Layered representations for human activity recognition
The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
We present the use of layered probabilistic representations using hidden Markov models for performing sensing, learning, and inference at multiple levels of temporal granularity We describe the use of representation in a system that diagnoses states of a user's activity based on real-time streams of evidence from video, acoustic, and computer interactions. We review the representation, present an implementation, and report on experiments with the layered representation in an office-awareness application.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The S-HSMM thus can be viewed as a member of the exponential family [5] with parameter θ.”
From Activity Recognition and Abnormality Detection with the Switching Hidden Semi-Markov Model (2005) · cites this paper as [5]
Citations
Cites
Fundamentals of speech recognition
Rabiner, L. R., & Juang, B.-H. F. (1993) · Cited by 7,680
Event structure in perception and conception.
Zacks, J. M., & Tversky, B. (2001) · Psychological Bulletin · doi:10.1037//0033-2909.127.1.3 · Cited by 1,198 · cited 1×
“Psychologists have, in fact, found that many human behaviors are hierarchically structured [ 20 ].”
BackgroundCoupled hidden Markov models for complex action recognition
Brand, M., Oliver, N., & Pentland, A. (2002) · Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.1997.609450 · Cited by 1,052 · cited 2×
“More complex models, such as Parameterized-HMM (PHMM) [19], Entropic-HMM [1], Variable-length HMM (VHMM) [8] and Coupled-HMM (CHMM) [2], have been used to recognize more complex activities such as the interaction between two people.”
MethodSelf-citationReal-time American Sign Language recognition from video using hidden Markov models
Starner, T., & Pentland, A. (2002) · Proceedings of International Symposium on Computer Vision - ISCV · doi:10.1109/iscv.1995.477012 · Cited by 773 · cited 1×
“Starner and Pentland in [18] use an HMM for recognizing hand movements used to relay symbols in American Sign Language.”
MethodRecognition of visual activities and interactions by stochastic parsing
Ivanov, Y. A., & Bobick, A. F. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.868686 · Cited by 659 · cited 3×
“[12] Y. Ivanov and A. Bobick.”
BackgroundInfluentialModels of attention in computing and communication: from principles to applications
Horvitz, E., Kadie, C., Paek, T., & Hovel, D. (2003) · Communications of the ACM · doi:10.1145/636772.636798 · Cited by 313
Self-citationHorvitz, E., Jacobs, A., & Hovel, D. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1301.6707 · Cited by 311 · cited 1×
“Recent work on probabilistic models for reasoning about a user’s location, intentions, and focus of attention have highlighted opportunities for building new kinds of applications and services [10].”
BackgroundSelf-citationDiscovery and segmentation of activities in video
Brand, M., & Kettnaker, V. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.868685 · Cited by 301 · cited 3×
“Brand and Kettnaker in [1] propose an entropicHMM approach to organize the observed video activities (office activity and outdoor traffic) into meaningful states.”
BackgroundMethodA practical methodology for speech source localization with microphone arrays
Brandstein, M. S., & Silverman, H. F. (1997) · Computer Speech & Language · doi:10.1006/csla.1996.0024 · Cited by 291 · cited 4×
“Typically, TDOA-based approaches have two steps: the time delay estimation and the sound source localization.”
BackgroundInfluentialLearning Variable-Length Markov Models of Behavior
Galata, A., Johnson, N., & Hogg, D. (2001) · Computer Vision and Image Understanding · doi:10.1006/cviu.2000.0894 · Cited by 265 · cited 2×
“More complex models, such as Parameterized-HMM (PHMM) [19], Entropic-HMM [1], Variable-length HMM (VHMM) [8] and Coupled-HMM (CHMM) [2], have been used to recognize more complex activities such as the interaction between two people.”
Method
Cited by
Items 101–200 of 317
POMDP Models for Assistive Technology
Hoey, J., Poupart, P., Boutilier, C. E., & Mihailidis, A. (2011) · IGI Global eBooks · doi:10.4018/978-1-60960-165-2.ch013 · Cited by 34
“This POMDP combines elements of human activity modeling (Wren et al. 1997; Oliver, Horvitz, & Garg 2002) and dialogue management (Roy, Gordon, & Thrun 2003; Williams, Poupart, & Young 2005).”
