Zhiwei Lin

Zhiwei Lin

Auto-generated profile, based on publicly available information

Zhiwei Lin

School of Mathematics and Physics, Queen’s University Belfast, Belfast BT7 1NN, UK

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
1 January 2020 in Information Sciences
Verified
Journal Article
Closed access
LMLianbo Ma
Lianbo Ma
RWRui Wang
Rui Wang
SCShengminjie Chen
Shengminjie Chen
SCShi Cheng
Shi Cheng
XWXingwei Wang
Xingwei Wang
MHMin Huang
Min Huang

1 July 2020 in Information Sciences
Verified
Journal Article
Closed access
NSNiloofer Shanavas
Niloofer Shanavas
HWHui Wang
Hui Wang
ZLZhiwei Lin
Zhiwei Lin
GHGlenn Hawe
Glenn Hawe

28 January 2020 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
TWTian Wang
Tian Wang
YCYang Chen
Yang Chen
ZLZhiwei Lin
Zhiwei Lin
AZAichun Zhu
Aichun Zhu
YLYong Li
Yong Li
HWHui Wang
Hui Wang
Generating action proposals in untrimmed videos is a challenging task, since video sequences usually contain lots of irrelevant contents and the duration of an action instance is arbitrary. The quality of action proposals is key to action detection performance. The previous methods mainly rely on sliding windows or anchor boxes to cover all ground-truth actions, but this is infeasible and computationally inefficient. To this end, this article proposes a RecapNet--a novel framework for generating action proposal, by mimicking the human cognitive process of understanding video content. Specifically, this RecapNet includes a residual causal convolution module to build a short memory of the past events, based on which the joint probability actionness density ranking mechanism is designed to retrieve the action proposals. The RecapNet can handle videos with arbitrary length and more important, a video sequence will need to be processed only in one single pass in order to generate all action proposals. The experiments show that the proposed RecapNet outperforms the state of the art under all metrics on the benchmark THUMOS14 and ActivityNet-1.3 datasets. The code is available publicly at https://github.com/tianwangbuaa/RecapNet.

1 November 2007
Verified
Conference Paper
Closed access
HWHui Wang
Hui Wang
ZLZhiwei Lin
Zhiwei Lin
A similarity measure is key to any distance-based data analysis task, e.g., clustering, classification and case-based reasoning. The choice of similarity measure depends on the type of data used in a data analysis task. For sequence data the well known similarity measures include sequence edit distance and longest common subsequence. A new measure of sequence similarity, all common subsequence (ACS), is recently proposed. ACS uses the number of common subsequences between a pair of sequences as a measure of similarity. The more common subsequences there are between them, the more similar they are to each other. A dynamic programming algorithm is presented in H. Wang (2007) to compute ACS, which we call calACS-DP. In this paper we analyze the complexities of this algorithm in time and space, which are both quadratic in the length of sequence. Based on this analysis we present a novel, more efficient algorithm to compute ACS, which we call calACS. This algorithm is derived from an algorithm presented in H. Wang and C. Liu, (2006). The space complexity of this algorithm is O(min{|A|, |B|} + 1) and the time complexity of this algorithm is O(|A| times |B|) for any two sequences A and B. We further illustrate this algorithm with an example.

1 May 2020 in Information Sciences
Verified
Journal Article
Closed access
ZXZhengui Xue
Zhengui Xue
ZLZhiwei Lin
Zhiwei Lin
HWHui Wang
Hui Wang
SMSally McClean
Sally McClean

1 April 2020 in IEEE Access
Verified
Journal Article
Open access
YYYi Yang
Yi Yang
ZLZhiwei Lin
Zhiwei Lin
BLBingfeng Li
Bingfeng Li
XLXinwei Li
Xinwei Li
LCLizhi Cui
Lizhi Cui
KWKeping Wang
Keping Wang
Applying model-based learning for the optimal decision of the multi-agent system is not trivial due to the expensive price or even the impossibility of obtaining the ground truth for training the model of the complex environment. Such as learning the optimal action of hydraulic supports in the top-coal caving, the optimal action could not accessible as the ground truth of the corresponding state in the intricate processes. Regarding the latent ground truth as the hidden variable is an effective method in the hidden Markov model. This paper extends the hidden variable of ground truth to the multi-agent system and proposes the hidden Markov random field (HMRF) model with reinforcement learning for optimizing the action decision of the multi-agent. In the HMRF model, the input states and the output actions of the multi-agent are considered as an observable random field and a latent Markov random field, respectively. Based on the HMRF model, the optimal decision is inferred by the maximum posterior probability with the prior probability obtained by Q-learning. Meanwhile, the parameters of the HMRF model are estimated by the expectation maximum algorithm. In the experiment, the top-coal caving demonstrates the effectiveness of the proposed method that the recall of top-coal is improved prominently with a very small price of increasing the rock-rate. Furthermore, the proposed method is employed to deal with the predator-preys problem in the gym. The experiment result shows that the communication between agents by the HMRF increases the reward of the preys.