Yangtao Wang

Dr. Yangtao Wang

School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China
orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
23 February 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
YXYanzhao Xie
Yanzhao Xie
RWRukai Wei
Rukai Wei
JSJingkuan Song
Jingkuan Song
YLYu Liu
Yu Liu
YWYangtao Wang
Yangtao Wang
KZKe Zhou
Ke Zhou
Due to the usage of global similarity, the hashing methods based on predefined hash centers have achieved more accurate retrieval results than the pairwise/triplet-based methods. Nevertheless, the fixed hash centers lack the perception of data distribution and are limited by the pre-determined Hadamard matrix, which consider neither the label semantic information nor the object scale size, resulting in sub-optimal retrieval performance and weak generalization ability. In this paper, we (1) adopt the label semantic information to generate self-adaptive hash centers and (2) propose the label-affinity coefficient ( lac ) that considers the scale size of each label/object appearing in the given image to calculate the real hash centroid for this image. Based on this, we propose Label-affinity Self-adaptive Central Similarity Hashing (LSCSH) for image retrieval. LSCSH consists of a hash code generator module and a hash center adapter module. First, we obtain the label word vector ( i.e. , the word vector representation of each class label) via the Word2Vector technique to generate and update the hash centers that adapt to the distribution of both label word vectors and generated hash codes. Second, we learn lac to indicate the dominance of different labels corresponding to objects in each given image, which considers the unequal scales of each object (corresponding to a label) to calculate a more accurate hash centroid for each image. Last but not least, we design an asynchronous learning mechanism to enable each hash code and its corresponding hash centroid to adapt to each other dynamically. We conduct extensive experiments on 5 image datasets including CIFAR-10, ImageNet, VOC2012, MS-COCO and NUS-WIDE. The experimental results demonstrate that LSCSH can achieve the state-of-the-art visual retrieval performance on both single-label and multi-label image datasets. The code of this work is released at: https://github.com/lzHZWZ/LSCSH_sourcecode.git .

21 February 2022 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
YWYangtao Wang
Yangtao Wang
YXYanzhao Xie
Yanzhao Xie
Lisheng FanLisheng Fan
Lisheng Fan
GHGuangxing Hu
Guangxing Hu

23 March 2022 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
YXYanzhao Xie
Yanzhao Xie
YWYangtao Wang
Yangtao Wang
YLYu Liu
Yu Liu
KZKe Zhou
Ke Zhou

27 January 2023 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
YXYanzhao Xie
Yanzhao Xie
YWYangtao Wang
Yangtao Wang
RWRukai Wei
Rukai Wei
YLYu Liu
Yu Liu
KZKe Zhou
Ke Zhou
Lisheng FanLisheng Fan
Lisheng Fan

31 October 2024 in Displays
Verified
Journal Article
Closed access
FZFangyuan Zhang
Fangyuan Zhang
RWRukai Wei
Rukai Wei
YXYanzhao Xie
Yanzhao Xie
YWYangtao Wang
Yangtao Wang
XTXin Tan
Xin Tan
Lisheng FanLisheng Fan
Lisheng Fan

10 March 2025
Verified
Conference Paper
Open access
XLXiaocui Li
Xiaocui Li
GLGuoliang Li
Guoliang Li
Xinyu ZhangXinyu Zhang
Xinyu Zhang
YWYangtao Wang
Yangtao Wang
QSQingyu Shi
Qingyu Shi
LWLiang Wei
Liang Wei
In recent years, incomplete multi-view clustering (IMVC) has attracted considerable attention for its ability to acheieve effective clustering results through the integration of key information amidst missing view. However, the existing IMVC methods are still faced with 3 limitations: (1) They exhibit deficiencies in considering the weight distribution within views, (2) they ignore the varying contributions of different views to the common consistent representation, and (3) they struggle to sufficiently extract and recover the vital information within incomplete views. To address these limitations, we incorporates local reasoning and correlation analysis to design an incomplete multi-view clustering method(IMVCLRCA), which introduces a new strategy of feature learning and missing view recovery, fully exploiting local similarity and structural continuity within views and performing precise local reasoning recovery on missing data. By maximizing mutual information between views through contrastive learning, we achieve the consistent representation learning of multiple views. Furthermore, based on semantic consistency, we comprehensively consider the correlation between views, utilized a weight matrix to fuse cross-view data, and constructed a view with a correlation structure, ultimately obtaining a common consistent representation. We conduct extensive experiments on 4 public datasets including Caltech101-20, BBCSport, Scene-15, and LandUse-21. Experimental results demonstrate that IMVCLRCA has higher accuracy and robustness compared to the state-of-the-art IMVC methods. The anonymous code of this project is available on GitHub at https://github.com/ggg2111/2025WSDM-IMVCLRCA.