Uniform Evaluation of Properties in Activity Recognition - Université Paris-Est-Créteil-Val-de-Marne
Communication Dans Un Congrès Année : 2022

Uniform Evaluation of Properties in Activity Recognition

Seyed Modaresi
Aomar Osmani
Mohammadreza Razzazi

Résumé

The main additional problem in activity recognition (AR) systems in contrast to traditional ones is the importance of duration: a predicted concept in AR is durative and can be correct in a period and incorrect in another one. Therefore, it is fundamental to extend the correctness vocabulary and to formalize a new evaluation system including these extensions. Even in similar areas, few empirical attempts are proposed which are confronted with the problems of correctness and completeness. In this paper, we propose the first formal multi-modal evaluation approach for durative concepts. This novel mathematical method evaluates the performance of an AR system from multiple perspectives, including detection, total duration, relative duration, boundary alignment, and uniformity. It extracts the properties considered in the state-of-the-art and redefines the well-known true-positive, false-positive and false-negative terms for durative events. Our proposed method is extensible, interpretable, customizable, open source and improves the expressiveness of the evaluation while its computation complexity remains linear. Comprehensive experimental evaluations are conducted to show the usefulness of our proposed method.
Fichier non déposé

Dates et versions

hal-04063325 , version 1 (08-04-2023)

Identifiants

Citer

Seyed Modaresi, Aomar Osmani, Mohammadreza Razzazi, Abdelghani Chibani. Uniform Evaluation of Properties in Activity Recognition. Advances in Knowledge Discovery and Data Mining: 26th Pacific-Asia Conference, PAKDD 2022, May 2022, Chengdu, China. pp.83-95, ⟨10.1007/978-3-031-05936-0_7⟩. ⟨hal-04063325⟩

Collections

LISSI UPEC
32 Consultations
0 Téléchargements

Altmetric

Partager

More