Object (computer science)

About: Object (computer science) is a research topic. Over the lifetime, 106024 publications have been published within this topic receiving 1360115 citations. The topic is also known as: obj & Rq.

Recognition and Structure from one 2D Model View: Observations on Prototypes, Object Classes and Symmetries

Abstract: In this note we discuss how recognition can be achieved from a single 2D model view exploiting prior knowledge of an object''s structure (e.g. symmetry). We prove that for any bilaterally symmetric 3D object one non- accidental 2D model view is sufficient for recognition. Symmetries of higher order allow the recovery of structure from one 2D view. Linear transformations can be learned exactly from a small set of examples in the case of "linear object classes" and used to produce new views of an object from a single view.

Method for creating structured documents in a publishing system

Abstract: An authoring environment for producing content for an on-line system is described. This environment includes a story editor which can save files in a Multimedia Document Format (MDF) file. A MDF file is an OLE storage wherein one storage object holds text of the content in a Multimedia Publishing Markup Language. Other parts of the MDF file include storages for holding content search terms and storages for embedded objects.

System and method for a distributed debugger for debugging distributed application programs

Abstract: A system and method for providing a distributed debugger system for a distributed target computer application are disclosed wherein the programmer/developer of the application can be at one host machine and wherein the application being developed makes use of objects and object implementations which may be located on a different host machine which is unknown to the programmer/developer. The system and method provides solutions to problems which are encountered in trying to debug a new application which is associated with the use of objects in a widely distributed, object oriented, client-server system. In a distributed object environment, requests and replies are made through an Object Request Broker (ORB) that is aware of the locations and status of objects. One architecture which is suitable for implementing such an ORB is provided by the Common Object Request Broker Architecture (CORBA) specification. The distributed debugger system disclosed herein is designed to function in a CORBA compliant distributed system.

Interpreting CNNs via Decision Trees

Abstract: This paper aims to quantitatively explain rationales of each prediction that is made by a pre-trained convolutional neural network (CNN) We propose to learn a decision tree, which clarifies the specific reason for each prediction made by the CNN at the semantic level Ie, the decision tree decomposes feature representations in high conv-layers of the CNN into elementary concepts of object parts In this way, the decision tree tells people which object parts activate which filters for the prediction and how much they contribute to the prediction score Such semantic and quantitative explanations for CNN predictions have specific values beyond the traditional pixel-level analysis of CNNs More specifically, our method mines all potential decision modes of the CNN, where each mode represents a common case of how the CNN uses object parts for prediction The decision tree organizes all potential decision modes in a coarse-to-fine manner to explain CNN predictions at different fine-grained levels Experiments have demonstrated the effectiveness of the proposed method

Systems and methods for sculpting virtual objects in a haptic virtual reality environment

Abstract: A user of a virtual object or computer model uses a haptic interface device in the real world to manipulate a virtual tool in a virtual environment to interact and modify the virtual object. The user uses the virtual tool in a sculpting mode to modify the shape of the virtual object by adding, removing, or modifying the material of the object. The user feels an interaction force from the virtual tool as it interacts with and modifies the virtual object. The designer can set geometric constraints, such as a constraint point, constraint line, or constraint surface, to limit or guide the movement of the virtual tool.