Sciweavers

237 search results - page 20 / 48
» Local Descriptors for Spatio-temporal Recognition
Sort
View
IBPRIA
2009
Springer
14 years 6 days ago
Class Representative Visual Words for Category-Level Object Recognition
Recent works in object recognition often use visual words, i.e. vector quantized local descriptors extracted from the images. In this paper we present a novel method to build such ...
Roberto Javier López-Sastre, Tinne Tuytelaa...
ECCV
2010
Springer
14 years 28 days ago
Making Action Recognition Robust to Occlusions and Viewpoint Changes
Most state-of-the-art approaches to action recognition rely on global representations either by concatenating local information in a long descriptor vector or by computing a single...
CVPR
2010
IEEE
14 years 4 months ago
Learning a Hierarchy of Discriminative Space-Time Neighborhood Features for Human Action Recognition
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...
Adriana Kovashka, Kristen Grauman
BMVC
2010
13 years 5 months ago
Learning Directional Local Pairwise Bases with Sparse Coding
Recently, sparse coding has been receiving much attention in object and scene recognition tasks because of its superiority in learning an effective codebook over k-means clusterin...
Nobuyuki Morioka, Shin'ichi Satoh
BMVC
2010
13 years 5 months ago
Automatic Facial Expression Recognition using Bags of Motion Words
We present a fully automatic approach for facial expression recognition based on a representation of facial motion using a vocabulary of local motion descriptors. Previous studies...
Liefei Xu, Philippos Mordohai