Submitted to Ieee Transactions on Pattern Analysis and Machine Intelligence. Special Section on Video Surveillance and Monitoring a Bayesian Computer Vision System for Modeling Human Interactions
Explore this paper's citation graph
Summary
A real-time computer vision and machine learning system for modeling and recognizing human behaviors in a visual surveillance task and the ability to use these a priori models to accurately classify real human behaviors and interactions with no additional tuning or training is demonstrated.
- Cited by
- 1,958
- References
- 27
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:1545504
References
- Blob - An unsupervised clustering approach to spatial preprocessing of MSS imagery
- Factorial Hidden Markov Models
- Automatic Symbolic Traffic Scene Analysis Using Belief Networks
- Operations for Learning with Graphical Models
- From image sequences towards conceptual descriptions
- Advanced visual surveillance using Bayesian networks
- The Representation Space Paradigm of Concurrent Evolving Object Descriptions
- Active gesture recognition using partially observable Markov decision processes
- A tutorial on hidden Markov models and selected applications in speech recognition
- Building qualitative event models automatically from visual input
- Pfinder: real-time tracking of the human body
- Modeling and Prediction of Human Behavior
- Boltzmann Chains and Hidden Markov Models
- Coupled hidden Markov models for complex action recognition
- Probabilistic visual learning for object detection
- Graphical Models for Recognizing Human Interactions
- Coupled hidden Markov models for modeling interacting processes
- MASSACHUSETTS INSTITUTE OF TECHNOLOGY ARTIFICIAL INTELLIGENCE LABORATORY and CENTER FOR BIOLOGICAL AND COMPUTATIONAL LEARNING DEPARTMENT OF BRAIN AND COGNITIVE SCIENCES
- Ieee Transactions on Knowledge and Data Engineering, to Appear Final Draft 1 a Guide to the Literature on Learning Probabilistic Networks from Data
- Mean field networks that learn to discriminate temporally distorted strings
Cited by
- A Comparative Study of Background Estimation Algorithms
- Time Dependent On-line Boosting for Robust Background Modeling
- Layered graphical models for tracking partially-occluded moving objects in video
- Using a Multimodal Sensing Approach to Characterize Human Responses to Affective and Deceptive States
- Labeling hypergraph-structured data using markov network
- Modeling and Recognizing Human Activities from Video
- Scene Understanding: perception, multi-sensor fusion, spatio-temporal reasoning and activity recognition. (Interprétation de Scènes : perception, fusion multi-capteurs, raisonnement spatio-temporel et reconnaissance d'activités)
- Multiple Cue Data Fusion using Markov Random Fields for Motion Detection
- Using Evidence Feed-Forward Hidden Markov Models
- A Framework for Activity Recognition and Detection of Unusual Activities
- Multimodal intent recognition for natural human-robotic interaction
- A fuzzy framework for human hand motion recognition
- Review of Computer Vision in Intelligent Environment Design
- Metode Background Subtraction untuk Deteksi Obyek Pejalan Kaki pada Lingkungan Statis
- Registration and Tracking Report
- Scene monitoring with a forest of cooperative sensors
- Fuzzy Voxel Object
- An event detection framework in video sequences based on hierarchic event structure perception
- Disparity contour grouping for multi-object segmentation in dynamically textured scenes
- An Examination of Audio-Visual Fused HMMs for Speaker Recognition
Related papers
No related papers recorded.