Action-Conditioned 3D Human Motion Synthesis with Transformer VAE
Open accessThe DOI matches its Crossref record; 76 of the 76 references it cites were found in a registry or an index.
Abstract
We tackle the problem of action-conditioned generation of realistic and diverse human motion sequences. In contrast to methods that complete, or extend, motion sequences, this task does not require an initial pose or sequence. Here we learn an action-aware latent representation for human motions by training a generative variational autoencoder (VAE). By sampling from this latent space and querying a certain duration through a series of positional encodings, we synthesize variable-length motion sequences conditioned on a categorical action. Specifically, we design a Transformer-based architecture, ACTOR, for encoding and decoding a sequence of parametric SMPL human body models estimated from action recognition datasets. We evaluate our approach on the NTU RGB+D, HumanAct12 and UESTC datasets and show improvements over the state of the art. Furthermore, we present two use cases: improving action recognition through adding our synthesized data to training, and motion denoising. Code and models are available on our project page [53].
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
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
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
Labaca-Castro, R. (2023) · Machine Learning under Malware Attack · doi:10.1007/978-3-658-40442-0_9 · Cited by 19,272
GAN(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
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
Yan, S., Xiong, Y., & Lin, D. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12328 · Cited by 5,410
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
Mildenhall, B., Srinivasan, P. P., Tancik, M., Barron, J. T., Ramamoorthi, R., & Ng, R. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_24 · Cited by 5,351
Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., & J, B. M. (2015) · ACM Transactions on Graphics · doi:10.1145/2816795.2818013 · Cited by 3,734 · cited 3×
“Consequently, without loss of generality, we employ the SMPL body model [46], which is a disentangled body representation (similar to recent models [53, 55, 58, 68]).”
MethodInfluentialSelf-citationHuman3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments
Ionescu, C., Papava, D., Olaru, V., & Sminchisescu, C. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.248 · Cited by 3,653 · cited 1×
“A challenge specific to our action-condition generation problem is that there exists limited motion capture (MoCap) data paired with distinct action labels, typically on the order of 10 categories [29, 59].”
BackgroundGaussian Error Linear Units (GELUs)
Hendrycks, D., & Gimpel, K. (2016) · arXiv · doi:10.48550/arxiv.1606.08415 · Cited by 3,537
(2017) · International Conference on Learning Representations · Cited by 3,248
NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
Shahroudy, A., Liu, J., Ng, T.-T., & Wang, G. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.115 · Cited by 3,148
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L.-Y., & Kot, A. C. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2916873 · Cited by 1,818
The Visual Analysis of Human Movement: A Survey
Gavrila, D. M. (1999) · Computer Vision and Image Understanding · doi:10.1006/cviu.1998.0716 · Cited by 1,782
Expressive Body Capture: 3D Hands, Face, and Body From a Single Image
Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A. A., Tzionas, D., & Black, M. J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01123 · Cited by 1,781 · cited 1×
“Consequently, without loss of generality, we employ the SMPL body model [43], which is a disentangled body representation (similar to recent models [50, 51, 54, 64]).”
MethodSelf-citationAMASS: Archive of Motion Capture As Surface Shapes
Mahmood, N., Ghorbani, N., Troje, N. F., Pons-Moll, G., & Black, M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00554 · Cited by 1,323
Self-citationOn the Continuity of Rotation Representations in Neural Networks
Zhou, Y., Barnes, C., Lu, J., Yang, J., & Li, H. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00589 · Cited by 1,255
Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear UnitsPreprint
Hendrycks, D., & Gimpel, K. (2016) · arXiv (Cornell University) · Cited by 1,156
MoCoGAN: Decomposing Motion and Content for Video Generation
Tulyakov, S., Liu, M.-Y., Yang, X., & Kautz, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00165 · Cited by 1,076
Romero (2017) · doi:10.1145/3130800.3130883 · Cited by 1,056
VIBE: Video Inference for Human Body Pose and Shape Estimation
Kocabas, M., Athanasiou, N., & Black, M. J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00530 · Cited by 1,031
Self-citationOn Human Motion Prediction Using Recurrent Neural Networks
Martinez, J., Black, M. J., & Romero, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.497 · Cited by 984
Self-citationRecurrent Network Models for Human Dynamics
Fragkiadaki, K., Levine, S., Felsen, P., & Malik, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.494 · Cited by 860
Simulating Humans: Computer Graphics, Animation, and Control
Badler, N. I., Phillips, C. B., & Webber, B. L. (1993) · Oxford University Press eBooks · doi:10.1093/oso/9780195073591.001.0001 · Cited by 751
A deep learning framework for character motion synthesis and editing
Holden, D., Saito, J., & Komura, T. (2016) · ACM Transactions on Graphics · doi:10.1145/2897824.2925975 · Cited by 655
AI Choreographer: Music Conditioned 3D Dance Generation with AIST++
Li, R., Yang, S., Ross, D. A., & Kanazawa, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01315 · Cited by 553 · cited 1×
“Very recently, [39] presents a Transformer-based method for dance generation conditioned on music and past motion.”
