Communications of the ACM
What size net gives valid generalization?
Neural Computation
Artificial Intelligence
The Combinatorics of Heuristic Search Termination for Object Recognition in Cluttered Environments
IEEE Transactions on Pattern Analysis and Machine Intelligence
On the relative complexity of active vs. passive visual search
International Journal of Computer Vision
Efficient noise-tolerant learning from statistical queries
STOC '93 Proceedings of the twenty-fifth annual ACM symposium on Theory of computing
Control of selective perception using Bayes nets and decision theory
International Journal of Computer Vision - Special issue on active vision II
Using intermediate objects to improve the efficiency of visual search
International Journal of Computer Vision - Special issue on active vision II
An introduction to computational learning theory
An introduction to computational learning theory
Modeling visual attention via selective tuning
Artificial Intelligence - Special volume on computer vision
Fat-shattering and the learnability of real-valued functions
Journal of Computer and System Sciences
Computational geometry: algorithms and applications
Computational geometry: algorithms and applications
Active object recognition integrating attention and viewpoint control
Computer Vision and Image Understanding
An Integrated Model for Evaluating the Amount of Data Required for Reliable Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Localization vs. Identification of Semi-Algebraic Sets
Machine Learning
Sensor planning for 3D object search
Computer Vision and Image Understanding
A Computational Model of View Degeneracy
IEEE Transactions on Pattern Analysis and Machine Intelligence
Predicting Performance of Object Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Active Object Recognition: Looking for Differences
International Journal of Computer Vision - Special issue: Research at McGill University
Spiking Neuron Models: An Introduction
Spiking Neuron Models: An Introduction
PAC-Bayesian Stochastic Model Selection
Machine Learning
Occlusions as a Guide for Planning the Next View
IEEE Transactions on Pattern Analysis and Machine Intelligence
Machine Learning
Transinformation for Active Object Recognition
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Rademacher and gaussian complexities: risk bounds and structural results
The Journal of Machine Learning Research
Vision: A Computational Investigation into the Human Representation and Processing of Visual Information
Efficient Discriminant Viewpoint Selection for Active Bayesian Recognition
International Journal of Computer Vision
Curious George: An attentive semantic robot
Robotics and Autonomous Systems
CRV '08 Proceedings of the 2008 Canadian Conference on Computer and Robot Vision
The ACRONYM model-based vision system
IJCAI'79 Proceedings of the 6th international joint conference on Artificial intelligence - Volume 1
Learning disjunction of conjunctions
IJCAI'85 Proceedings of the 9th international joint conference on Artificial intelligence - Volume 1
Computer Vision and Image Understanding - Special issue: Attention and performance in computer vision
A Computational Perspective on Visual Attention
A Computational Perspective on Visual Attention
IEEE Transactions on Pattern Analysis and Machine Intelligence
Active 3D Object Localization Using a Humanoid Robot
IEEE Transactions on Robotics
Isolated 3D object recognition through next view planning
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Towards active event recognition
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Hi-index | 0.00 |
We present some theoretical results related to the problem of actively searching a 3D scene to determine the positions of one or more pre-specified objects. We investigate the effects that input noise, occlusion, and the VC-dimensions of the related representation classes have in terms of localizing all objects present in the search region, under finite computational resources and a search cost constraint. We present a number of bounds relating the noise-rate of low level feature detection to the VC-dimension of an object representable by an architecture satisfying the given computational constraints. We prove that under certain conditions, the corresponding classes of object localization and recognition problems are efficiently learnable in the presence of noise and under a purposive learning strategy, as there exists a polynomial upper bound on the minimum number of examples necessary to correctly localize the targets under the given models of uncertainty. We also use these arguments to show that passive approaches to the same problem do not necessarily guarantee that the problem is efficiently learnable. Under this formulation, we prove the existence of a number of emergent relations between the object detection noise-rate, the scene representation length, the object class complexity, and the representation class complexity, which demonstrate that selective attention is not only necessary due to computational complexity constraints, but it is also necessary as a noise-suppression mechanism and as a mechanism for efficient object class learning. These results concretely demonstrate the advantages of active, purposive and attentive approaches for solving complex vision problems.