Tools
Sorted by:
Try your query at:
 |
 |
 |
 |
 |
 |
Results 1 - 10
of
19
A Mechanism for Filtering Distractors for Graphical Passwords
"... Abstract. Graphical passwords hold some promise in a world of increasing numbers of passwords, which computer users are straining to remember. However, since these kinds of mechanisms are a fairly new innovation many design and implementation problems exist which could well prevent these mechanisms ..."
Abstract
- Add to MetaCart
from realising their full potential. This paper addresses the problem of choosing distractors for graphical passwords. It is important that the distractors should not be too similar to the target image, since that could cause confusion and seriously reduce the potential for enhanced memorability
Unsupervised Detection of Downward-Entailing Operators By Maximizing Classification Certainty
"... We propose an unsupervised, iterative method for detecting downward-entailing operators (DEOs), which are important for deducing entailment relations between sentences. Like the distillation algorithm of Danescu-Niculescu-Mizil et al. (2009), the initialization of our method depends on the correlati ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
We propose an unsupervised, iterative method for detecting downward-entailing operators (DEOs), which are important for deducing entailment relations between sentences. Like the distillation algorithm of Danescu-Niculescu-Mizil et al. (2009), the initialization of our method depends
DaMN – Discriminative and Mutually Nearest: Exploiting Pairwise Category Proximity for Video Action Recognition
"... Abstract. We propose a method for learning discriminative category-level features and demonstrate state-of-the-art results on large-scale ac-tion recognition in video. The key observation is that one-vs-rest clas-sifiers, which are ubiquitously employed for this task, face challenges in separating v ..."
Abstract
- Add to MetaCart
-level representation also outperform existing methods in knowledge transfer experiments, both cross-dataset from UCF101 to HMDB51 and to new categories with limited training data (one-shot and few-shot learning). Finally, we study the generality of the proposed approach by applying DaMN to other classification tasks
Computation Of Shot-Noise Probability Distributions And Densities
- SIAM J. Comput
, 1996
"... . The computation of the cumulative distribution (cdf), the complementary cdf (ccdf), and the density of certain shotnoise random variables is discussed. After subtracting off a few terms that can be computed in closed form, what remains can be approximated by a general method for approximating samp ..."
Abstract
-
Cited by 20 (0 self)
- Add to MetaCart
at these locations. For shot-noise densities, these locations are easily identified. Key words. filtered point process, Poisson process AMS subject classification. 62E17 1. Introduction. The computation of the cumulative distribution (cdf) F (y), the complementary cdf (ccdf) F c (y) := 1 \Gamma F (y
Discriminately Decreasing Discriminability with Learned Image Filters
"... In machine learning and computer vision, input signals are often filtered to increase data discriminability. For example, preprocessing face images with Gabor band-pass filters is known to improve performance in expression recognition tasks [1]. Sometimes, however, one may wish to purposely decrease ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
decrease discriminability of one classification task (a “distractor ” task), while simultaneously preserving information relevant to another task (the target task): For example, due to privacy concerns, it may be important to mask the identity of persons contained in face images before submitting them to a
1 Supplementary Discussion 1.1 Overview
"... (1.2), for both target and distractor stimuli. We then present feature importance maps illustrating which features played the largest role in detecting these categories (1.2.2). After that, we present the results of our quartile analysis in greater detail (1.3): We report pair-wise comparison statis ..."
Abstract
- Add to MetaCart
(1.2), for both target and distractor stimuli. We then present feature importance maps illustrating which features played the largest role in detecting these categories (1.2.2). After that, we present the results of our quartile analysis in greater detail (1.3): We report pair-wise comparison
C.: Technologies that make you smile: Adding humor to text-based applications
- IEEE Intelligent Systems
, 2006
"... N atural language's creative genres are traditionally considered to be outside the scope of computational modeling. Computational linguists have paid little attention to humor in particular because it is puzzling by nature. However, given the importance of humor in our daily lives and computer ..."
Abstract
-
Cited by 4 (3 self)
- Add to MetaCart
longer jokes can have a relatively complex narrative structure, a one-liner must produce the humorous effect in one shot, with few words. This makes one-liners particularly suitable for automatic learning settings because the humor-producing features are guaranteed to be present in the first (and only
LEADERS ON THE COUCH: THE CASE OF ROBERTO CALVI
"... I would like to express my appreciation for the help of ..."
Akademisk avhandling för teknisk doktorsexamen vid
, 1994
"... mcmxciv This thesis deals with combinatorics in connection with Coxeter groups, finitely generated but not necessarily finite. The representation theory of groups as nonsingular matrices over a field is of immense theoretical importance, but also basic for computational group theory, where the group ..."
Abstract
- Add to MetaCart
mcmxciv This thesis deals with combinatorics in connection with Coxeter groups, finitely generated but not necessarily finite. The representation theory of groups as nonsingular matrices over a field is of immense theoretical importance, but also basic for computational group theory, where
Results 1 - 10
of
19
