• Publications
  • Influence
Time weight collaborative filtering
This paper presents a novel algorithm to compute the time weights for different items in a manner that will assign a decreasing weight to old data, and uses clustering to discriminate between different kinds of items.
RFID Data Management: Challenges and Opportunities
A brief overview of RFID technology is provided and a few of the data management challenges that are suitable topics for exploratory research are highlighted.
Concept-based document readability in domain specific information retrieval
An effective and computationally tractable concept-based model of text readability that takes into account domain specific knowledge, i.e., how the domain-specific concepts contained in the document affect the document's readability is proposed.
Online human gesture recognition from motion data streams
A new effective and efficient feature extraction method that uses a dynamic matching approach to construct a feature vector for each frame and improves sensitivity to the features of different gestures and decreases sensitivity toThe features of gestures within the same class.
An Effective Approach for Cyberbullying Detection
An effective approach to detect cyberbullying messages from social media through a weighting scheme of feature selection is proposed and a graph model is presented to extract the cyberBullying network, which is used to identify the most active cyberbullies predators and victims through ranking algorithms.
Motion vector encryption in multimedia streaming
  • Zheng Liu, Xue Li
  • Computer Science
    10th International Multimedia Modelling…
  • 5 January 2004
This paper targets this security problem and illustrates attacks at two different levels that can restore useful video information using motion vectors only, and describes a new motion vector encryption algorithm called MVEA.
Call Attention to Rumors: Deep Attention Based Recurrent Neural Networks for Early Rumor Detection
A deep attention model based on recurrent neural networks to selectively learn temporal representations of sequential posts for rumor identification that outperforms state-of-the-art baselines by detecting rumors more quickly and accurately than competitors.
Enabling Next-Generation RFID Applications: Solutions and Challenges
Radio-frequency identification technology provides promising benefits such as inventory visibility and business process automation, but companies must address major challenges such as data processing, integration architecture design, security, and privacy.
PME: Projected Metric Embedding on Heterogeneous Networks for Link Prediction
A novel heterogenous information network embedding model PME based on the metric learning to capture both first-order and second-order proximities in a unified way is proposed and the experimental results show superiority of the proposed PME model in terms of prediction accuracy and scalability.
Emerging event detection in social networks with location sensitivity
The proposed approach for the early detection of emerging hotspot events in social networks with location sensitivity considers the message-mentioned locations for identifying the locations of events and identifies strong correlations between user locations and event locations in detecting the emerging events.