Adversarial Multi-view Networks for Activity Recognition
Open accessThe DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.
Abstract
Human activity recognition (HAR) plays an irreplaceable role in various applications and has been a prosperous research topic for years. Recent studies show significant progress in feature extraction (i.e., data representation) using deep learning techniques. However, they face significant challenges in capturing multi-modal spatial-temporal patterns from the sensory data, and they commonly overlook the variants between subjects. We propose a Discriminative Adversarial MUlti-view Network (DAMUN) to address the above issues in sensor-based HAR. We first design a multi-view feature extractor to obtain representations of sensory data streams from temporal, spatial, and spatio-temporal views using convolutional networks. Then, we fuse the multi-view representations into a robust joint representation through a trainable Hadamard fusion module, and finally employ a Siamese adversarial network architecture to decrease the variants between the representations of different subjects. We have conducted extensive experiments under an iterative left-one-subject-out setting on three real-world datasets and demonstrated both the effectiveness and robustness of our approach.
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
“Using Wasserstein GAN and Siamese networks, they demonstrate the ability to generalize to new subjects without sacrificing performance.”
From Past, Present, and Future of Sensor-based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task (2025) · cites this paper as [10]
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 2×
“…segment; 2) concatenate-based fusion, which gets the final representation by concatenating representations of all views; 3) self-attention based fusion, which uses the self-attention mechanism [46] to calculate the importance of each view and merges the re-weighted sub-representations by summing.”
BackgroundHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 2×
“Such studies [14, 39, 40, 47] typically use deep neural networks, e.g., Convolution Neural Networks (CNN) [37], Long-Short Term Memory (LSTM) [23], as the feature extractor to learn representations of the input sensory segments automatically; then, they map the representations to corresponding…”
MethodGAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
Hearst, M. A., Dumais, S. T., Osuna, E., Platt, J., & Scholkopf, B. (1998) · IEEE Intelligent Systems and their Applications · doi:10.1109/5254.708428 · Cited by 7,243 · cited 1×
“To verify the overall performance of the proposed DAMUN model, we compare our model with the following baseline and state-of-the-arts: • SVM [22]: the traditional support vector machine (SVM) with the radial basis function (RBF) kernel.”
Method(2017) · International Conference on Machine Learning · Cited by 6,382
Proceedings of the 19th International Joint Conference on Artificial Intelligence
Pujol, J. M., Delgado, J., Ramon Sangüesa, A., & Flache, A. (2005) · International Joint Conference on Artificial Intelligence · Cited by 5,771
Siamese Neural Networks for One-shot Image Recognition
Koch, G. E., Zemel, R. S., & Salakhutdinov, R. (2015) · Cited by 3,740
Activity Recognition from User-Annotated Acceleration Data
Bao, L., & Intille, S. S. (2004) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-24646-6_1 · Cited by 3,147 · cited 2×
“Most early studies in the area aim to recognize human activities from solely accelerometer signals [6, 19, 34].”
BackgroundMethodActivity recognition using cell phone accelerometers
Kwapisz, J. R., Weiss, G. M., & Moore, S. A. (2011) · ACM SIGKDD Explorations Newsletter · doi:10.1145/1964897.1964918 · Cited by 2,912 · cited 2×
“Most early studies in the area aim to recognize human activities from solely accelerometer signals [6, 19, 34].”
BackgroundMethodDeep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Ordóñez, F., & Roggen, D. (2016) · Sensors · doi:10.3390/s16010115 · Cited by 2,761 · cited 11×
“Based on this observation, Murahari and Plötz [39] extend the DeepConvLSTM [40] by adding the temporal attention module after the LSTM layer.”
BackgroundMethodInfluentialActivityNet: A large-scale video benchmark for human activity understanding
Heilbron, F. C., Escorcia, V., Ghanem, B., & Niebles, J. C. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298698 · Cited by 2,578 · cited 1×
“Current human activity recognition schemes are severely limited by the variability and complexity of the activities, Heilbron et.al [9] introduce a large scale video benchmark for human activity understanding that contains 203 simple and complex activities to ease the problem.”
BackgroundModeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
Lai, G., Chang, W.-C., Yang, Y., & Liu, H. (2018) · The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval · doi:10.1145/3209978.3210006 · Cited by 2,152 · cited 1×
“Let there be N potential activities to be recognized, 𝐶 = { 𝑐 1 ,𝑐 2 , ...,𝑐 𝑁 } , the purpose of HAR is to learn a function, F ( 𝑺𝒆𝒈 , •) , to infer the correct activity label for the given segment 𝑆𝑒𝑔 , where • represents all the parameters to be learned during the training process.”
Background(2013) · RECERCAT (Consorci de Serveis Universitaris de Catalunya) · Cited by 1,959
A tutorial on human activity recognition using body-worn inertial sensors
Bulling, A., Blanke, U., & Schiele, B. (2014) · ACM Computing Surveys · doi:10.1145/2499621 · Cited by 1,668 · cited 1×
“Let 𝑀 be the total number of sensors embedded in multiple devices and 𝑠 𝑖,𝑡 be the reading of sensor 𝑖 ( Following the standard HAR procedure [8], we divide the multi-variate sensory streams into segments with a fixed-size sliding window.”
MethodIntroducing a New Benchmarked Dataset for Activity Monitoring
Reiss, A., & Stricker, D. (2012) · 2012 16th International Symposium on Wearable Computers · doi:10.1109/iswc.2012.13 · Cited by 1,456 · cited 2×
“Specially, current works employ an impaired LOSO setting which only test the model in one selected subject (for example, [38, 39, 43, 49] use subject six for testing in the PAMAP2 dataset [45]).”
BackgroundMethodSpatial as Deep: Spatial CNN for Traffic Scene Understanding
Pan, X., Shi, J., Luo, P., Wang, X., & Tang, X. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12301 · Cited by 1,177
Self-citationThe Opportunity challenge: A benchmark database for on-body sensor-based activity recognition
Chavarriaga, R., Sagha, H., Calatroni, A., Digumarti, S. T., Tröster, G., Millán, J. D. R., & Roggen, D. (2013) · Pattern Recognition Letters · doi:10.1016/j.patrec.2012.12.014 · Cited by 742 · cited 1×
“To further examine the efficacy of DAMUN on sporadic activities, we additionally carry out an experiment with the Opportunity dataset [11] containing three subjects and 17 sporadic gestures (exclude the NULL class).”
MethodDeep Learning for Sensor-based Human Activity Recognition
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2022) · ACM Computing Surveys · doi:10.1145/3447744 · Cited by 690 · cited 1×
“Compared with vision-based, sensor-based approaches own some unique merits in terms of pervasiveness, low computational complexity and better privacy preserving [15].”
BackgroundSelf-citationHuman Activity Recognition Using Wearable Sensors by Deep Convolutional Neural Networks
Jiang, W., & Yin, Z. (2015) · Proceedings of the 23rd ACM international conference on Multimedia · doi:10.1145/2733373.2806333 · Cited by 676 · cited 2×
“Vision-based solutions have been extensively studied in the past decades.”
BackgroundDeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing
Yao, S., Hu, S., Zhao, Y., Zhang, A., & Abdelzaher, T. (2017) · Proceedings of the 26th International Conference on World Wide Web · doi:10.1145/3038912.3052577 · Cited by 667 · cited 1×
“In this section, we first briefly introduce the general background of human activity recognition and then elaborate on deep learning methods for sensor-based HAR.”
BackgroundDeep, Convolutional, and Recurrent Models for Human Activity Recognition Using Wearables
Hammerla, N. Y., Halloran, S., & Ploetz, T. (2016) · arXiv · doi:10.48550/arxiv.1604.08880 · Cited by 606 · cited 4×
“Instead of using a large window size (5 seconds) for PAMAP2 (as in [18, 20]), we set each window to contain 20 time points for the three datasets, resulting in window lengths of 0.”
