• Corpus ID: 16902873

Plan and Activity Recognition from a Topic Modeling Perspective

@inproceedings{Freedman2014PlanAA,
  title={Plan and Activity Recognition from a Topic Modeling Perspective},
  author={Richard Gabriel Freedman and Hee-Tae Jung and Shlomo Zilberstein},
  booktitle={ICAPS},
  year={2014}
}
We examine new ways to perform plan recognition (PR) using natural language processing (NLP) techniques. PR often focuses on the structural relationships between consecutive observations and ordered activities that comprise plans. However, NLP commonly treats text as a bag-of-words, omitting such structural relationships and using topic models to break down the distribution of concepts discussed in documents. In this paper, we examine an analogous treatment of plans as distributions of… 

Figures from this paper

Temporal and Object Relations in Unsupervised Plan and Activity Recognition
We consider ways to improve the performance of unsupervised plan and activity recognition techniques by considering temporal and object relations in addition to postural data. Temporal relationships
A Study of Action Recognition Problems: Dataset and Architectures Perspectives
TLDR
Different action recognition datasets are explored to highlight their ability to evaluate different models, and a usage is proposed for each dataset based on the content and format of data it includes, the number of classes and challenges it covers.
Discovering Underlying Plans Based on Shallow Models
TLDR
Two approaches are proposed, DUP and RNNPlanner, to discover target plans based on vector representations of actions based on the corpora, capable of discovering underlying plans that are not from plan libraries without requiring action models provided.
Does the Human's Representation Matter for Unsupervised Activity Recognition?
TLDR
Several ways that motion capture information can be represented for use in unsupervised activity recognition methods are presented, and it is illustrated how the representation choice has the potential to produce variations in the learned clusters.
A Unifying Perspective of Plan, Activity, and Intent Recognition
TLDR
A generalized formalization of recognition that can be used in all three types of recognition is proposed and a perspective that emphasizes how PAIR applies to different aspects of the generative planning and execution process is proposed.
Observation Decoding with Sensor Models: Recognition Tasks via Classical Planning
TLDR
This paper formalizes the observation decoding task exploiting a probabilistic sensor model to build more accurate hypothesis about the behaviour of the acting agent and forms the probability distribution of the observations perceived when the agent performs an action or visits a state as a classical cost planning task that is solved with an optimal planner.
Automated Interpretations of Unsupervised Learning-Derived Clusters for Activity Recognition
TLDR
This work proposes the use of feature vectors for signal data such as postures read by a RGB-D sensor in order to derive activity clusters for AR tasks which enable machines to derive their own activity clusters.
Learning Therapy Strategies from Demonstration Using Latent Dirichlet Allocation
TLDR
This work applies Latent Dirichlet Allocation on the batch data collected during teletherapy sessions between a single stroke patient and a single therapist to encode the therapist's decision criteria in terms of the patient's motor performance features.
Integrating Planning and Recognition to Close the Interaction Loop
TLDR
A framework that integrates these processes by taking advantage of features shared between them is proposed, which can be risky in real-time situations where there may be enough time to only run a few steps.
Recognizing Multi-Agent Plans When Action Models and Team Plans Are Both Incomplete
  • H. Zhuo
  • Computer Science
    ACM Trans. Intell. Syst. Technol.
  • 2019
TLDR
This article presents a weighted MAX-SAT–based framework to recognize multi-agent plans from partially observed team traces with the help of two types of auxiliary knowledge to help recognizeMulti-Agent Plan Recognition, and empirically exhibits both effectiveness and efficiency in benchmark domains from International Planning Competition.
...
...

References

SHOWING 1-10 OF 17 REFERENCES
Human Action Recognition by Semilatent Topic Models
  • Yang WangGreg Mori
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2009
TLDR
Two new models for human action recognition from video sequences using topic models differ from previous latent topic models for visual recognition in two major aspects: first of all, the latent topics in the models directly correspond to class labels; second, some of the latent variables in previous topic models become observed in this case.
Using Dependent Regions for Object Categorization in a Generative Framework
  • G. WangYe ZhangLi Fei-Fei
  • Computer Science
    2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
TLDR
This paper relaxes the independence assumption and model explicitly the inter-dependency of the local regions of the "bag of words" models, and introduces a linkage structure over the latent themes to encode the dependencies of the patches.
On Natural Language Processing and Plan Recognition
TLDR
The relations between natural language processing and plan recognition are outlined, it is argued that each of them can effectively inform the other, and key recent research results in NLP are focused on and argued for their applicability to PR.
The Hierarchical Hidden Markov Model: Analysis and Applications
TLDR
This work introduces, analyzes and demonstrates a recursive hierarchical generalization of the widely used hidden Markov models, which is motivated by the complex multi-scale structure which appears in many natural sequences, particularly in language, handwriting and speech.
Accounting for Context in Plan Recognition, with Application to Traffic Monitoring
TLDR
A general Bayesian framework encompassing this view is presented, and it is shown how context can be exploited in plan recognition on a problem in traffic monitoring.
Discovery of activity patterns using topic models
TLDR
Experimental results show the ability of the approach to model and recognize daily routines without user annotation to be able to be used in this work.
Learning Hierarchical Hidden Markov Models with General State Hierarchy
TLDR
This paper presents a general HHMM in which the state hierarchy can be a lattice allowing arbitrary sharing of substructures, and provides a method for numerical scaling to avoid underflow, an important issue in dealing with long observation sequences.
Getting Serious About Parsing Plans: A Grammatical Analysis of Plan Recognition
This paper is concerned with making precise the notion that recognizing plans is much like parsing text. To this end, it establishes a correspondence between Kautz' plan recognition formalism and
Probabilistic Topic Models
Plan Recognition (Dagstuhl Seminar 11141)
TLDR
This Dagstuhl seminar brought together researchers with a wide range of interests and backgrounds and featured a substantial set of longer tutorials on aspects of plan and activity recognition, and related topics and useful methods, as a way of establishing a common vocabulary and shared basis of understanding.
...
...