Ruishan Liu

  • Citations Per Year
Learn More
There is indeed a relationship among various action categories, with which many correlated action categories can be clustered into a same group, named super-category. Knowledge sharing within super-category is an effective strategy to achieve good generalization performance. In this paper, we propose a novel human action recognition method based on(More)
been investigated. [ 33–38 ] Pulsed laser sequences [ 33–37 ] were used to measure Rabi oscillations between different spin ground states, and scanning probe techniques [ 37 ] were used to achieve nanoscale resolution. For many practical applications, however, wide fi eld imaging and a simple experimental procedure are benefi cial. To accomplish this, we(More)
Human action recognition from videos is a challenging computer vision task and it has wide applications, such as human robot/machine interaction, interactive entertainment, multimedia information retrieval, and surveillance. In this paper, we present a novel human action recognition method based on human joint position available video sequences. We use the(More)
Given two persons and their social network features, our job is to predict which one is more influential. In our project, we collect training samples from Kaggle based on human judgement. We use several different models to make predictions, such as Logistic Regression, SVM, Naive Bayes and Neural Network. We also use some auxiliary techniques like cross(More)
In this paper we present an application on real-time face tracking and replacement. We implement this application through three sections: detection, tracking and replacement. For detection, we use haar features based cascade classifiers to detect the face, eyes and nose on both target and source images. Then face tracking is implemented by two distinct(More)
  • 1