BackgroundMethodInfluentialmHealthDroid: A Novel Framework for Agile Development of Mobile Health Applications
Banos, O., Garcia, R., Holgado-Terriza, J. A., Damas, M., Pomares, H., Rojas, I., Saez, A., & Villalonga, C. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-13105-4_14 · Cited by 583 · cited 1×
“Finally, we evaluate the performance of our proposed method in comparison with state-of-the-art and via ablation studies.”
MethodEnsembles of Deep LSTM Learners for Activity Recognition using Wearables
Guan, Y., & Plötz, T. (2017) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3090076 · Cited by 511 · cited 19×
“It’s mean recognition accuracy achieves 3.35%, 2.94%, and 2.48% absolute improvements over the best SOTA in the MHEALTH, PAMAP2 and UCIDSADS datasets, respectively.”
BackgroundMethodResultInfluentialDiscovery of activity patterns using topic models
Huynh, T., Fritz, M., & Schiele, B. (2008) · Proceedings of the 10th international conference on Ubiquitous computing · doi:10.1145/1409635.1409638 · Cited by 442 · cited 1×
“While several datasets are publicly available for HAR, many of them only contain a few subjects (e.g. the Ubicomp 08 dataset [24] only has one subject) or human activities (e.g. the UCI dataset [2] only contains six activities).”
BackgroundA Review on Video-Based Human Activity Recognition
Ke, S.-R., Thuc, H., Lee, Y.-J., Hwang, J.-N., Yoo, J.-H., & Choi, K.-H. (2013) · Computers · doi:10.3390/computers2020088 · Cited by 439 · cited 1×
“Ke et.al [30] provide a survey about the vision based human activity recognition.”
BackgroundBarshan, B., & Yuksek, M. C. (2014) · The Computer Journal · doi:10.1093/comjnl/bxt075 · Cited by 346 · cited 1×
“• UCIDSADS Dataset 3 The UCIDSADS Dataset [7] was specially devised for daily and sports activities.”
MethodDeep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2020) · arXiv · doi:10.48550/arxiv.2001.07416 · Cited by 314 · cited 1×
“Compared with vision-based, sensor-based approaches own some unique merits in terms of pervasiveness, low computational complexity and better privacy preserving [15].”
BackgroundSelf-citationSTG2Seq: Spatial-Temporal Graph to Sequence Model for Multi-step Passenger Demand Forecasting
Bai, L., Yao, L., Kanhere, S. S., Wang, X., & Sheng, Q. Z. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/274 · Cited by 288
Self-citationAttnSense: Multi-level Attention Mechanism For Multimodal Human Activity Recognition
Ma, H., Li, W., Zhang, X., Gao, S., & Lu, S. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/431 · Cited by 266 · cited 6×
“The normalized segments are fed into the network directly without sophisticated operations like hand-crafted feature extraction or Fourier transformation [38].”
BackgroundMethodResultInfluentialOn the use of ensemble of classifiers for accelerometer-based activity recognition
Catal, C., Tufekci, S., Pirmit, E., & Kocabag, G. (2015) · Applied Soft Computing · doi:10.1016/j.asoc.2015.01.025 · Cited by 240 · cited 1×
“The work [10, 34, 50] utilizes subject-dependent protocols and can easily achieve high recognition accuracy because of the information leakage problem (samples in the training set and testing set may come from neighboring windows and contain extremely similar information).”
MethodA Comprehensive Analysis on Wearable Acceleration Sensors in Human Activity Recognition
Janidarmian, M., Roshan Fekr, A., Radecka, K., & Zilic, Z. (2017) · Sensors · doi:10.3390/s17030529 · Cited by 217 · cited 1×
“Besides the most frequently used time-domain features (e.g., mean, variance, and skewness) and frequency domain features (e.g., power spectral density) [27], a few methods endeavor to design new features containing temporal and structural information.”
