Share This Author
Learning to Represent Programs with Graphs
This work proposes to use graphs to represent both the syntactic and semantic structure of code and use graph-based deep learning methods to learn to reason over program structures, and suggests that these models learn to infer meaningful names and to solve the VarMisuse task in many cases.
Probabilistic Graphical Models and Deep Belief Networks for Prognosis of Breast Cancer
- M. Khademi, N. Nedialkov
- Computer ScienceIEEE 14th International Conference on Machine…
- 1 December 2015
A probabilistic graphical model (PGM) for prognosis and diagnosis of breast cancer is proposed and extensive experiments using real-world databases show promising results in comparison to Support Vector Machines and k-Nearest Neighbors classifiers, for classifying tumors and predicting events like recurrence and metastasis.
Extended Two-Dimensional PCA for efficient face representation and recognition
- M. Safayani, M. Shalmani, M. Khademi
- Computer Science4th International Conference on Intelligent…
- 10 October 2008
A novel method called Extended Two-Dimensional PCA is proposed which is an extension to the original 2DPCA which considers a radius of r diagonals around it and expands the averaging so as to include the covariance information within those diagonsals.
A Markov Game model for valuing actions, locations, and team performance in ice hockey
- O. Schulte, M. Khademi, S. Gholami, Zeyu Zhao, M. J. Roshtkhari, Philippe Desaulniers
- EconomicsData Mining and Knowledge Discovery
- 1 November 2017
Model validation shows that the total team action and state value both provide a strong indicator predictor of team success, as measured by the team’s average goal ratio.
Multimodal Neural Graph Memory Networks for Visual Question Answering
- M. Khademi
- Computer ScienceACL
- 1 July 2020
A new neural network architecture, Multimodal Neural Graph Memory Networks (MN-GMN), for visual question answering that rivals the state-of-the-art models on Visual7W, VQA-v2.0, and CLEVR datasets.
Recognizing Combinations of Facial Action Units with Different Intensity Using a Mixture of Hidden Markov Models and Neural Network
An accurate real-time sequence-based system for representation and recognition of facial AUs is presented and it is robust to illumination changes and it can represent the temporal information involved in formation of the facial expressions.
Image Caption Generation with Hierarchical Contextual Visual Spatial Attention
Experimental results on MS-COCO dataset show that the architecture outperforms the state-of-the-art and the dynamic spatial attention mechanism considers the spatial context of the image regions.
Relative facial action unit detection
- M. Khademi, Louis-Philippe Morency
- Computer ScienceIEEE Winter Conference on Applications of…
- 24 March 2014
This paper presents a subject-independent facial action unit (AU) detection method by introducing the concept of relative AU detection, for scenarios where the neutral face is not provided. We…
Deep Generative Probabilistic Graph Neural Networks for Scene Graph Generation
The proposed algorithm, called Deep Generative Probabilistic Graph Neural Networks (DG-PGNN), to generate a scene graph for an image significantly outperforms the state-of-the-art results on the Visual Genome dataset for scene graph generation.
New S-norm and T-norm Operators for Active Learning Method
This paper introduces two new operators based on morphology which satisfy the following conditions: first, they serve as fuzzy S-norm and T-norm, and second, they satisfy Demorgans law, so they complement each other perfectly.