Sciweavers

629 search results - page 2 / 126
» Learning and Forgetting with Local Information of New Object...
Sort
View
87
Voted
ICPR
2008
IEEE
16 years 4 months ago
A new objective function for sequence labeling
We propose a new loss function for discriminative learning of Markov random fields, which is an intermediate loss function between the sequential loss and the pointwise loss. We s...
Hisashi Kashima, Yuta Tsuboi
ICCV
2007
IEEE
16 years 5 months ago
3D generic object categorization, localization and pose estimation
We propose a novel and robust model to represent and learn generic 3D object categories. We aim to solve the problem of true 3D object categorization for handling arbitrary rotati...
Silvio Savarese, Fei-Fei Li 0002
116
Voted
BMVC
2010
15 years 1 months ago
Histogram of Oriented Cameras - A New Descriptor for Visual SLAM in Dynamic Environments
Simultaneous localization and mapping (SLAM) is a basic prerequisite in autonomous mobile robotics. Most existing visual SLAM approaches either assume a static environment, or sim...
Katrin Pirker
109
Voted
ICRA
2002
IEEE
87views Robotics» more  ICRA 2002»
15 years 8 months ago
Visual Guided Grasping of Aggregates using Self-Valuing Learning
We present a self-valuing learning technique which is capable of learning how to grasp unfamiliar objects and generalize the learned abilities. The learning system consists of two...
Bernd Rössler, Jianwei Zhang, Alois Knoll
137
Voted
IEEECIT
2009
IEEE
15 years 10 months ago
Clustering of Software Systems Using New Hybrid Algorithms
—Software clustering is a method for increasing software system understanding and maintenance. Software designers, first use MDG graph to model the structure of software system. ...
Ali Safari Mamaghani, Mohammad Reza Meybodi