Abstract

Automated video surveillance requires the recognition of agent plans from videos. One promising direction for plan recognition involves learning shallow action affinity models from plan traces. Extracting such traces from raw video involves uncertainty about the actions. One solution is to represent traces as sequences of action distributions. To use such a representation in approximate plan recognition, we need embeddings of these action distributions. To address this problem, we propose a distribution to vector (Distr2Vec) model, which learns embeddings of action distributions using KL-divergence as the loss function.

Original languageEnglish (US)
Title of host publication17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages2153-2155
Number of pages3
Volume3
ISBN (Print)9781510868083
StatePublished - Jan 1 2018
Event17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018 - Stockholm, Sweden
Duration: Jul 10 2018Jul 15 2018

Other

Other17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018
CountrySweden
CityStockholm
Period7/10/187/15/18

    Fingerprint

Keywords

  • Distr2Vec
  • Distribution sequences
  • Plan recognition
  • Word2Vec

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering

Cite this

Zha, Y., Li, Y., Gopalakrishnan, S., Li, B., & Kambhampati, S. (2018). Recognizing plans by learning embeddings from observed action distributions. In 17th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2018 (Vol. 3, pp. 2153-2155). International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).