Asymptotic Behaviors of Probabilistic Counting-out Game on a Line
T. Ou, M. Shu, J. Wierman. Will appear in MAA Undergraduate Poster Session and AMS Special Session at Joint Mathematics Meeting, 2019
Develop strategies to utilize Markov and integer sum properties to prove exact formula for asymptotic expected survival time for a novel type of probabilistic counting-out game.
Referring Image Segmentation via Recurrent Refinement Networks
R. Li, K. Li, Y. Kuo, M. Shu, X. Qi, X. Shen, J. Jia. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
Utilize the feature pyramids inherently existing in convolutional neural networks to capture the semantics at different scales to improve performance of referring semantic segmentation task.
Facelet-Bank for Fast Portrait Manipulation
Y. Chen, H. Lin, M. Shu, R. Li, X. Tao, Y. Ye, X. Shen, J. Jia. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
Design a model to conduct digital face manipulation based on an end-to-end convolutional neural network that supports fast inference, edit-effect control, and quick partial-model update.
Probabilistic Counting-out Game on a Line
M. Shu, T. Ou, J. Wierman. Undergraduate Presentation Session presented at Mathematical Association of America MathFest, 2018
Introduce to a novel type of counting-out game. Derive Markov recursions to solve for exact solutions of winning probability and expected survival, prove its general formula, and discover
new type of integer sequences based on variations of this game.