We consider the problem of grasping novel objects in cluttered environments. If a full 3-d model of the scene were available, one could use the model to estimate the stability and...
For object category recognition to scale beyond a small number of classes, it is important that algorithms be able to learn from a small amount of labeled data per additional clas...
Kevin Tang, Marshall Tappen, Rahul Sukthankar, Chr...
Given an image, we propose a hierarchical generative
model that classifies the overall scene, recognizes and segments
each object component, as well as annotates the image
with ...
Property testing deals with tasks where the goal is to distinguish between the case that an object (e.g., function or graph) has a prespecified property (e.g., the function is li...
An E-Partner is a photo-realistic conversation agent, which has a talking head that not only look photo-realistic but also can have a conversation with the user about a given topic...
Bo Zhang, Changbo Hu, Qingsheng Cai, Baining Guo, ...