Article
Computer Science, Artificial Intelligence
Jie Zhao, Yong Deng
Summary: This article presents a novel model of evidence theory based on complex networks, addresses some typical issues of evidence theory, and introduces a new combination rule.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Abhimanyu Sahu, Ananda S. Chowdhury
Summary: This paper addresses the problem of egocentric video co-summarization. It proposes a method based on random walk on a constrained graph in transfer learned feature space to obtain accurate summaries for each shot. The method shows advantages over state-of-the-art methods in both short and long duration videos.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Information Systems
Vivek Kumar Singh, Nitin Kumar
Summary: This paper proposes a Convex Hull Based Random Walks (CoBRa) approach for salient object detection. In this approach, an image is segmented into superpixels and a Convex Hull is constructed to partition the image into foreground and background regions. The centroid of the foreground region is calculated and used to compute initial saliency. Two thresholds are applied to produce binary segmented images, and foreground and background seeds are collected and refined. A random walk is then constructed to generate a pixel-wise saliency map. Experimental results on six datasets demonstrate the superiority of the proposed approach.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Mathematics, Interdisciplinary Applications
Andrei A. Klishin, Dani S. Bassett
Summary: Random walks are commonly used as a model for exploring and discovering complex networks. Exposure theory, a statistical mechanics framework, is introduced to predict the learning of nodes and edges in various types of networks and demonstrates a universal trajectory for edge learning.
JOURNAL OF COMPLEX NETWORKS
(2022)
Article
Computer Science, Information Systems
Jingyanning Yang, Jinguo You, Xiaorong Wan
Summary: Graph representation learning with the GSE model improves efficiency on big data graphs and effectively alleviates the local optimal problem caused by random walks. Experimental results demonstrate that GSE outperforms main existing clustering baselines.
Article
Computer Science, Artificial Intelligence
Arzu Gorgulu Kakisim
Summary: Attributed network embedding method ANEA generates low-dimensional representations of network objects by incorporating attribute data into the embedding process. It captures high-order semantic relations between attributes by performing random walks on two different graph structures. ANEA learns embeddings through a joint space of the network structure and attributes, effectively modeling the proximity among nodes.
APPLIED INTELLIGENCE
(2022)
Article
Chemistry, Multidisciplinary
Fei Yan, Cheng Chen, Peng Xiao, Siyu Qi, Zhiliang Wang, Ruoxiu Xiao
Summary: This study summarizes the achievements in the field of saliency prediction, including the early neurological and psychological mechanisms, the guiding role of classic models, and the development process and data comparison of classic and deep saliency prediction models. It also discusses the relationship between the model and human vision, the factors causing semantic gaps, the influences of attention in cognitive research, the limitations of the saliency model, and the emerging applications.
APPLIED SCIENCES-BASEL
(2022)
Article
Geochemistry & Geophysics
Bohan Chen, Yifei Lou, Andrea L. Bertozzi, Jocelyn Chanussot
Summary: In this article, two graph-based semisupervised unmixing methods are proposed, which significantly improve blind unmixing performance by using a small number of training pixels and graph-based learning methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Computer Science, Information Systems
Sichao Fu, Weifeng Liu, Weili Guan, Yicong Zhou, Dapeng Tao, Changsheng Xu
Summary: This study introduces Dynamic Graph Learning Convolutional Networks (DGLCN), which extracts richer sample features to improve classification performance by continuously optimizing high-order structural relationships between data points.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Luying Zhong, Zhaoliang Chen, Zhihao Wu, Shide Du, Zheyi Chen, Shiping Wang
Summary: This article proposes a learnable GCN-based framework to obtain optimal graph structures and designs dual-GCN-based meta-channels to explore local and global relations. The introduction of SGIB maximizes the mutual information between the same and different meta-channels, improving node classification performance.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Theory & Methods
Guanghan Duan, Hongwu Lv, Huiqiang Wang, Guangsheng Feng
Summary: Deep learning greatly enhances binary anomaly detection capabilities, but the performance in intrusion class differentiation is still insufficient. Two challenges, emphasizing statistical attack characteristics and the need for high-quality labeled data samples, have not been fully explored. To address these issues, a dynamic line graph neural network (DLGNN)-based intrusion detection method with semisupervised learning is proposed. Experimental results on 6 novel datasets demonstrate high accuracy in abnormality detection and state-of-the-art multiclass performance.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2023)
Article
Multidisciplinary Sciences
Pauline Formaglio, Marina E. Wosniack, Raphael M. Tromer, Jaderson G. Polli, Yuri B. Matos, Hang Zhong, Ernesto P. Raposo, Marcos G. E. da Luz, Rogerio Amino
Summary: Plasmodium sporozoites actively migrate in the dermis and enter blood vessels to induce infection. Through intravital imaging, researchers found that sporozoites adopt a strategy of alternating global superdiffusive skin exploration and local subdiffusive blood vessel exploitation, enabling them to find intravasation hotspots associated with pericytes, enter the bloodstream and initiate malaria infection.