MethodHMM machine learning and inference for Activities of Daily Living recognition
Cheng, B., Tsai, Y.-A., Liao, G., & Byeon, E.-S. (2009) · The Journal of Supercomputing · doi:10.1007/s11227-009-0335-0 · Cited by 33
“Oliver proposed a layered Hidden Markov Model based activity recognition system that has a more explicit definition of activity resulting in more precise inference results [6].”
BackgroundMulti-user Preference Model and Service Provision in a Smart Home Environment
Lin, Z., & Fu, L. (2007) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2007.4341737 · Cited by 33
“In [13], layered Hidden Markov Models (LHMMs) is used to recognize multiple users' activity.”
BackgroundDetecting Stochastically Scheduled Activities in Video ∗
Albanese, M., Moscato, V., Picariello, A., Subrahmanian, V. S., & Udrea, O. (n.d.) · Cited by 33
Lu, C.-H., Ho, Y.-C., Chen, Y., & Fu, L. (2013) · IEEE Transactions on Human-Machine Systems · doi:10.1109/tsmc.2013.2281586 · Cited by 33
“Previous researchers have modeled activities using graphic models such as Bayesian networks (see [22], [23]) or Hidden Markov Models (see [24]–[26]) in supervised [27]–[29], semisupervised [30], [31], or unsupervised learning [32], [33] approaches.”
MethodPADS: A Probabilistic Activity Detection Framework for Video Data
Albanese, M., Chellappa, R., Cuntoor, N. P., Moscato, V., Picariello, A., Subrahmanian, V. S., & Udrea, O. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.33 · Cited by 31
“Oliver et al. [ 22 ] described an approach based on CHMMs for learning and recognizing human interactions.”
Human Movement Modeling and Activity Perception Based on Fiber-Optic Sensing System
Sun, Q., Hu, F., & Hao, Q. (2014) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2014.2354046 · Cited by 30
“The popular methods for hierarchical human activity analysis are statistical approaches [37].”
MethodSocial Behavioral Phenotyping of Drosophila With a 2D–3D Hybrid CNN Framework
Jiang, Z., Chazot, P. L., Celebi, M. E., Crookes, D., & Jiang, R. (2019) · IEEE Access · doi:10.1109/access.2019.2917000 · Cited by 31
An Iterative Decoding Algorithm for Fusion of Multimodal Information
Shivappa, S. T., Rao, B. D., & Trivedi, M. M. (2007) · EURASIP Journal on Advances in Signal Processing · doi:10.1155/2008/478396 · Cited by 29
“For an activity that involves temporal variation, hidden Markov models (HMMs) are a popular modeling framework [14].”
BackgroundDaily Routine Classification from Mobile Phone Data
Farrahi, K., & Gática-Pérez, D. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-85853-9_16 · Cited by 32
Rank Pooling Approach for Wearable Sensor-Based ADLs Recognition
Nisar, M. A., Shirahama, K., Li, F., Huang, X., & Grzegorzek, M. (2020) · Sensors · doi:10.3390/s20123463 · Cited by 28
“A layered HMM approach is proposed to detect human activities in an office environment [25] using multimodal data.”
Toward Recognition of Short and Non-repetitive Activities from Wearable Sensors
Zinnen, A., Laerhoven, K. V., & Schiele, B. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-76652-0_9 · Cited by 28
“[6] discover that HMMs have the ability to capture different levels of abstraction with respect to the time granularity.”
BackgroundUnderstanding human interactions with track and body synergies (TBS) captured from multiple views
Park, S., & Trivedi, M. M. (2008) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2007.10.005 · Cited by 28
“Section 3 describes the overall system diagram and the two-stage analysis paradigm.”
BackgroundLearning Automation Policies for Pervasive Computing Environments
Ziebart, B. D., Roth, D., Campbell, R. H., & Dey, A. K. (2005) · International Conference on Autonomic Computing · doi:10.1109/icac.2005.37 · Cited by 28
“Much of the machine learning research in pervasive computing environments is focused on activity recognition [13, 8, 3].”
BackgroundContext Cube: Flexible and Effective Manipulation of Sensed Context Data
Harvel, L. D., Liu, L., Abowd, G. D., Lim, Y.-X., Scheibe, C., & Chatham, C. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24646-6_4 · Cited by 28
“We could also use other tems, dedicated to trending analysis, to construct the qualitative rule, such as the ordinates system at Microsoft [17].”
BackgroundMethodChikhaoui, B., Wang, S., & Pigot, H. (2012) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2012.08.004 · Cited by 33
“[17] proposed a layeredHMM for human activity recognition, to address the problem of temporal granularity.”
