• Publications
  • Influence
ArnetMiner: extraction and mining of academic social networks
TLDR
This paper addresses several key issues in the ArnetMiner system, which aims at extracting and mining academic social networks. Expand
  • 1,405
  • 159
  • PDF
Self-supervised Learning: Generative or Contrastive
TLDR
We take a look into new self-supervised learning methods for representation in computer vision, natural language processing, and graph learning. Expand
  • 24
  • 4
  • PDF
Consensus algorithms for biased labeling in crowdsourcing
TLDR
We empirically study the performance of four existing EM-based consensus algorithms, DS, GLAD, RY, and ZenCrowd, on these datasets. Expand
  • 21
  • 4
SVQR : A Novel Secure Visual Quick Response Code and Its Anti-counterfeiting Solution
TLDR
This paper presents an authentication solution to realize the anti-counterfeiting for message which is encoded following QR code standard using digital signature and watermarking techniques. Expand
  • 7
  • PDF
ANiTW: A Novel Intelligent Text Watermarking technique for forensic identification of spurious information on social media
TLDR
We propose a novel intelligent text watermarking technique called ANiTW which utilizes an instance-based learning algorithm to hide an invisible watermark into text-based information such that the hidden watermark can be extracted, even if a malicious user manipulates a portion of the watermarked information. Expand
  • 6
Machine Learning with Crowdsourcing: A Brief Summary of the Past Research and Future Directions
TLDR
We summarize a large number of techniques to deal with inaccuracy, randomness, and uncertainty issues when learning with crowdsourcing. Expand
  • 4
  • PDF
Building the electronic evidence analysis model based on association rule mining and FP-growth algorithm
TLDR
In China’s criminal procedure law, electronic data is a kind of independent evidence. Expand
  • 5
Knowledge modeling via contextualized representations for LSTM-based personalized exercise recommendation
TLDR
In this paper, we propose two approaches that use a contextualized representation of KCs, one with a content-based approach and another with a Long Short Term Memory (LSTM) network plus a personalization mechanism. Expand
  • 2
Recognition of Emotion According to the Physical Elements of the Video
TLDR
We used k-nearest neighbors (K-NN), support vector machine (SVM), and multilayer perceptron (MLP) classifiers in the machine learning method to accurately predict the four dimensions that express emotions, as well as summarize the relationship between the two-dimensional emotion space and physical elements. Expand
  • 2
  • PDF
Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things
TLDR
In the Internet of Things (IoT) era, billions of sensors and devices collect and process data from the environment, transmit them to cloud centers, and receive feedback via the internet for connectivity and perception. Expand
  • 3
  • PDF