The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Recognition of human activity through hierarchical stochastic learning
Abstract
Seeking to extend the functional capability of the elderly, we explore the use of probabilistic methods to learn and recognise human activity in order to provide monitoring support. We propose a novel approach to learning the hierarchical structure of sequences of human actions through the application of the hierarchical hidden Markov model (HHMM). Experimental results are presented for learning and recognising sequences of typical activities in a home.
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
“Luhr et al. [17] were the first to employ the HHMM in modeling and recognizing human activities.”
From Efficient duration and hierarchical modeling for human activity recognition (2009) · cites this paper as [17]
Citations
Cites
A New Approach to Linear Filtering and Prediction Problems
Kalman, R. E. (1960) · Journal of Basic Engineering · doi:10.1115/1.3662552 · Cited by 31,751
A tutorial on hidden Markov models and selected applications in speech recognition
Rabiner, L. R. (1989) · Proceedings of the IEEE · doi:10.1109/5.18626 · Cited by 22,743 · cited 1×
“To allow for multiple observation sequences, we have modified the original re-estimation formula based on [8].”
MethodLearning patterns of activity using real-time tracking
Stauffer, C., & Grimson, W. E. L. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.868677 · Cited by 3,248 · cited 1×
“We implemented a robust motion tracker using a Gaussian background model for foreground segmentation as described in [9] and a Kalman filter to track objects across frames [5].”
MethodA Bayesian computer vision system for modeling human interactions
Oliver, N. M., Rosario, B., & Pentland, A. P. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.868684 · Cited by 1,578 · cited 1×
“Using HMMs and coupled HMMs (CHMMS) [7] built models of peoples’ individual and interactive behaviour based on their proximity and trajectories in an outdoor scene.”
MethodThe hierarchical hidden Markov model: Analysis and applications
Fine, S., Singer, Y., & Tishby, N. (1998) · Machine Learning · doi:10.1023/a:1007469218079 · Cited by 906 · cited 3×
“The HHMM was first proposed in [3] and is a special case of stochastic context free grammar (SCFG).”
BackgroundMethodInfluentialRecognition 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 1×
“The models were initially trained using data produced by synthetic agents and then refined using data collected from the real-world scene under surveillance.”
MethodPolicy Recognition in the Abstract Hidden Markov Model
Bui, H., Venkatesh, S., & WEST, G. A. W. (2002) · Cited by 243
Self-citationPolicy Recognition in the Abstract Hidden Markov Model
Bui, H. H., Venkatesh, S., & West, G. (2002) · Journal of Artificial Intelligence Research · doi:10.1613/jair.839 · Cited by 123
Self-citationTRACKING AND SURVEILLANCE IN WIDE-AREA SPATIAL ENVIRONMENTS USING THE ABSTRACT HIDDEN MARKOV MODEL
Bui, H., Venkatesh, S., & WEST, G. A. W. (2001) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001401000782 · Cited by 87 · cited 5×
“Similar to the HHMM, the abstract hidden Markov model (AHMM) [2, 1] is a hierarchical stochastic model Proceedings of the First IEEE International Conference on Pervasive Computing and Communications (PerCom’03) 0-7695-1895/03 $17.00 © 2003 IEEE 0-7695-1893-1/03 $17.00 © 2003 IEEE for representing a hierarchical abstr…”
MethodInfluentialSelf-citationHierarchical learning and planning in partially observable markov decision processes
Mahadevan, S., & Theocharous, G. (2002) · Cited by 30
Cited by
Qiu, S., Zhao, H., Jiang, N., Wang, Z., Liu, L., An, Y., Zhao, H., Miao, X., Liu, R., & Fortino, G. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.11.006 · Cited by 671
Activity Recognition and Abnormality Detection with the Switching Hidden Semi-Markov Model
Duong, T. V., Bui, H. H., Phung, D. Q., & Venkatesh, S. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.61 · Cited by 535
“Examples of these models include the Abstract HMM [2], the Hierarchical HMM [3, 8, 1], and the Layered HMM [18].”
