Back to search

Central Florida

Feature Pruning For Action Recognition In Complex Environment

Abstract

dc:description.abstract

A significant number of action recognition research efforts use spatio-temporal interest point detectors for feature extraction. Although the extracted features provide useful information for recognizing actions, a significant number of them contain irrelevant motion and background clutter. In many cases, the extracted features are included as is in the classification pipeline, and sophisticated noise removal techniques are subsequently used to alleviate their effect on classification. We introduce a new action database, created from the Weizmann database, that reveals a significant weakness in systems based on popular cuboid descriptors. Experiments show that introducing complex backgrounds, stationary or dynamic, into the video causes a significant degradation in recognition performance. Moreover, this degradation cannot be fixed by fine-tuning the system or selecting better interest points. Instead, we show that the problem lies at the descriptor level and must be addressed by modifying descriptors.

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Nagaraja, Adarsh
Contributors dc:contributor
  • Tappen, Marshall

Subjects

dc:subject × 10

Rights

Language dc:language
English

Identifiers

dc:identifier.*
Identifier
CFE0003882

Chain of custody

source
Harvested from
Central Florida
Base URL
stars.library.ucf.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Nagaraja, Adarsh. Feature Pruning For Action Recognition In Complex Environment. https://stars.library.ucf.edu/etd/1875