Qualitative Recognition of Ongoing Human Action Sequences
Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence. Robotics and Vision. Pages 1600-1608.
Abstract
This paper deals with the qualitative visual recognition of continuous human action sequences. Based on an analysis of the structure of physical actions, a framework for temporal segmentation and qualitative classification of physical actions is proposed. In order to achieve correctness as W<'ll as efficiency in real time action recognition , a hierarchical spatio-temporal attention cont.rol nwthod is developed . As the integration of these ideas, a cognitive architecture for action recognition is proposed. An experimental system is built for recognizing block assembly tasks performed by human workers. The system generated symbolic descriptions of the shown tasks in near r ea l time.
@inproceedings{ijcai1993p222,
title = {Qualitative Recognition of Ongoing Human Action Sequences},
author = {Kuniyoshi, Yasuo and Inoue, Hirochika},
booktitle = {Proceedings of the Thirteenth International Joint Conference on
Artificial Intelligence, {IJCAI-93}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Ruzena Bajcsy},
pages = {1600--1608},
year = {1993},
note = {Robotics and Vision},
url = {https://ijcai.org/proceedings/1993/222},
}
TY - CPAPER TI - Qualitative Recognition of Ongoing Human Action Sequences AU - Kuniyoshi, Yasuo AU - Inoue, Hirochika T2 - Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, IJCAI-93 PB - International Joint Conferences on Artificial Intelligence PY - 1993 SP - 1600 EP - 1608 UR - https://ijcai.org/proceedings/1993/222 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