MethodSelf-citationHuman Activity Recognition from Wireless Sensor Network Data: Benchmark and Software
van Kasteren, T. L. M., Englebienne, G., & Kröse, B. J. A. (2011) · Atlantis Ambient and Pervasive Intelligence · doi:10.2991/978-94-91216-05-3_8 · Cited by 215
“They have been su cce sfully applied to activity recognition from video data [20], in an office environment us ing cameras, microphones and keyboard input [21] and on data obtained from a wearable sens ing system [22].”
MethodReducing the Calibration Effort for Probabilistic Indoor Location Estimation
Chai, X., & Yang, Q. (2007) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2007.1025 · Cited by 178
“In pervasive computing, HMM and its variations have been successfully used in tracking and recognizing human activities [17].”
MethodThe use of pervasive sensing for behaviour profiling — a survey
Atallah, L., & Yang, G. (2009) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2009.06.009 · Cited by 170
“[73] and Kawanaka et al.”
An architecture for context prediction
Mayrhofer, R. (2004) · Trauner eBooks · Cited by 122
Efficient duration and hierarchical modeling for human activity recognition
Duong, T., Phung, D., Bui, H., & Venkatesh, S. (2009) · Artificial Intelligence · doi:10.1016/j.artint.2008.12.005 · Cited by 115
“Both the inference and learning tasks for the HSMM are again similar to the HMM and have been discussed in various papers [17,20,21,34,43] for different state duration probabilistic models.”
MethodSelf-citationLearning to detect user activity and availability from a variety of sensor data
Mühlenbrock, M., Brdiczka, O., Snowdon, D., & Meunier, J.-L. (2004) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom.2004.1276841 · Cited by 85
“As a prominent example, an approach based on hierarchical hidden Markov models has been developed to learn the hierarchical structure of sequences of human actions [11].”
Method(2004) · Deakin Research Online (Deakin University) · Cited by 82
Self-citationPREDICTING INHABITANT ACTION USING ACTION AND TASK MODELS WITH APPLICATION TO SMART HOMES
Rao, S., & Cook, D. J. (2004) · International Journal of Artificial Intelligence Tools · doi:10.1142/s0218213004001533 · Cited by 69
View-Invariant Human Activity Recognition Based on Shape and Motion Features
Niu, F., & Abdel-Mottaleb, M. S. (2005) · IEEE International Symposium on Multimedia Software Engineering (MSE) · doi:10.1109/mmse.2004.88 · Cited by 67
Detecting and discriminating behavioural anomalies
Loy, C. C., Xiang, T., & Gong, S. (2010) · Pattern Recognition · doi:10.1016/j.patcog.2010.07.023 · Cited by 67
“HHMM is chosen because it is effective in modelling different stochastic levels and length scales that present in a complex behaviour [41] [22].”
BackgroundHMM-Based Segmentation and Recognition of Human Activities from Video Sequences
Niu, F., & Abdel-Mottaleb, M. S. (2005) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2005.1521545 · Cited by 65
Activity knowledge transfer in smart environments
Rashidi, P., & Cook, D. J. (2011) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2011.02.007 · Cited by 72
“Markov models [10] and their variations such as hierarchical hidden Markov models (HHMM) [20] recently have been quite popular for recognizing activities.”
Hierarchical Activity Recognition Using Automatically Clustered Actions
van Kasteren, T. L. M., Englebienne, G., & Kröse, B. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-25167-2_9 · Cited by 59
“Their results show that these models perform well in recognizing several cooking related activities [5].”
BackgroundReducing the Calibration Effort for Location Estimation Using Unlabeled Samples
Chai, X., & Yang, Q. (2005) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom.2005.34 · Cited by 55
“In pervasive computing, HMM and its variation have been successfully used in tracking and recognizing human activities [10].”
MethodActivity recognition for health monitoring elderly using temporal probabilistic models
van Kasteren, T. L. M. (2011) · UvA-DARE (University of Amsterdam) · Cited by 47
Fast Activity Detection: Indexing for Temporal Stochastic Automaton-Based Activity Models
Albanese, M., Pugliese, A., & Subrahmanian, V. S. (2011) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2011.246 · Cited by 35
“In this paper, we propose a temporal probabilistic graph so that the elapsed time between observations also plays a role in defining whether a sequence of observations constitutes an activity.”
