Results 1 - 10
of
674
Learning on the test data: Leveraging unseen features
- Proc. ICML
, 2003
"... This paper addresses the problem of classification in situations where the data distribution is not homogeneous: Data instances might come from different locations or times, and therefore are sampled from related but different distributions. In particular, features may appear in some parts of the da ..."
Abstract
-
Cited by 15 (3 self)
- Add to MetaCart
of the data that are rarely or never seen in others. In most situations with nonhomogeneous data, the training data is not representative of the distribution under which the classifier must operate. We propose a method, based on probabilistic graphical models, for utilizing unseen features during
A Maximum Entropy Model for Part-Of-Speech Tagging
, 1996
"... This paper presents a statistical model which trains from a corpus annotated with Part-OfSpeech tags and assigns them to previously unseen text with state-of-the-art accuracy(96.6%). The model can be classified as a Maximum Entropy model and simultaneously uses many contextual "features" t ..."
Abstract
-
Cited by 580 (1 self)
- Add to MetaCart
This paper presents a statistical model which trains from a corpus annotated with Part-OfSpeech tags and assigns them to previously unseen text with state-of-the-art accuracy(96.6%). The model can be classified as a Maximum Entropy model and simultaneously uses many contextual "features
Unconscious pop-out: attentional capture by unseen feature singletons only when top-down attention is available
"... Visual “pop-out ” occurs when a unique visual target (e.g. a feature singleton) is present among a set of homogeneous distractors. However, the role of visual awareness in this process remains unclear. Here we show that, even though subjects were not aware of a suppressed pop-out display, their subs ..."
Abstract
- Add to MetaCart
Visual “pop-out ” occurs when a unique visual target (e.g. a feature singleton) is present among a set of homogeneous distractors. However, the role of visual awareness in this process remains unclear. Here we show that, even though subjects were not aware of a suppressed pop-out display
The adaptive nature of human categorization
- Psychological Review
, 1991
"... A rational model of human categorization behavior is presented that assumes that categorization reflects the derivation of optimal estimates of the probability of unseen features of objects. A Bayesian analysis is performed of what optimal estimations would be if categories formed a disjoint partiti ..."
Abstract
-
Cited by 344 (2 self)
- Add to MetaCart
A rational model of human categorization behavior is presented that assumes that categorization reflects the derivation of optimal estimates of the probability of unseen features of objects. A Bayesian analysis is performed of what optimal estimations would be if categories formed a disjoint
unknown title
"... Neuronportant but previously unseen features of brain molecular architecture. ..."
Abstract
- Add to MetaCart
Neuronportant but previously unseen features of brain molecular architecture.
Visual Odometry
- Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR’04
, 2004
"... We present a system that estimates the motion of a stereo head or a single moving camera based on video input. The system operates in real-time with low delay and the motion estimates are used for navigational purposes. The front end of the system is a feature tracker. Point features are matched bet ..."
Abstract
-
Cited by 299 (5 self)
- Add to MetaCart
We present a system that estimates the motion of a stereo head or a single moving camera based on video input. The system operates in real-time with low delay and the motion estimates are used for navigational purposes. The front end of the system is a feature tracker. Point features are matched
Minimum redundancy feature selection from microarray gene expression data
, 2003
"... Selecting a small subset of genes out of the thousands of genes in microarray data is important for accurate classification of phenotypes. Widely used methods typically rank genes according to their differential expressions among phenotypes and pick the top-ranked genes. We observe that feature sets ..."
Abstract
-
Cited by 239 (8 self)
- Add to MetaCart
Selecting a small subset of genes out of the thousands of genes in microarray data is important for accurate classification of phenotypes. Widely used methods typically rank genes according to their differential expressions among phenotypes and pick the top-ranked genes. We observe that feature
Learning to Recognize Objects from Unseen Modalities
"... Abstract. In this paper we investigate the problem of exploiting multiple sources of information for object recognition tasks when additional modalities that are not present in the labeled training set are available for inference. This scenario is common to many robotics sensing applications and is ..."
Abstract
-
Cited by 7 (0 self)
- Add to MetaCart
and is in contrast with the assumption made by existing approaches that require at least some labeled examples for each modality. To leverage the previously unseen features, we make use of the unlabeled data to learn a mapping from the existing modalities to the new ones. This allows us to predict the missing data
Learning methods for generic object recognition with invariance to pose and lighting
- In Proceedings of CVPR’04
, 2004
"... We assess the applicability of several popular learning methods for the problem of recognizing generic visual categories with invariance to pose, lighting, and surrounding clutter. A large dataset comprising stereo image pairs of 50 uniform-colored toys under 36 angles, 9 azimuths, and 6 lighting co ..."
Abstract
-
Cited by 253 (18 self)
- Add to MetaCart
of the objects with various amounts of variability and surrounding clutter were used for training and testing. Nearest Neighbor methods, Support Vector Machines, and Convolutional Networks, operating on raw pixels or on PCA-derived features were tested. Test error rates for unseen object instances placed
Enriching the Knowledge Sources Used in a Maximum Entropy Part-of-Speech Tagger
- In EMNLP/VLC 2000
, 2000
"... This paper presents results for a maximumentropy -based part of speech tagger, which achieves superior performance principally by enriching the information sources used for tagging. In particular, we get improved results by incorporating these features: (i) more extensive treatment of capitali ..."
Abstract
-
Cited by 202 (4 self)
- Add to MetaCart
of capitalization for unknown words; (ii) features for the disambiguation of the tense forms of verbs; (iii) features for disambiguating particles from prepositions and adverbs. The best resulting accuracy for the tagger on the Penn Treebank is 96.86% overall, and 86.91% on previously unseen words.
Results 1 - 10
of
674