TY - GEN
T1 - Strategic Pairwise Selection for Labeling High-Risk Action from Video-Based Data
AU - Chen, Kuan Ting
AU - Chen, Bo Heng
AU - Chuang, Kun Ta
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.
PY - 2024
Y1 - 2024
N2 - Accidental risk can occur anywhere in daily life, with typical examples including pedestrian accidents and concerns about child safety on school campuses. In response to these risks, the field of dangerous behavior detection technology has gained considerable attention. Such technology aims to minimize response times and mitigate the occurrence of harm through early detection of potentially dangerous behavior. However, when it comes to generating label data for these models, the diversity of human behavior and the subjective nature of defining dangerous behaviors make the labeling process challenging, often leading to ambiguous situations. To overcome this challenge, we introduce a labeling generation framework based on pair comparison called Strategic Pair Selection (SPS). SPS employs a comparative approach to assist annotators in determining ambiguous cases, thus enhancing the accuracy of the detection of dangerous behavior. Additionally, SPS combines video-based action analysis to learn distinctive features of dangerous behaviors, optimizing the selection of pairs for comparison. The experimental results on real data demonstrate that SPS outperforms other pairwise sampling baseline models, showing its attractive practicability.
AB - Accidental risk can occur anywhere in daily life, with typical examples including pedestrian accidents and concerns about child safety on school campuses. In response to these risks, the field of dangerous behavior detection technology has gained considerable attention. Such technology aims to minimize response times and mitigate the occurrence of harm through early detection of potentially dangerous behavior. However, when it comes to generating label data for these models, the diversity of human behavior and the subjective nature of defining dangerous behaviors make the labeling process challenging, often leading to ambiguous situations. To overcome this challenge, we introduce a labeling generation framework based on pair comparison called Strategic Pair Selection (SPS). SPS employs a comparative approach to assist annotators in determining ambiguous cases, thus enhancing the accuracy of the detection of dangerous behavior. Additionally, SPS combines video-based action analysis to learn distinctive features of dangerous behaviors, optimizing the selection of pairs for comparison. The experimental results on real data demonstrate that SPS outperforms other pairwise sampling baseline models, showing its attractive practicability.
UR - http://www.scopus.com/inward/record.url?scp=85190781232&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85190781232&partnerID=8YFLogxK
U2 - 10.1007/978-981-97-1711-8_4
DO - 10.1007/978-981-97-1711-8_4
M3 - Conference contribution
AN - SCOPUS:85190781232
SN - 9789819717101
T3 - Communications in Computer and Information Science
SP - 46
EP - 60
BT - Technologies and Applications of Artificial Intelligence - 28th International Conference, TAAI 2023, Proceedings
A2 - Lee, Chao-Yang
A2 - Lin, Chun-Li
A2 - Chang, Hsuan-Ting
PB - Springer Science and Business Media Deutschland GmbH
T2 - 28th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2023
Y2 - 1 December 2023 through 2 December 2023
ER -