MethodZeng, M., Gao, H., Yu, T., Mengshoel, O. J., Langseth, H., Lane, I., & Liu, X. (2018) · Proceedings of the 2018 ACM International Symposium on Wearable Computers · doi:10.1145/3267242.3267286 · Cited by 185 · cited 7×
“Most recent studies [19, 35, 38–40, 43, 49] deploy subject-independent settings in the evaluation to avoid the information leakage problem and evaluate the models’ generalization ability on new subjects.”
BackgroundMethodResultInfluentialOn attention models for human activity recognition
Murahari, V. S., & Plötz, T. (2018) · Proceedings of the 2018 ACM International Symposium on Wearable Computers · doi:10.1145/3267242.3267287 · Cited by 157 · cited 6×
“Based on this observation, Murahari and Plötz [39] extend the DeepConvLSTM [40] by adding the temporal attention module after the LSTM layer.”
BackgroundMethodInfluentialEduSense: Practical Classroom Sensing at Scale
Ahuja, K., Kim, D., Xhakaj, F., Varga, V., Xie, A., Zhang, S., Townsend, J. E., Harrison, C., Ogan, A., & Agarwal, Y. (2019) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3351229 · Cited by 145 · cited 1×
“Ahuja et.al [1] develop a comprehensive sensing system that detects the actions and interactions between instructors and students based on visual and audio signals.”
BackgroundHammerla, N. Y., Kirkham, R., Andras, P., & Ploetz, T. (2013) · Proceedings of the 2013 International Symposium on Wearable Computers · doi:10.1145/2493988.2494353 · Cited by 138 · cited 1×
“For example, Hammerla et al. [21] propose the Empirical Cumulative Density Function (ECDF) feature to preserve the spatial information of the signal frames.”
BackgroundPeng (2018) · doi:10.1145/3214277 · Cited by 134 · cited 2×
“Based on this framework, Peng et al. [42] propose to divide human activities into simple activities and complex activities, which are closely linked.”
MethodGymCam: Detecting, Recognizing and Tracking Simultaneous Exercises in Unconstrained Scenes
Khurana, R., Ahuja, K., Yu, Z., Mankoff, J. C., Harrison, C., & Goel, M. (2018) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3287063 · Cited by 97 · cited 1×
“For instance, Khurana et.al [31] present a vision-based system to track exercise of multiple users in the gym environment with a single camera.”
BackgroundSelf-citationGuo, H., Chen, L., Peng, L., & Chen, G. (2016) · Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing · doi:10.1145/2971648.2971708 · Cited by 83 · cited 3×
“In this regard, we additionally compare the mean F-score ( 𝐹 ) against the weighted F-score to enhance our experimental results analysis and report the classification confusion matrix (in Section 5.8) to investigate the performance of each class and thus gain deeper insights into the model.”
BackgroundMethodInfluentialMobile activity recognition for a whole day: recognizing real nursing activities with big dataset
Inoue, S., Ueda, N., Nohara, Y., & Nakashima, N. (2015) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2750858.2807533 · Cited by 59 · cited 1×
“Among the related techniques, sensor-based HAR plays an irreplaceable role in many scenarios such as elderly assisted living, sports monitoring, and surgical operation recording, given its easiness of deployment and better privacy [25].”
BackgroundA Novel Distribution-Embedded Neural Network for Sensor-Based Activity Recognition
Qian, H., Pan, S. J., Da, B., & Miao, C. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/779 · Cited by 56 · cited 4×
“Most recent studies [19, 35, 38–40, 43, 49] deploy subject-independent settings in the evaluation to avoid the information leakage problem and evaluate the models’ generalization ability on new subjects.”
BackgroundMethodResultInfluentialDistributionally Robust Semi-Supervised Learning for People-Centric Sensing
Chen, K., Yao, L., Zhang, D., Chang, X., Long, G., & Wang, S. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33013321 · Cited by 49
Self-citationMulti-modality Sensor Data Classification with Selective Attention
Zhang, X., Yao, L., Huang, C., Wang, S., Tan, M., Long, G., & Wang, C. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/432 · Cited by 41
Self-citationMulti-agent Attentional Activity Recognition
Chen, K., Yao, L., Zhang, D., Guo, B., & Yu, Z. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/186 · Cited by 41
Self-citationChen, K., Yao, L., Wang, X., Zhang, D., Gu, T., Yu, Z., & Yang, Z. (2018) · 2018 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489767 · Cited by 36
Self-citationKwon, H., Abowd, G. D., & Plötz, T. (2018) · Proceedings of the 2018 ACM International Symposium on Wearable Computers · doi:10.1145/3267242.3267258 · Cited by 35 · cited 3×
“The main tasks of sensor-based HAR involve partitioning multi-variate data streams from one or more sensors into segments and assigning an appropriate activity label to each segment [43].”