BackgroundA Reconfigurable HMM for Activity Recognition
Hasan, M. K., Rubaiyeat, H. A., Lee, Y.-K., & Lee, S. (2008) · International Conference on Advanced Communication Technology · doi:10.1109/icact.2008.4493886 · Cited by 33
“Several approaches have been found in mobility based activity detection, such as Hierarchical HMM [ 6 ], Bayes Filter [7], Dynamic Bayesian Network [8], Naive Bayes [9] etc.”
MethodMulti-modal emotive computing in a smart house environment
Moncrieff, S., Venkatesh, S., WEST, G. A. W., & Greenhill, S. (2006) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2006.07.003 · Cited by 33
“[2,3,13–15].”
Self-citationFormation of Learning Groups by using Learner Profiles and Context Information
Muehlenbrock, M. (2005) · Cited by 26
Integration of IoT Energy Management System with Appliance and Activity Recognition
Lai, C., Lai, Y.-H., Yang, L. T., & Chao, H. (2012) · IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) · doi:10.1109/greencom.2012.20 · Cited by 25
“In aspect of data collection, some systems obtain nearby data with sensors [6-11] and some deal with images taken by video devices [12-14].”
BackgroundIntent Inference and Syntactic Tracking with GMTI Measurements
Wang, A., Krishnamurthy, V., & Balaji, B. (2011) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2011.6034667 · Cited by 23
“In addition, in video surveillance, hierarchical hidden Mark ov model is applied to track sequences of human actions [20], and it can be shown that the hierarchical hidde n Markov model is a special case of SCFG [21].”
MethodAicha, A. N., Englebienne, G., & Kröse, B. (2013) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2494091.2497283 · Cited by 20
“Different kinds of methods like Hidden Markov Models (HMM) [11], hierarchical hidden Markov model (HHMM) [6], Switching hidden semi-Markov models (SHSMM) [2], Rao-Blackwellised particle filter [9] have been used for modelling and inference of the ADLs of a single person.”
MethodSimilarity measure for anomaly detection and comparing human behaviors
Anderson, D. T., Ros, M., Keller, J. M., Cuéllar, M. P., Popescu, M., Delgado‐Rodríguez, M., & Vila, M. A. (2012) · International Journal of Intelligent Systems · doi:10.1002/int.21544 · Cited by 18
Predicting Task Intent From Surface Electromyography Using Layered Hidden Markov Models
Razin, Y. S., Pluckter, K., Ueda, J., & Feigh, K. M. (2017) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2017.2662741 · Cited by 19
“for activity recognition, they have been limited to using visual data from video decomposition [7]–[10].”
MethodActive-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.”
BackgroundScalable Detection of Cyber Attacks
Albanese, M., Jajodia, S., Pugliese, A., & Subrahmanian, V. S. (2011) · Communications in computer and information science · doi:10.1007/978-3-642-27245-5_4 · Cited by 17
“[8] use Hierarchical HMMs to learn probabilities of sequences of activities.”
MethodA unified approach to the recognition of complex actions from sequences of zone-crossings
Sanromà, G., Patino, L., Burghouts, G. J., Klamer Schutte, B., & Ferryman, J. M. (2014) · Image and Vision Computing · doi:10.1016/j.imavis.2014.02.005 · Cited by 15
“Some examples of these approaches are Hierarchical Hidden Markov Models (HHMM) [9–12] and Syntactic methods [13–18].”
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
Self-citationDuration Abnormality Detection in Sequences of Human Activity
Lühr, S., Venkatesh, S., WEST, G. A. W., & Bui, H. (2004) · Deakin Research Online (Deakin University) · Cited by 14
Self-citationAicha, A. N., Englebienne, G., & Kröse, B. (2012) · International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) · doi:10.1145/2413097.2413112 · Cited by 10
“Di.erent kinds of methods like Hidden Markov Models (HMM) [14], hierarchical hidden Markov model (HHMM) [10], Switching hidden semi-Markov models (SHSMM) [2], Rao-Blackwellised particle .lter [12] have been used for modelling and inference of the ADLs of a single person.”