BackgroundDetecting and predicting of abnormal behavior using hierarchical Markov model in smart home network
Kang, W., Shin, D., & Shin, D. (2010) · Industrial Engineering and Engineering Management · doi:10.1109/icieem.2010.5646583 · Cited by 27
“Earlier approaches to tackling this problem included the layered hidden Markov model (LHMM) [ 4 ], stochastic context free grammar (SCFG) [5], abstract hidden Markov model (AHMM) [6], and hierarchical hidden Markov model (HHMM) [7, 8].”
MethodActivity recognition through multi-scale motion detail analysis
Du, Y., Chen, F., Xu, W., & Zhang, W. (2007) · Neurocomputing · doi:10.1016/j.neucom.2007.09.012 · Cited by 27
Gritai, A., Sheikh, Y. A., Rao, C., & Shah, M. A. (2009) · International Journal of Computer Vision · doi:10.1007/s11263-009-0239-8 · Cited by 28
“2001), Layered Hidden Markov Model (LHMM) (Oliver et al. 2002), stochastic context free grammar (SCFG) (Bobick and Ivanov 1998), and Hierarchical Hidden Markov model (HHMM) (Venkatesh et al.”
BackgroundFinding "Unexplained" Activities in Video
Albanese, M., Molinaro, C., Persia, F., Picariello, A., & Subrahmanian, V. S. (2011) · Archivio Istituzionale della Ricerca - Università degli Studi dell Aquila · doi:10.5591/978-1-57735-516-8/ijcai11-274 · Cited by 27
A Survey on Context-Aware Sensing for Body Sensor Networks
Korel, B. T., & Koo, S. G. M. (2010) · Wireless Sensor Network · doi:10.4236/wsn.2010.28069 · Cited by 29
“Layered HMMs (LHMM) are separate layers of HMMs connected according to their inferential results [31].”
BackgroundHierarchical modeling using automated sub-clustering for sound event recognition
Niessen, M. E., van Kasteren, T. L. M., & Merentitis, A. (2013) · IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) · doi:10.1109/waspaa.2013.6701862 · Cited by 27
“The variation and compositionality of events in real-world environment has previously been accounted for with a cascade hierarchical model, which means that the output of a HMM was fed as input to another HMM, therefore processing the data at different levels of abstraction [3].”
MethodAn Exploration into Activity-Informed Physical Advertising Using PEST
Sala, M. C., Partridge, K., Jacobson, L., & Begole, B. (2007) · Springer eBooks · doi:10.1007/978-3-540-72037-9_5 · Cited by 29
Efficient Hidden Semi-Markov Model Inference for Structured Video Sequences
Tweed, D., Fisher, R. B., Bins, J., & List, T. (2006) · IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance (VS-PETS) · doi:10.1109/vspets.2005.1570922 · Cited by 24
“[ 18 ] develops the Layered HMM using this assumption and use it to recognise office behaviour.”
MethodAn empirical study of the potential for context-aware power management
Harris, C., & Cahill, V. (2007) · Ubiquitous Computing · doi:10.5555/1771592.1771606 · Cited by 25
Multimodal detection of human interaction events in a nursing home environment
Chen, D., Malkin, R. E., & Yang, J. (2004) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/1027933.1027949 · Cited by 24
Task oriented facial behavior recognition with selective sensing
Gu, H., Zhang, Y., & Ji, Q. (2005) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2005.05.004 · Cited by 26
“[30] proposed to use two layered HMM to decompose the substantial parameter spaces and segment the problem into distinct layers that operate at different temporal scales so as to make the recognition more efficient.”
MethodWhat is happening now? Detection of activities of daily living from simple visual features
Lepri, B., Mana, N., Cappelletti, A., Pianesi, F., & Zancanaro, M. (2010) · Personal and Ubiquitous Computing · doi:10.1007/s00779-010-0290-z · Cited by 23
“[19] exploited layered probabilistic representations (Layered Hidden Markov Models) for modeling human activities based on real-time video, audio, and computer-generated (mouse and keyboard) data stream.”
BackgroundBayesian Interaction Primitives: A SLAM Approach to Human-Robot Interaction.
