EUVIMEDEUVIMED entdecken
Crossref

HAKE: A Knowledge Engine Foundation for Human Activity Understanding

Yong-Lu Li, Xinpeng Liu, Xiaoqian Wu, Yizhuo Li, Zuoyu Qiu, Liang Xu, Yue Xu, Hao-Shu Fang, Cewu Lu

IEEE Transactions on Pattern Analysis and Machine Intelligence · 01.07.2023 · 45 (7) · 8494-8506

DOI: 10.1109/tpami.2022.3232797 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, erschienen am 01.07.2023. Verfasst von Yong-Lu Li und 8 weiteren Autor:innen. Hauptthemen laut MEDLINE: Artificial Intelligence, Gadiformes. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: National Key Research and Development Project of China, Shanghai Municipal Science and Technology, Shanghai Qi Zhi Institute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human activity understanding is of widespread interest in artificial intelligence and spans diverse applications like health care and behavior analysis. Although there have been advances with deep learning, it remains challenging. The object recognition-like solutions usually try to map pixels to semantics directly, but activity patterns are much different from object patterns, thus hindering another success. In this article, we propose a novel paradigm to reformulate this task in two-stage: first mapping pixels to an intermediate space spanned by atomic activity primitives, then programming detected primitives with interpretable logic rules to infer semantics. To afford a representative primitive space, we build a knowledge base including 26+ M primitive labels and logic rules from human priors or automatic discovering. Our framework, Human Activity Knowledge Engine (HAKE), exhibits superior generalization ability and performance upon canonical methods on challenging benchmarks. Code and data are available at http://hake-mvig.cn/.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceGadiformesHumansAnimalsAlgorithmsKnowledge BasesHuman Activities

Förderung

  • National Key Research and Development Project of China
  • Shanghai Municipal Science and Technology
  • Shanghai Qi Zhi Institute
  • Shanghai Municipal Commission of Economy and Informatization

Zitieren

APA

Li, Y. L., Liu, X., Wu, X., Li, Y., Qiu, Z., Xu, L., Xu, Y., Fang, H. S., & Lu, C. (2023). HAKE: A Knowledge Engine Foundation for Human Activity Understanding. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(7), 8494-8506. https://doi.org/10.1109/tpami.2022.3232797

Vancouver

Li YL, Liu X, Wu X, Li Y, Qiu Z, Xu L, et al. HAKE: A Knowledge Engine Foundation for Human Activity Understanding. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(7):8494-8506. doi:10.1109/tpami.2022.3232797

BibTeX
@article{Li2023,
  author = {Li, Yong-Lu and Liu, Xinpeng and Wu, Xiaoqian and Li, Yizhuo and Qiu, Zuoyu and Xu, Liang and Xu, Yue and Fang, Hao-Shu and Lu, Cewu},
  title = {HAKE: A Knowledge Engine Foundation for Human Activity Understanding},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2023},
  volume = {45},
  number = {7},
  pages = {8494--8506},
  doi = {10.1109/tpami.2022.3232797}
}
Kostenlos starten →