MethodForward-Backward Activation Algorithm for Hierarchical Hidden Markov Models
Wakabayashi, K., & Miura, T. (2012) · neural information processing systems · Cited by 8
PASS: A Parallel Activity-Search System
Pugliese, A., Subrahmanian, V. S., Thomas, C., & Molinaro, C. (2013) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2013.171 · Cited by 8
“THERE are many applications where there is a criticalneed to identify the activities that are going on in a stream of observation data.”
BackgroundMahmoud, S. M., Lotfi, A., & Langensiepen, C. S. (2010) · International Conference on Intelligent Environments (IE) · doi:10.1109/ie.2010.18 · Cited by 8
Lavania, C., Thulasidasan, S., LaMarca, A., Scofield, J., & Bilmes, J. (2016) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2971648.2971716 · Cited by 8
“There have been other works that have explored the use of HHMMs and other hierarchical and temporal models, such as [39, 36, 49].”
BackgroundResearch on Human Motion Recognition Based on Wi-Fi and Inertial Sensor Signal Fusion
Shu, Y., Chen, C., Shu, K.-I., & Zhang, H. (2018) · IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) · doi:10.1109/smartworld.2018.00110 · Cited by 6
“Nguyen and Venkatesh used a hierarchical hidden Markov model (HHMM) to identify complex human motion [21], [22].”
MethodDistributed activity recognition using key sensors
Sarkar, A. M. J., Hasan, K., Lee, Y.-K., Lee, S., & Zabir, S. M. S. (2009) · International Conference on Advanced Communication Technology · Cited by 5
Human Action Recognition for Home Sensor Network
Gu, Y., & Yuan, C. (2012) · Lecture notes in electrical engineering · doi:10.1007/978-3-642-34531-9_68 · Cited by 3
Mapping of Activity Recognition as a Distributed Inference Problem in Sensor Network.
Hasan, M. K., Rubaiyeat, H. A., Lee, Y.-K., & Lee, S. (2008) · Cited by 4
Detection and Classification of Human Movements in Video Scenes
Hochuli, A. G., Oliveira, L. S., Britto, A. S., & Koerich, A. L. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-77129-6_58 · Cited by 4
“Besides the need of a more efficient tool in the security area, the detection of non-conventional events in video scenes could be used in other contexts, such as: to detect when an elderly people has an accident inside his/her house [1,2], non-conventional activities in an office, transit infractions [3].”
MethodMAGIC: A Multi-Activity Graph Index for Activity Detection
Albanese, M., Pugliese, A., Subrahmanian, V. S., & Udrea, O. (2007) · IEEE International Conference on Information Reuse and Integration (IRI) · doi:10.1109/iri.2007.4296632 · Cited by 4
“Models of activities that account for such uncertainty have been devised in various communities and are based on context free grammars [8, 9], graphical models [4, 6] and stochastic automata [1].”
BackgroundIdentifying Tasks and Predicting Action in Smart Homes using Unlabeled Data
Rao, S., & Cook, D. J. (2003) · Cited by 4
Learning Hierarchical Models of Complex Daily Activities from Annotated Videos
Tayyub, J., Hawasly, M., Hogg, D., & Cohn, A. G. (2018) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2018.00182 · Cited by 4
“[11] were amongst the first to propose a hierarchical extension to the traditional HMM to recognise behavioural patterns.”
BackgroundQian, K., Gao, G., Fang, F., & Zhang, L. (2016) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm.2016.7606998 · Cited by 3
“Keywords—Activity recognition; RGB-D; Dynamic Time Warping; Gaussian Mixture Model; Service Robot I. INTRODUCTION Activity in Daily life (ADL) usually includes common action in daily life such as dialing phone, drinking water, taking medicine and et.al.”