Campbell, J., & Amor, H. B. (2017) · Conference on Robot Learning · Cited by 23
Tracking and Modeling of Human Activity Using Laser Rangefinders
Panangadan, A. V., Matarić, M. J., & Sukhatme, G. S. (2010) · International Journal of Social Robotics · doi:10.1007/s12369-009-0043-1 · Cited by 23
Park, S., & Kautz, H. (2008) · Cited by 22
Khan, Z. A., & Sohn, W. (2012) · Computing · doi:10.1007/s00607-012-0216-x · Cited by 22
“In [38], layered HMMs are utilized to recognize real time human activities in office environment e.”
MethodVideo Event Modeling and Recognition in Generalized Stochastic Petri Nets
Lavee, G., Rudzsky, M., Rivlin, E., & Borzin, A. (2009) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2009.2031372 · Cited by 21
Structural Learning of Activities from Sparse Datasets
Albinali, F., Davies, N., & Friday, A. (2007) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom.2007.33 · Cited by 23
Preference model assisted activity recognition learning in a smart home environment
Chen, Y., Lu, C.-H., Hsu, K.-C., Fu, L., Yeh, Y.-J., & Kuo, L.-C. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5353937 · Cited by 25
“For correctly detecting the starting/ending time of an activity, Oliver et al. [ 2 ] propose a Layer Hidden Markov Model (LHMM), which can be regarded as a cascade of Hidden Markov Models (HMMs), to deal with different time scales in different layers.”
BackgroundISEQL, an Interval-based Surveillance Event Query Language
Helmer, S., & Persia, F. (2016) · International Journal of Multimedia Data Engineering and Management · doi:10.4018/ijmdem.2016100101 · Cited by 21
Oliver, N., & Horvitz, E. (2003) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/958432.958442 · Cited by 20
Self-citationAdaBoost.MRF: Boosted Markov Random Forests and Application to Multilevel Activity Recognition
Tran, T., Phung, D., Venkatesh, S., & Bui, H. (2006) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2006.49 · Cited by 20
“Differing from the original LHMMs, our variant can handle partially observed state variables to make it compatible with the DCRFs considered in this paper.”
BackgroundMethodInfluentialValue directed learning of gestures and facial displays
Hoey, J., & Little, J. J. (2004) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2004.1315277 · Cited by 23
Minimalist plans for interpreting manipulation actions
Guha, A., Yang, Y., Fermuller, C. M., & Aloimonos, Y. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6697213 · Cited by 19
“In these methods to relate the objects to actions, HMMs are used in [20] and [21].”
MethodEnhancing Mobile Recommender Systems with Activity Inference
Partridge, K., & Price, B. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-02247-0_29 · Cited by 19
“A growing number of papers have investigated ways to answer the question “What are you doing now?” Some prominent work includes models for activity recognition [8], wearable systems [9], Conditional Random Fields using GPS data [10], and predictive systems using temporal patterns [11] and spatial patterns [12].”
BackgroundHigh-Level Surveillance Event Detection Using an Interval-Based Query Language
Helmer, S., & Persia, F. (2016) · IEEE International Conference on Semantic Computing (ICSC) · doi:10.1109/icsc.2016.19 · Cited by 19
Active-learning assisted self-reconfigurable activity recognition in a dynamic environment
Ho, Y.-C., Lu, C.-H., chen, I.-H., Huang, S.-S., Wang, C.-Y., & Fu, L. (2009) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2009.5152428 · Cited by 18
“In the second category [4] [5] [11] [12] [13] [14] [15] [16] [17], they focused more on analyzing what happen in the environments instead of tracking each individual, and the system learned the models of human activities from the frequent patterns of training data rather than from domain knowledge.”
BackgroundActivity recognition and uncertain knowledge in video scenes
Romdhane, R., Crispim-Junior, C. F., Brémond, F., & Thonnat, M. (2013) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2013.6636669 · Cited by 21
“HMMs and their extensions [16], [6], [4] have been widely used.”
BackgroundMethodPassive RFID for Object and Use Detection during Trauma Resuscitation
Parlak, S., Marsic, I., Sarcevic, A., Bajwa, W. U., Waterhouse, L. J., & Burd, R. S. (2015) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2015.2436393 · Cited by 18
“E-mail: {marsic, waheed.bajwa}@rutgers.edu.”
S-SEER: Selective Perception in a Multimodal Office Activity Recognition System
Oliver, N., & Horvitz, E. (2005) · Lecture notes in computer science · doi:10.1007/978-3-540-30568-2_11 · Cited by 18
“We have developed a probabilistic representation based on a tiered formulation of dynamic graphical models that we refer to as Layered Hidden Markov Models (LHMMs) [1].”
