DMCA
Recognizing human actions by attributes (2011)
Cached
Download Links
| Venue: | University of Michigan |
| Citations: | 96 - 3 self |
BibTeX
@INPROCEEDINGS{Liu11recognizinghuman,
author = {Jingen Liu and Benjamin Kuipers and Silvio Savarese},
title = {Recognizing human actions by attributes},
booktitle = {University of Michigan},
year = {2011}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In this paper we explore the idea of using high-level se-mantic concepts, also called attributes, to represent human actions from videos and argue that attributes enable the construction of more descriptive models for human action recognition. We propose a unified framework wherein man-ually specified attributes are: i) selected in a discriminative fashion so as to account for intra-class variability; ii) co-herently integrated with data-driven attributes to make the attribute set more descriptive. Data-driven attributes are automatically inferred from the training data using an in-formation theoretic approach. Our framework is built upon a latent SVM formulation where latent variables capture the degree of importance of each attribute for each action class. We also demonstrate that our attribute-based action representation can be effectively used to design a recogni-tion procedure for classifying novel action classes for which no training samples are available. We test our approach on several publicly available datasets and obtain promising re-sults that quantitatively demonstrate our theoretical claims. 1.
Keyphrases
human action data-driven attribute discriminative fashion training data available datasets action class high-level se-mantic concept intra-class variability theoretical claim human action recognition promising re-sults latent svm formulation in-formation theoretic approach novel action class unified framework descriptive model recogni-tion procedure attribute-based action representation training sample