BackgroundLearning an activity-based semantic scene model
Makris, D. (2004) · OpenGrey (Institut de l'Information Scientifique et Technique) · Cited by 3
Semantic Video Content Analysis
Albanese, M., Turaga, P. K., Chellappa, R., Pugliese, A., & Subrahmanian, V. S. (2010) · Studies in computational intelligence · doi:10.1007/978-3-642-12900-1_6 · Cited by 2
“[16] use Hierarchical HMMs to learn the probabilistic nature of simple sequences of activities.”
MethodTopology Estimation of Hierarchical Hidden Markov Models for Language Models
Wakabayashi, K., & Miura, T. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-13881-2_13 · Cited by 2
“There have been some studies to show effectiveness of HHMM description capability in several domains[ 5 ].”
BackgroundHuman Action Recognition by Principal Component Analysis of Motion Curves
Chivers, D. S. (2012) · Journal of Bioresource Management · Cited by 2
Modeling and simulation for user assistance in smart environments
Steiniger, A., & Uhrmacher, A. M. (2010) · Winter Simulation Conference · doi:10.1109/wsc.2010.5679138 · Cited by 1
“Various extensions to the basic HMM formalism exist that improve the prediction accuracy and expressiveness of the formalism, such as task-based Markov models (Rao and Cook 2003) and hierarchical hidden Markov models (L¨ uhr et al. 2003).”
MethodSpotting Human Activities and Gestures in Continuous Data Streams
Zinnen, A. (2009) · Technischen Universität Darmstadt · doi:10.26083/tuprints-00001983 · Cited by 2
Phung, D., Bui, H., & Venkatesh, S. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-27868-9_127 · Cited by 1
“The HHMM is also applied in other domains other than multimedia such as in hand-written recognition [14], robot navigation [18], behaviour recognition [19] and information retrieval [20].”
Self-citationA Unified Stochastic Architecture for Spoken Dialogue Systems
Lamont, O., & Mann, G. A. (2003) · Lecture notes in computer science · doi:10.1007/978-3-540-24581-0_77 · Cited by 1
“These areas include: language modelling [11], [12], optical character recognition [11], task analysis [ 13 ], robot navigation [14], video analysis [15], gene identification [16], [12] and information extraction [12].”
BackgroundAn Efficient Parallel Processing Technique For Large Text Files
Jyothi, B. R., & Mohan, A. K. (2015)
Detection of non-conventional events on video scenes
Hochuli, A. G., Britto, A. S., & Koerich, A. L. (2007) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2007.4414089
“In the former, most of the approaches employ Markov process and state transition functions [1], hidden Markov models [3] and hierarchical hidden Markov models [2] to model categories of non-conventional events inside pre-defined environments.”
MethodModel-Based Guidance for Human-Intensive Processes
Christov, S. C. (2015) · ScholarWorks@UMassAmherst (University of Massachusetts Amherst) · doi:10.7275/6207031.0
Theory of Communication between Human and Humanoid Robot based on Embodied Symbol Model
Takano, W., Yamane, K., Sugihara, T., Yamamoto, K., & Nakamura, Y. (2010) · Journal of the Robotics Society of Japan · doi:10.7210/jrsj.28.735
Liouane, Z. (2018) · theses.fr (ABES) · doi:10.70675/9d639f14zd293z4a3azb413z7feac09687b1 · Cited by 1
Metadata
- Authors
- Luhr, S., Bui, H. H., Venkatesh, S., & West, G. A. W.
- Affiliations
- Curtin University (AU)
- Venue
- Proceedings of the First IEEE International Conference on Pervasive Computing and Communications, 2003. (PerCom 2003).
- Publisher
- IEEE Comput. Soc
- Published
- 2004-01-23
- Pages
- 416-422
- ISSN
- 2474-249X (ISSN-L)
- OpenAlex
- W2152177292
- Cited by
- 58
- References
- 10
- Citations by year
- 2021: 2 · 2018: 3 · 2017: 1 · 2016: 2 · 2015: 1 · 2014: 1 · 2013: 2 · 2012: 6
- FWCI
- 4.24
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Pervasive Computing and Communications (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Keywords
- human activity recognition, hierarchical hidden Markov models, elderly care, home monitoring, probabilistic learning, home activities
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.