BackgroundMethodInfluentialSelf-citationKeyhole Adversarial Plan Recognition for Recognition of Suspicious and Anomalous Behavior
Avrahami-Zilberbrand, D., & Kaminka, G. A. (2014) · Elsevier eBooks · doi:10.1016/b978-0-12-398532-3.00004-x · Cited by 17
“AHMM [10], HHMM [17] and Layered HMM [46] are capable of handling activities that have hierarchical structure.”
MethodInfluentialUnusual Activity Analysis Using Video Epitomes and pLSA
Choudhary, A., Pal, M., Banerjee, S., & Chaudhury, S. (2008) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1109/icvgip.2008.89 · Cited by 17
“A video epitome is a compact representation of a video which is smaller in both space and time as compared to the input video.”
BackgroundIncorporating uncertainty in a layered HMM architecture for human activity recognition
Glodek, M., Bigalke, L., Schels, M., & Schwenker, F. (2011) · Joint ACM Workshop on Human Gesture and Behavior Understanding (J-HGBU) · doi:10.1145/2072572.2072584 · Cited by 16
“Incorporating Uncertainty in a Layered HMM Architecture for Human Activity Recognition Michael Glodek Institute of Neural Information Lutz Bigalke Institute of Neural Information Martin Schels Institute of Neural Information Processing University of Ulm 89075 Ulm, Germany michael.glodek@uniulm.de Processing Universit…”
MethodPADUA: Parallel Architecture to Detect Unexplained Activities
Molinaro, C., Moscato, V., Picariello, A., Pugliese, A., Rullo, A., & Subrahmanian, V. S. (2014) · ACM Transactions on Internet Technology · doi:10.1145/2633685 · Cited by 21
“2008], coupled Hidden Markov Models [Brand et al. 1997; Oliver et al. 2002], Dynamic Bayesian Networks [Hamid et al.”
BackgroundMethodOliver, N., & Horvitz, E. (2005) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2004.12.004 · Cited by 17
Self-citationGoal recognition with variable-order Markov models
Armentano, M. G., & Amandi, A. (2009) · Cited by 15
HMM Classifier for Human Activity Recognition
Gaikwad, K. (2012) · Computer Science & Engineering An International Journal · doi:10.5121/cseij.2012.2403 · Cited by 15
Recognising online spatial activities using a bioinformatics inspired sequence alignment approach
Riedel, D. E., Venkatesh, S., & Liu, W. (2008) · Pattern Recognition · doi:10.1016/j.patcog.2008.04.019 · Cited by 15
Multimodal Sensing for Explicit and Implicit Interaction
Wilson, A. D. (2005) · International Conference on Human-Computer Interaction · Cited by 15
Modeling sequences of user actions for statistical goal recognition
Armentano, M. G., & Amandi, A. (2011) · User Modeling and User-Adapted Interaction · doi:10.1007/s11257-011-9103-y · Cited by 14
“Part of these research efforts was devoted to learning the parameters of the model used for recognition, such as probabilities, while the structure of the model itself remained fixed (Oliver et al. 2002; Bui 2003; Philipose et al. 2004; Nguyen et al. 2005; Pascal et al. 2005; Duong et al. 2006; Liao et al. 2007).”
MethodMulti-person activity recognition through hierarchical and observation decomposed HMM
Guo, P., & Miao, Z. (2010) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2010.5582559 · Cited by 14
“Some variations of HMM have also been proposed like PHMM [3], LHMM [4], HHMM [5] and so on.”
MethodHuman action recognition based on scene semantics
Hu, T., Zhu, X., Guo, W., Wang, S., & Zhu, J. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5496-x · Cited by 14
“Currently, numerous detection methods have been proposed, including the analysis of space–time features [7, 9, 13, 19, 22, 53], activity template matching [1, 12, 38, 46, 47], sequential state models [5, 8, 14, 21, 41, 50], and image statistics [25, 30, 33].”
MethodProbabilistic Vehicle Motion Modeling and Risk Estimation
Tay, C., Mekhnacha, K., & Laugier, C. (2012) · Springer eBooks · doi:10.1007/978-0-85729-085-4_57 · Cited by 14
Real-Time Video Intelligent Surveillance System
Zhang, W., Chen, F., Xu, W., & Zhang, E. (2006) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2006.262707 · Cited by 13
“Although the hidden Semi-Markov model and Layer HMM [7] can solve the long-time case to some extent, they can not cover the case that the duration varies greatly.”
