-
Article
Open AccessA framework for training larger networks for deep Reinforcement learning
The success of deep learning in computer vision and natural language processing communities can be attributed to the training of very deep neural networks with millions or billions of parameters, which can the...
-
Chapter and Conference Paper
EvIs-Kitchen: Egocentric Human Activities Recognition with Video and Inertial Sensor Data
Egocentric Human Activity Recognition (ego-HAR) has received attention in fields where human intentions in a video must be estimated. The performance of existing methods, however, are limited due to insufficie...
-
Article
An integration of bottom-up and top-down salient cues on RGB-D data: saliency from objectness versus non-objectness
Bottom-up and top-down visual cues are two types of information that helps the visual saliency models. These salient cues can be from spatial distributions of the features (space-based saliency) or contextual/...
-
Article
Part-Based Geometric Categorization and Object Reconstruction in Cluttered Table-Top Scenes
This paper presents an approach for 3D geometry-based object categorization in cluttered table-top scenes. In our method, objects are decomposed into different geometric parts whose spatial arrangement is repr...
-
Article
Partial matching of real textured 3D objects using color cubic higher-order local auto-correlation features
In recent years, the need for retrieving real 3D objects has grown significantly. However, various important considerations must be taken into account to solve the real 3D object retrieval problem. Three-dimen...
