Sciweavers

NIPS
2008
14 years 29 days ago
Learning a discriminative hidden part model for human action recognition
We present a discriminative part-based approach for human action recognition from video sequences using motion features. Our model is based on the recently proposed hidden conditi...
Yang Wang 0003, Greg Mori
NIPS
2008
14 years 29 days ago
Multi-label Multiple Kernel Learning
We present a multi-label multiple kernel learning (MKL) formulation in which the data are embedded into a low-dimensional space directed by the instancelabel correlations encoded ...
Shuiwang Ji, Liang Sun, Rong Jin, Jieping Ye
NIPS
2008
14 years 29 days ago
Multi-resolution Exploration in Continuous Spaces
The essence of exploration is acting to try to decrease uncertainty. We propose a new methodology for representing uncertainty in continuous-state control problems. Our approach, ...
Ali Nouri, Michael L. Littman
NIPS
2008
14 years 29 days ago
Evaluating probabilities under high-dimensional latent variable models
We present a simple new Monte Carlo algorithm for evaluating probabilities of observations in complex latent variable models, such as Deep Belief Networks. While the method is bas...
Iain Murray, Ruslan Salakhutdinov
NIPS
2008
14 years 29 days ago
Non-parametric Regression Between Manifolds
This paper discusses non-parametric regression between Riemannian manifolds. This learning problem arises frequently in many application areas ranging from signal processing, comp...
Florian Steinke, Matthias Hein
NIPS
2008
14 years 29 days ago
Clustering via LP-based Stabilities
A novel center-based clustering algorithm is proposed in this paper. We first formulate clustering as an NP-hard linear integer program and we then use linear programming and the ...
Nikos Komodakis, Nikos Paragios, Georgios Tziritas
NIPS
2008
14 years 29 days ago
Overlaying classifiers: a practical approach for optimal ranking
ROC curves are one of the most widely used displays to evaluate performance of scoring functions. In the paper, we propose a statistical method for directly optimizing the ROC cur...
Stéphan Clémençon, Nicolas Va...
NIPS
2008
14 years 29 days ago
Clustered Multi-Task Learning: A Convex Formulation
In multi-task learning several related tasks are considered simultaneously, with the hope that by an appropriate sharing of information across tasks, each task may benefit from th...
Laurent Jacob, Francis Bach, Jean-Philippe Vert
NIPS
2008
14 years 29 days ago
Tracking Changing Stimuli in Continuous Attractor Neural Networks
Continuous attractor neural networks (CANNs) are emerging as promising models for describing the encoding of continuous stimuli in neural systems. Due to the translational invaria...
C. C. Alan Fung, K. Y. Michael Wong, Si Wu
NIPS
2008
14 years 29 days ago
Mind the Duality Gap: Logarithmic regret algorithms for online optimization
We describe a primal-dual framework for the design and analysis of online strongly convex optimization algorithms. Our framework yields the tightest known logarithmic regret bound...
Shai Shalev-Shwartz, Sham M. Kakade