BackgroundMethodVision2Sensor: Knowledge Transfer Across Sensing Modalities for Human Activity Recognition
Radu, V., & Henne, M. (2019) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3351242 · Cited by 33 · cited 1×
“Considering the complexity associated with labeling the sensory data, Radu and Henne [44] propose to annotate the sensor data with video and computer vision classifiers automatically.”
MethodFávero, L. P. L., Belfiore, P., & Souza, R. D. F. (2023) · Elsevier eBooks · doi:10.1016/b978-0-12-824271-1.00032-9 · Cited by 23
Research works printed but not linked: 11
- Arjovsky Martin, 2017, International conference on machine learning. 214--223
- Chen Kaixuan, 2019, Proceedings of the 28th International Joint Conference on Artificial Intelligence.
- Glorot Xavier, 2010, Proceedings of the thirteenth international conference on artificial intelligence and statistics. 249--256
- Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672--2680. Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672--2680.
- Hammerla Nils Y, 2016, Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. AAAI Press, 1533--1540
- Ioffe Sergey, 2015, International Conference on Machine Learning. 448--456
- Jordao Artur, 2018, Jessica Sena, and William Robson Schwartz.
- Kingma Diederik P, 2014, Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 · arXiv
- Koch Gregory, ICML deep learning workshop
- LeCun Yann, 2015, Deep learning. nature 521, 7553
- Yang Jianbo, 2015, Twenty-Fourth International Joint Conference on Artificial Intelligence.
Cited by
Deep Learning for Sensor-based Human Activity Recognition
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2022) · ACM Computing Surveys · doi:10.1145/3447744 · Cited by 690
Self-citationDeep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2020) · arXiv · doi:10.48550/arxiv.2001.07416 · Cited by 314
Self-citationEssa, E., & Abdelmaksoud, I. R. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110867 · Cited by 113
Suh, S., Rey, V. F., & Lukowicz, P. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.110143 · Cited by 107
MM-Fit: Multimodal Deep Learning for Automatic Exercise Logging across Sensing Devices
Strömbäck, D., Huang, S., & Radu, V. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3432701 · Cited by 73
“user, adversarial networks have been used [3], which rely on Siamese networks to decrease the variants between the representations of different subjects.”
Method
Metadata
- Authors
- Bai, L., Yao, L., Wang, X., Kanhere, S. S., Guo, B., & Yu, Z.
- Affiliations
- UNSW Sydney (AU)
- University of Technology Sydney (AU)
- Northwestern Polytechnical University (CN)
- Venue
- Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Published
- 2020-06-15
- Volume
- 4
- Issue
- 2
- Pages
- 1-22
- ISSN
- 2474-9567 (ISSN-L)
- OpenAlex
- W3034851746
- Cited by
- 40
- References
- 47
- Citations by year
- 2026: 3 · 2025: 5 · 2024: 5 · 2023: 9 · 2022: 9 · 2021: 6 · 2020: 3
- FWCI
- 2.63
- Type
- journal article
- Language
- en
- Open access
- green
- hdl.handle.net
- Locations
- Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies (publishedVersion, public-domain)
- UTS ePRESS (University of Technology Sydney) (submittedVersion, other-oa)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Engineering › Biomedical Engineering › Gait Recognition and Analysis
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Keywords
- human activity recognition, multi-view feature extraction, adversarial learning, Siamese network, spatiotemporal patterns, sensor data, interindividual variability, wearable sensors, cross-subject generalization
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.