• Publications
  • Influence
Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL for Multiband Image Segmentation
A novel statistical and variational approach to image segmentation based on a new algorithm, named region competition, derived by minimizing a generalized Bayes/minimum description length (MDL) criterion using the variational principle is presented. Expand
Cross-View Action Modeling, Learning, and Recognition
A novel multiview spatio-temporal and-or graph (MST-AOG) representation for cross-view action recognition, which takes advantage of the 3D human skeleton data obtained from Kinect cameras to avoid annotating enormous multi-view video frames, but the recognition does not need 3D information and is based on 2D video input. Expand
Prior Learning and Gibbs Reaction-Diffusion
It is found that the partial differential equations given by gradient descent on U(I; /spl Lambda/, S) are essentially reaction-diffusion equations, where the usualEnergy terms produce anisotropic diffusion, while the inverted energy terms produce reaction associated with pattern formation, enhancing preferred image features. Expand
Image Segmentation by Data-Driven Markov Chain Monte Carlo
The DDMCMC paradigm provides a unifying framework in which the role of many existing segmentation algorithms are revealed as either realizing Markov chain dynamics or computing importance proposal probabilities and generalizes these segmentation methods in a principled way. Expand
Minimax Entropy Principle and Its Application to Texture Modeling
The minimax entropy principle is applied to texture modeling, where a novel Markov random field model, called FRAME, is derived, and encouraging results are obtained in experiments on a variety of texture images. Expand
Learning Human-Object Interactions by Graph Parsing Neural Networks
This paper addresses the task of detecting and recognizing human-object interactions (HOI) in images and videos. We introduce the Graph Parsing Neural Network (GPNN), a framework that incorporatesExpand
Learning Active Basis Model for Object Detection and Recognition
An active basis model, a shared sketch algorithm, and a computational architecture of sum-max maps for representing, learning, and recognizing deformable templates are proposed. Expand
Interpretable Convolutional Neural Networks
A method to modify a traditional convolutional neural network into an interpretable CNN, in order to clarify knowledge representations in high conv-layers of the CNN, which can help people understand the logic inside a CNN. Expand
RAVEN: A Dataset for Relational and Analogical Visual REasoNing
This work proposes a new dataset, built in the context of Raven's Progressive Matrices (RPM) and aimed at lifting machine intelligence by associating vision with structural, relational, and analogical reasoning in a hierarchical representation and establishes a semantic link between vision and reasoning by providing structure representation. Expand
Filters, Random Fields and Maximum Entropy (FRAME): Towards a Unified Theory for Texture Modeling
The resulting model, called FRAME (Filters, Random fields And Maximum Entropy), is a Markov random field (MRF) model, but with a much enriched vocabulary and hence much stronger descriptive ability than the previous MRF models used for texture modeling. Expand