MethodA System for Context-Dependent User Modeling
Nurmi, P., Salden, A. H., Lau, S. L., Suomela, J., Sutterer, M., Millerat, J., Martin, M., Lagerspetz, E., & Poortinga, R. (2006) · Lecture notes in computer science · doi:10.1007/11915072_97 · Cited by 15
HIERARCHICAL DYNAMIC MODEL FOR HUMAN DAILY ACTIVITY RECOGNITION
Florentino-Liaño, B., Niamh, O., & Artés-Rodríguez, A. (2012) · International Conference on Bio-inspired Systems and Signal Processing · doi:10.5220/0003781900610068 · Cited by 12
“To overcome this problem, (Oliver et al., 2002) develop a Layered Hidden Markov Model (LHMM), in which each layer of the architecture is connected to the next layer via its inferential results.”
BackgroundJouini, R., Lemlouma, T., Maâlaoui, K., & Saidane, L. A. (2016) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc.2016.7577210 · Cited by 12
Peters, C., Wachsmuth, S., & Hoey, J. (2009) · International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) · doi:10.1145/1579114.1579179 · Cited by 13
“More recently, Oliver et al.[22] used a predefined hierarchical HMM to learn patterns of behavior in an office.”
MethodSurvey on classifying human actions through visual sensors
Rose, M. S. D., & Wagner, C. (2011) · Artificial Intelligence Review · doi:10.1007/s10462-011-9232-z · Cited by 12
“Layered Hidden Markov Models (LHMMs) are used in Oliver et al. (2002) to detect specific activities in an office environment.”
BackgroundMethodInfluentialD’Auria, D., Persia, F., Bettini, F., Helmer, S., & Siciliano, B. (2018) · IEEE International Conference on Robotic Computing (IRC) · doi:10.1109/irc.2018.00050 · Cited by 12
“[10] use coupled HMMs, Hamid et al.”
Machine listening for context-aware computing
Waibel, A., & Malkin, R. G. (2006) · Cited by 12
A Unified Model for Human Behavior Modeling Using a Hierarchy with a Variable Number of States
Alemdar, H. O., van Kasteren, T. L. M., Niessen, M. E., Merentitis, A., & Ersoy, C. (2014) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2014.653 · Cited by 12
“The data were obtained from either ambient sensors deployed in the environment such as video [6], [7], audio [3], [8], and binary sensors [9], [10] or wearable sensors deployed on the body such as accelerometers and gyroscopes [2], [11].”
BackgroundMethodAn Empirical Study of the Potential for Context-Aware Power Management
Harris, C., & Cahill, V. (2007) · Springer eBooks · doi:10.1007/978-3-540-74853-3_14 · Cited by 15
“[7] present a system, SEER, that infers user activity from realtime streams of video, acoustic, and computer interactions in an o ce environment.”
BackgroundDiscovering activity patterns in office environment using a network of low-resolution visual sensors
Eldib, M., Deboeverie, F., Philips, W. R., & Aghajan, H. K. (2017) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-017-0511-7 · Cited by 12
“In Oliver and Horvitz (2005), the authors compared Layered HMMs (LHMMs) (Oliver et al. 2002, 2004) and dynamic Bayesian networks for identifying office activities from multi-modal sensors such as video, audio and the user’s interaction with the computer.”
BackgroundGhasemi, A., & Kumar, C. N. R. (2017) · International Conference on Intelligent Sustainable Systems (ICISS) · doi:10.1109/iss1.2017.8389392 · Cited by 13
Activity Recognition in Smart Environments: An Information Retrieval Problem
Chikhaoui, B., Wang, S., & Pigot, H. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-21535-3_5 · Cited by 10
“approaches is a complex task, and it is based on a deep analysis of the data gathered from the environment [8, 2, 10, 11, 4, 7].”
BackgroundMirarmandehi, N., & Rabiee, H. R. (2010) · International Conference on Pervasive Computing and Applications (ICPCA) · doi:10.1109/icpca.2010.5704069 · Cited by 10
“For recognition of these activities a layered architecture was introduced in [12, 11] to recognize activities in an office.”