NATURE COMMUNICATIONS
(2023)
Article
Automation & Control Systems
Chaoying Yang, Jie Liu, Kaibo Zhou, Xingxing Jiang
Summary: Node-level graph data-driven diagnosis methods outperform graph-level methods by effectively learning information from unlabeled nodes. However, the features of these nodes, indirectly involved in graph feature learning, are not fully utilized. To address this, a semisupervised machine fault diagnosis method is proposed, which combines unsupervised graph contrastive learning (GCL). A new GCL framework is fused into the graph transformer network (GTN) to generate positive and negative graphs based on Pearson correlation coefficient. The GTN training includes a supervised cross-entropy loss and a new unsupervised GCL loss, guiding the contrastive learning of positive and negative graphs. This method achieves competitive performance according to experimental results on public and real datasets.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Information Systems
Fei Yan, Zhiliang Wang, Siyu Qi, Ruoxiu Xiao
Summary: This study proposes a multilevel saliency prediction network that uses a combination of spatial and channel information to find possible high-level features, further improving the performance of a saliency model.
Article
Computer Science, Information Systems
Bo Jiang, Yuan Zhang, Bin Luo, Xiaochun Cao, Jin Tang
Summary: The STGL model proposed in this paper aims to exploit both spatial and temporal structures of patches simultaneously in a unified graph representation and semi-supervised learning model. It naturally exploits the learned representation of the object in the previous frame, leading to more accurate and robust representation of the object in the current frame.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Computer Science, Artificial Intelligence
Pojala Chiranjeevi, Viswanath Gopalakrishnan, Pratibha Moogi
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2015)
Article
Engineering, Electrical & Electronic
Viswanath Gopalakrishnan, Deepu Rajan, Yiqun Hu
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2012)
Article
Computer Science, Information Systems
Viswanath Gopalakrishnan, Yiqun Hu, Deepu Rajan
IEEE TRANSACTIONS ON MULTIMEDIA
(2009)
Proceedings Paper
Acoustics
Dhruv Kohli, Biplab Ch Das, Viswanath Gopalakrishnan, Kiran Nanjunda Iyer
2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
(2017)
Proceedings Paper
Acoustics
Raushan Kumar, Rakesh Kumar, Viswanath Gopalakrishnan, Kiran Nanjunda Iyer
2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
(2017)
Proceedings Paper
Engineering, Electrical & Electronic
Smit Marvaniya, Mogilipaka Damoder, Viswanath Gopalakrishnan, Kiran Nanjunda Iyer, Kapil Soni
2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
(2016)
Proceedings Paper
Engineering, Electrical & Electronic
Biplab Chandra Das, Viswanath Gopalakrishnan, Kiran Nanjunda Iyer, Anshuman Gaurav
2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
(2016)
Proceedings Paper
Engineering, Electrical & Electronic
Viswanath Gopalakrishnan, Anirudh Purwar, Satish Lokkoju, Raushan Kumar, Kiran Nanjunda Iyer
2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
(2015)
Proceedings Paper
Engineering, Electrical & Electronic
Sudha Velusamy, Vishwanath Gopalakrishnan, Balasubramanian Anand, Pratibha Moogi, BasantKumar Pandey
2013 IEEE CONSUMER COMMUNICATIONS AND NETWORKING CONFERENCE (CCNC)
(2013)
Proceedings Paper
Engineering, Electrical & Electronic
Balasubramanian Anand, Bilva Bhalchandra Navathe, Sudha Velusamy, Hariprasad Kannan, Anshul Sharma, Viswanath Gopalakrishnan
2012 IEEE CONSUMER COMMUNICATIONS AND NETWORKING CONFERENCE (CCNC)
(2012)
Proceedings Paper
Computer Science, Artificial Intelligence
Sudha Velusamy, Viswanath Gopalakrishnan, Bilva Navathe, Hariprasad Kannan, Balasubramanian Anand, Anshul Sharma
AFFECTIVE COMPUTING AND INTELLIGENT INTERACTION, PT I
(2011)
Proceedings Paper
Computer Science, Artificial Intelligence
Viswanath Gopalakrishnan, Yiqun Hu, Deep Rajan
COMPUTER VISION - ACCV 2010, PT II
(2011)