Search Results for author: Matti Karppa

Found 5 papers, 2 papers with code

DEANN: Speeding up Kernel-Density Estimation using Approximate Nearest Neighbor Search

1 code implementation6 Jul 2021 Matti Karppa, Martin Aumüller, Rasmus Pagh

We present an algorithm called Density Estimation from Approximate Nearest Neighbors (DEANN) where we apply Approximate Nearest Neighbor (ANN) algorithms as a black box subroutine to compute an unbiased KDE.

Density Estimation

An adaptive prefix-assignment technique for symmetry reduction

2 code implementations26 Jun 2017 Tommi Junttila, Matti Karppa, Petteri Kaski, Jukka Kohonen

This paper presents a technique for symmetry reduction that adaptively assigns a prefix of variables in a system of constraints so that the generated prefix-assignments are pairwise nonisomorphic under the action of the symmetry group of the system.

SLMotion - An extensible sign language oriented video analysis tool

no code implementations LREC 2014 Matti Karppa, Ville Viitaniemi, Marcos Luzardo, Jorma Laaksonen, Tommi Jantunen

We present a software toolkit called SLMotion which provides a framework for automatic and semiautomatic analysis, feature extraction and annotation of individual sign language videos, and which can easily be adapted to batch processing of entire sign language corpora.

Sign Language Recognition

S-pot - a benchmark in spotting signs within continuous signing

no code implementations LREC 2014 Ville Viitaniemi, Tommi Jantunen, Leena Savolainen, Matti Karppa, Jorma Laaksonen

In this paper we present S-pot, a benchmark setting for evaluating the performance of automatic spotting of signs in continuous sign language videos.

Comparing computer vision analysis of signed language video with motion capture recordings

no code implementations LREC 2012 Matti Karppa, Tommi Jantunen, Ville Viitaniemi, Jorma Laaksonen, Birgitta Burger, Danny De Weerdt

We consider a non-intrusive computer-vision method for measuring the motion of a person performing natural signing in video recordings.

Cannot find the paper you are looking for? You can Submit a new open access paper.