BackgroundAn activity based approach to context-aware computing
Canny, J., & Rattenbury, T. (2008) · Cited by 9
Video event description in scene context
Liu, C., Hu, C., Liu, Q., & Aggarwal, J. K. (2013) · Neurocomputing · doi:10.1016/j.neucom.2012.03.037 · Cited by 9
Walocha, F., Drewitz, U., & Ihme, K. A. (2022) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2022.3155375 · Cited by 9
Group Behavior Recognition for Gesture Analysis
Kosta, G., & Macq, B. M. M. (2008) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2007.913968 · Cited by 9
Context-Aware Experience Sampling for the Design and Study of Ubiquitous Technologies
Rondoni, J. (2003) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 13
A temporal belief-based hidden markov model for human action recognition in medical videos
Ahouandjinou, A., Motamed, C., & Ezin, E. C. (2015) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661815030025 · Cited by 8
“To get around these limitations, two classes of extension to the HMM have been pro posed [42]: HMM with Hierarchical pattern and its models includes the Abstract HMM [46], the Hierar chical HMM [42–45], and the Layered HMM [47] and Semi Hidden Markov Model (SHMM) and intro duces its hidden variants [48] including expl…”
MethodA Layered Hidden Markov Model for Predicting Human Trajectories in a Multi-floor Building
Li, Q., & Lau, H. C. (2015) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat.2015.239 · Cited by 8
Decision Theoretic Modeling of Human Facial Displays
Hoey, J., & Little, J. J. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24672-5_3 · Cited by 8
“There are many approaches to this problem, ranging from the complete Bayesian solution in which the temporal segmentation is parametrised and integrated out, to specification of a fixed segmentation time [4].”
BackgroundMethodClassification and Decision-Theoretic Framework for Detecting and Reporting Unseen Falls
Khan, S. S. (2016) · UWSpace (University of Waterloo) · doi:10.13140/rg.2.2.34981.29929 · Cited by 13
Learning People Movement Model from Multiple Cameras for Behaviour Recognition
Nguyen, N. T., Venkatesh, S., West, G. A. W., & Bui, H. H. (2004) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-27868-9_33 · Cited by 7
D’Auria, D., & Persia, F. (2015) · Communications in computer and information science · doi:10.1007/978-3-319-25936-9_12 · Cited by 7
Can a Single Human Supervise a Swarm of 100 Heterogeneous Robots?
Adams, J. A., Hamell, J. D., & Walker, P. M. (2024) · IEEE transactions on field robotics. · doi:10.1109/tfr.2024.3502316 · Cited by 7
“Many workload assessment algorithms rely on metrics collected from EEG headsets [18], [22], [23], cameras [24], [25], [26], motion capture [27], dedicated interaction systems (i.e., keyboards [19], [28], and smartphones [29]) to infer the human’s cognitive workload.”
Human activity recognition using deep learning techniques with spider monkey optimization
Kolkar, R., & Geetha, V. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15007-7 · Cited by 9
Discovery of Activity Structures using the Hierarchical Hidden Markov Model
Nguyen, N., & Venkatesh, S. (2005) · British Machine Vision Conference (BMVC) · doi:10.5244/c.19.40 · Cited by 7
“Recent approaches using hierarchical probabilistic models such as the layered hidden Markov model (LHMM) [13], stochastic context free grammar (SCFG) [15], the abstract hidden Markov model (AHMM) [3] or the hierarchical hidden Markov model (HHMM) [6, 2] are robust in modelling and recognising high-level behaviours.”
MethodA Vision-Based Emergency Response System with a Paramedic Mobile Robot
Jeong, I.-W., Jin, C. H. O. I., Cho, K., Seo, Y.-H., & Yang, H. S. (2010) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e93.d.1745 · Cited by 7
“Finite State Machine (FSM) [1], [4], Bayesian Network [3] and Hidden Markov Model (HMM) [6] are used to recognize users’ actions.”
MethodActivity recognition using logical hidden semi-Markov models
Zha, Y., Yue, S., Yin, Q., & Liu, X. (2013) · International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) · doi:10.1109/iccwamtip.2013.6716604 · Cited by 7
“The former class of enriched models concludes hierarchical HMMs [10], abstract HMMs [11], abstract hidden memory Markov models [12]and layered HMMs [13], the latter modification is done by using hidden semi-Markov models (HSMMs) [14][15].”
BackgroundHuman activity recognition using UWB radar and cameras on a mobile robot
Li, T., Ge, M.-M., & Yuan, G.-W. (2009) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea.2009.5138706 · Cited by 7
“The Variations include a coupled HMM (CHMM) [4, 5], a parametric HMM (PHMM) [6], some variable length Markov models (VLMM) [7, 8], an entropic HMM (EHMM) [9], and a layered HMM (LHMM) [10, 11, 12].”
