zhang
- Computer ScienceIEEE Transactions on Image Processing
- 1 June 2004
The basic idea is that local sharp variation points, denoting the appearing or vanishing of an important image structure, are utilized to represent the characteristics of the iris.
A Comprehensive Study on Cross-View Gait Based Human Identification with Deep CNNs
- Zifeng Wu, Yongzhen Huang, Liang Wang, Xiaogang Wang, T. Tan
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 1 February 2017
Experimental results show that this first work based on deep CNNs for gait recognition in the literature outperforms the previous state-of-the-art methods by a significant margin, and shows great potential for practical applications.