Yong Chen

Yong Chen

Auto-generated profile, based on publicly available information

Yong Chen

Beijing University of Posts and Telecommunications, Beijing, China

Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

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

Representative Publications

View All Publications
15 October 2018 in Applied Sciences
Verified
Journal Article
Open access
PDF file
LFLibo Feng
Libo Feng
HZHui Zhang
Hui Zhang
YCYong Chen
Yong Chen
LLLiqi Lou
Liqi Lou
The permissioned blockchain system has recently become popular in a wide range of scenarios, such as artificial intelligence, financial applications and the Internet of things, due to its dominance in terms of distribution, decentralization, reliability and security. However, the Practical Byzantine Fault-Tolerant (PBFT) algorithm, which is currently adopted in such systems, sparks communication bottlenecks when the number of consensus nodes increases sharply, which seriously hinders large-scale applications. In this paper, we propose a scalable dynamic multi-agent hierarchical PBFT algorithm (SDMA-PBFT), which reduces the communication costs from O(n2) to O( n × k × log k n ). Specifically, SDMA-PBFT forms multiple autonomous systems at each agent node in which message multicasting can be efficiently carried out and the internal voting results can be effectively collected. Therefore, the design of these agent nodes facilitates the in-and-out operations of consensus nodes in the blockchain system. Simulation results show that our proposed algorithm substantially outperforms the PBFT algorithm in terms of latency. Hence, it can be applied to the permissioned blockchain system effectively and efficiently.

9 January 2020 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
YCYong Chen
Yong Chen
ZTZhibao Tian
Zhibao Tian
HZHui Zhang
Hui Zhang
JWJun Wang
Jun Wang
DZDell Zhang
Dell Zhang
Learning to hash is a fundamental technique widely used in large-scale image retrieval. Most existing methods for learning to hash address the involved discrete optimization problem by the continuous relaxation of the binary constraint, which usually lead to large quantization errors and consequently suboptimal binary codes. A few discrete hashing methods have emerged recently. However, they either completely ignore some useful constraints (specifically the balance and decorrelation of hash bits) or just turn those constraints into regularizers that would make the optimization easier but less accurate. In this paper, we propose a novel supervised hashing method named, Strongly Constrained Discrete Hashing (SCDH), which overcomes such limitations. It can learn the binary codes for all examples in the training set, and meanwhile obtain a hash function for unseen samples with the above mentioned constraints preserved. Although the model of SCDH is fairly sophisticated, we are able to find closed-form solutions to all of its optimization subproblems and thus design an efficient algorithm that converges quickly. In addition, we extend SCDH to a kernelized version SCDHK. Our experiments on three large benchmark datasets have demonstrated that not only can SCDH and SCDHK achieve substantially higher MAP scores than state-of-the-art baselines, but they run much faster than those that are also supervised as well.

18 May 2020 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
YCYong Chen
Yong Chen
HZHui Zhang
Hui Zhang
ZTZhibao Tian
Zhibao Tian
JWJun Wang
Jun Wang
DZDell Zhang
Dell Zhang
XLXuelong Li
Xuelong Li
Due to the exponential growth of multimedia data, multi-modal hashing as a promising technique to make cross-view retrieval scalable is attracting more and more attention. However, most of the existing multi-modal hashing methods either divide the learning process unnaturally into two separate stages or treat the discrete optimization problem simplistically as a continuous one, which leads to suboptimal results. Recently, a few discrete multi-modal hashing methods that try to address such issues have emerged, but they still ignore several important discrete constraints (such as the balance and decorrelation of hash bits). In this paper, we overcome those limitations by proposing a novel method named “Enhanced Discrete Multi-modal Hashing (EDMH)” which learns binary codes and hashing functions simultaneously from the pairwise similarity matrix of data, under the aforementioned discrete constraints. Although the model of EDMH looks a lot more complex than the other models for multi-modal hashing, we are actually able to develop a fast iterative learning algorithm for it, since the subproblems of its optimization all have closed-form solutions after introducing a couple of auxiliary variables. Our experimental results on three real-world datasets have revealed the usefulness of those previously ignored discrete constraints and demonstrated that EDMH not only performs much better than state-of-the-art competitors according to several retrieval metrics but also runs much faster than most of them.

12 April 2024
Verified
Conference Paper
Open access
KTKailong Tan
Kailong Tan
YZYuxiang Zhou
Yuxiang Zhou
QXQianchen Xia
Qianchen Xia
RLRui Liu
Rui Liu
YCYong Chen
Yong Chen
Keyframe extraction aims to sum up a video’s semantics with the minimum number of its frames. This paper puts forward a Large Model based Sequential Keyframe Extraction for video summarization, dubbed LMSKE, which contains three stages as below. First, we use the large model “TransNetV21” to cut the video into consecutive shots, and employ the large model “CLIP2” to generate each frame’s visual feature within each shot; Second, we develop an adaptive clustering algorithm to yield candidate keyframes for each shot, with each candidate keyframe locating nearest to a cluster center; Third, we further reduce the above candidate keyframes via redundancy elimination within each shot, and finally concatenate them in accordance with the sequence of shots as the final sequential keyframes. To evaluate LMSKE, we curate a benchmark dataset and conduct rich experiments, whose results exhibit that LMSKE performs much better than quite a few SOTA competitors with average F1 of 0.5311, average fidelity of 0.8141, and average compression ratio of 0.9922.

29 October 2003 in Analytical Chemistry
Verified
Journal Article
Closed access
YCYong Chen
Yong Chen
ZGZhao Gao
Zhao Gao
FLFei Li
Fei Li
LGLiaohai Ge
Liaohai Ge
MZMeiqin Zhang
Meiqin Zhang
YSYuanhua Shao
Yuanhua Shao

12 March 2019 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
YCYong Chen
Yong Chen
JWJunjie Wu
Junjie Wu
JLJianying Lin
Jianying Lin
RLRui Liu
Rui Liu
HZHui Zhang
Hui Zhang
ZYZhiwen Ye
Zhiwen Ye
Lifelong topic model (LTM), an emerging paradigm for never-ending topic learning, aims to yield higher-quality topics as time passes through knowledge accumulated from the past yet learned for the future. In this paper, we propose a novel lifelong topic model based on non-negative matrix factorization (NMF), called Affinity Regularized NMF for LTM (NMF-LTM), which to our best knowledge is distinctive from the popular LDA-based LTMs. NMF-LTM achieves lifelong learning by introducing word-word graph Laplacian as semantic affinity regularization. Other priors such as sparsity, diversity, and between-class affinity are incorporated as well for better performance, and a theoretical guarantee is provided for the algorithmic convergence to a local minimum. Extensive experiments on various public corpora demonstrate the effectiveness of NMF-LTM, particularly its human-like behaviors in two carefully designed learning tasks and the ability in topic modeling of big data. A further exploration of semantic relatedness in knowledge graphs and a case study on a large-scale real-world corpus exhibit the strength of NMF-LTM in discovering high-quality topics in an efficient and robust way.