MethodModelization of Limb Coordination for Human Action Analysis
Gaitanis, K., Hernandez, P. C., & Macq, B. M. M. (2006) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2006.312724 · Cited by 7
“Index Terms— dynamic, bayesian network, human action, particle filter, rao-blackwell, Hidden Markov Model.”
BackgroundOffice presence detection using multimodal context information
Huang, X., Weng, J., & Zhang, Z. (2004) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2004.1326659 · Cited by 7
“Currently, the overall system is hand-designed (computational model only) but a major part (IHDR) is automatically generated (computational model and model generator), which is the major difference between this work and [ 6 ].”
BackgroundResultThe use of hidden semi-Markov models in clinical diagnosis maze tasks
Marhasev, E., Hadad, M., Kaminka, G. A., & Feintuch, U. (2009) · Intelligent Data Analysis · doi:10.3233/ida-2009-0402 · Cited by 7
Peters, C., Hermann, T. M., & Wachsmuth, S. (2012) · International Conference on Pattern Recognition Applications and Methods · doi:10.5220/0003773601620171 · Cited by 6
“DBNs and Hidden Markov Models (HMMs) as a special variant of DBNs are widely used in user behavior recognition: (Oliver et al., 2002) use hierarchical HMMs for behavior recognition in an office environment, (Galata et al.”
MethodMachine Learning for Activity Recognition in Smart Buildings: A Survey
Amayri, M., Ali, S., Bouguila, N., & Ploix, S. (2021) · Springer eBooks · doi:10.1007/978-3-030-76477-7_6 · Cited by 12
Exploring Temporal Structure of Trajectory Components for Action Recognition
Cheng, G., Huang, Y., Wan, Y., & Buckles, B. P. (2014) · International Journal of Intelligent Systems · doi:10.1002/int.21690 · Cited by 6
“The spatial/temporal relations of actionlets are described by probabilistic models such as hidden Markov models 21,22 and dynamic Bayesian networks.”
MethodReal Time Analysis of Situation Events for Intelligent Surveillance
Xiao, X., & Layuan, L. (2008) · International Symposium on Computational Intelligence and Design · doi:10.1109/iscid.2008.164 · Cited by 6
“Oliver [5] proposed a Layered Hidden Markov Model (LHMM) where the classification results of the low layer are used as inputs to the higher layer.”
THRESHOLD DYNAMIC TIME WARPING FOR SPATIAL ACTIVITY RECOGNITION
Riedel, D. E., Venkatesh, S., & Liu, W. (2007) · Deakin Research Online (Deakin University) · Cited by 6
A language-based approach to indexing heterogeneous multimedia lifelog
Cheng, P.-W., Chennuru, S. K., Buthpitiya, S., & Zhang, Y. (2010) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/1891903.1891937 · Cited by 6
“Layered probabilistic representations using HMM is much more powerful for sensing, learning and inferencing human activities at multiple levels [5, 14].”
MethodCompound Hidden Markov Model for Activity Labelling
Figueroa-Angulo, J. I., Savage, J., Bribiesca, E., Ramírez, B. E., & Sucar, L. E. (2015) · International Journal of Intelligence Science · doi:10.4236/ijis.2015.55016 · Cited by 6
“The Layered Hidden Markov Model [28] [43] is a model in which several Hidden Markov Models in layers of increasing activity levels.”
Background
Metadata
- Authors
- Oliver, N., Horvitz, E., & Garg, A.
- Affiliations
- Microsoft (United States) (US)
- University of Illinois Urbana-Champaign (US)
- Venue
- Proceedings. Fourth IEEE International Conference on Multimodal Interfaces
- Publisher
- IEEE Comput. Soc
- Published
- 2003-06-26
- Pages
- 3-8
- OpenAlex
- W2134067070
- Cited by
- 312
- References
- 20
- Citations by year
- 2025: 1 · 2024: 2 · 2023: 6 · 2022: 2 · 2021: 4 · 2020: 12 · 2019: 6 · 2018: 14 · 2017: 17 · 2016: 12 · 2015: 18 · 2014: 13 · 2013: 26 · 2012: 23
- FWCI
- 14.53
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Modeling and Causal Inference
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Keywords
- human activity recognition, hidden Markov models, temporal granularity, video analysis, acoustic sensing, computer interaction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.