MethodPhase-functioned neural networks for character control
Holden, D., Komura, T., & Saito, J. (2017) · ACM Transactions on Graphics · doi:10.1145/3072959.3073663 · Cited by 546
Learning 3D Human Dynamics From Video
Kanazawa, A., Zhang, J. Y., Felsen, P., & Malik, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00576 · Cited by 531
Model-based image analysis of human motion using constraint propagation
O'Rourke, J., & Badler, N. I. (1980) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.1980.6447699 · Cited by 432
Accelerating 3D deep learning with PyTorch3D
Johnson, J., Ravi, N., Reizenstein, J., Novotny, D., Tulsiani, S., Lassner, C., & Branson, S. (2020) · SIGGRAPH Asia 2020 Courses · doi:10.1145/3415263.3419160 · Cited by 413
Action2Motion: Conditioned Generation of 3D Human Motions
Guo, C., Zuo, X., Wang, S., Zou, S., Sun, Q., Deng, A., Gong, M., & Cheng, L. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413635 · Cited by 398
GHUM & GHUML: Generative 3D Human Shape and Articulated Pose Models
Xu, H., Bazavan, E. G., Zanfir, A., Freeman, W. T., Sukthankar, R., & Sminchisescu, C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00622 · Cited by 347
HP-GAN: Probabilistic 3D Human Motion Prediction via GAN
Barsoum, E., Kender, J., & Liu, Z. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00191 · Cited by 322
Neural state machine for character-scene interactions
Starke, S., Zhang, H., Komura, T., & Saito, J. (2019) · ACM Transactions on Graphics · doi:10.1145/3355089.3356505 · Cited by 290
Language2Pose: Natural Language Grounded Pose Forecasting
Ahuja, C., & Morency, L.-P. (2019) · 2019 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2019.00084 · Cited by 271
Harvey, F. G., Yurick, M., Nowrouzezahrai, D., & Pal, C. (2020) · ACM Transactions on Graphics · doi:10.1145/3386569.3392480 · Cited by 266
Learning 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
Latent structured models for human pose estimation
Ionescu, C., Li, F., & Sminchisescu, C. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126500 · Cited by 258
STAR: Sparse Trained Articulated Human Body Regressor
Osman, A. A. A., Bolkart, T., & Black, M. J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58539-6_36 · Cited by 252
Self-citationDLow: Diversifying Latent Flows for Diverse Human Motion Prediction
Yuan, Y., & Kitani, K. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58545-7_20 · Cited by 249
Text2Action: Generative Adversarial Synthesis from Language to Action
Ahn, H., Ha, T., Choi, Y., Yoo, H., & Oh, S. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460608 · Cited by 197
Structured Prediction Helps 3D Human Motion Modelling
Aksan, E., Kaufmann, M., & Hilliges, O. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00724 · Cited by 193
We are More than Our Joints: Predicting how 3D Bodies Move
Zhang, Y., Black, M. J., & Tang, S. (2021) · 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/cvpr46437.2021.00338 · Cited by 186
Self-citationMoGlow: probabilistic and controllable motion synthesis using normalising flows
Henter, G. E., Alexanderson, S., & Beskow, J. (2020) · ACM Transactions on Graphics · doi:10.1145/3414685.3417836 · Cited by 176
Convolutional Sequence Generation for Skeleton-Based Action Synthesis
Yan, S., Li, Z., Xiong, Y., Yan, H., & Lin, D. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00449 · Cited by 176
QuaterNet: A Quaternion-based Recurrent Model for Human Motion
Pavllo, D., Grangier, D., & Auli, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.06485 · Cited by 174
A Recurrent Variational Autoencoder for Human Motion Synthesis
Habibie, I., Holden, D., Schwarz, J., Yearsley, J., & Komura, T. (2017) · Procedings of the British Machine Vision Conference 2017 · doi:10.5244/c.31.119 · Cited by 162
Context-Aware Human Motion Prediction
Corona, E., Pumarola, A., Alenya, G., & Moreno-Noguer, F. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00702 · Cited by 159
Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows
Zanfir, A., Băzăvan, E. G., Xu, H., Freeman, W. T., Sukthankar, R., & Sminchisescu, C. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58539-6_28 · Cited by 158
Deep Video Generation, Prediction and Completion of Human Action Sequences
Cai, H., Bai, C., Tai, Y., & Tang, C. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01216-8_23 · Cited by 157
3D Human Motion Estimation via Motion Compression and Refinement
Luo, Z., Golestaneh, S. A., & Kitani, K. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-69541-5_20 · Cited by 157
Holden, D., Kanoun, O., Perepichka, M., & Popa, T. (2020) · ACM Transactions on Graphics · doi:10.1145/3386569.3392440 · Cited by 143
Jiang, J., Xia, G., Carlton, D., Anderson, C. N., & Miyakawa, R. H. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054554 · Cited by 136
Synthetic Humans for Action Recognition from Unseen Viewpoints
Varol, G., Laptev, I., Schmid, C., & Zisserman, A. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01467-7 · Cited by 129
Self-citationInteractive character animation by learning multi-objective control
Lee, K., Lee, S., & Lee, J. (2018) · ACM Transactions on Graphics · doi:10.1145/3272127.3275071 · Cited by 117
Learning Statistical Models of Human Motion
Bowden, R. (2000) · Cited by 111
A Large-scale RGB-D Database for Arbitrary-view Human Action Recognition
Ji, Y., Xu, F., Yang, Y., Shen, F., Shen, H. T., & Zheng, W. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3240675 · Cited by 111
Spatio-Temporal Manifold Learning for Human Motions via Long-Horizon Modeling
Wang, H., Ho, E. S. L., Shum, H. P. H., & Zhu, Z. (2019) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2019.2936810 · Cited by 104
Human Motion Modeling using DVGANsPreprint
Lin, X., & Amer, M. R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.10652 · Cited by 101
Accelerating 3D Deep Learning with PyTorch3D
Ravi, N., Reizenstein, J., Novotný, D., Gordon, T., Lo, W., Johnson, J. M., & Gkioxari, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.08501 · Cited by 101
Single-Shot Motion Completion with TransformerPreprint
Duan, Y., Shi, T., Zou, Z., Lin, Y., Qian, Z., Zhang, B., & Yuan, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.00776 · Cited by 94
Transformer-based Conditional Variational Autoencoder for Controllable Story GenerationPreprint
Fang, L., Zeng, T., Liu, C., Bo, L., Dong, W., & Chen, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.00828 · Cited by 93
Dancing to MusicPreprint
Lee, H. Y., Yang, X.-D., Liu, M., Wang, T. C., Lu, Y., Yang, M., & Kautz, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.02001 · Cited by 75
Representing cyclic human motion using functional analysis
Ormoneit, D., Black, M. J., Hastie, T. J., & Kjellström, H. (2005) · Image and Vision Computing · doi:10.1016/j.imavis.2005.09.004 · Cited by 72
Self-citationVariational Transformers for Diverse Response GenerationPreprint
Lin, Z., Winata, G. I., Xu, P., Liu, Z., & Fung, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.12738 · Cited by 70
Learning to Generate Diverse Dance Motions with Transformer
Li, J., Yin, Y., Chu, H., Zhou, Y., Wang, T., Fidler, S., & Li, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.08171 · Cited by 69
Bayesian Adversarial Human Motion Synthesis
Zhao, R., Su, H., & Ji, Q. (2020) · 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/cvpr42600.2020.00626 · Cited by 68
3D Human Shape Reconstruction from a Polarization Image
Zou, S., Zuo, X., Qian, Y., Wang, S., Xu, C., Gong, M., & Cheng, L. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58568-6_21 · Cited by 60
Perpetual Motion: Generating Unbounded Human MotionPreprint
Zhang, Y., Black, M. J., & Tang, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.13886 · Cited by 45
Self-citationModeling Human Locomotion with Topologically Constrained Latent Variable Models
Urtasun, R., Fleet, D. J., & Lawrence, N. D. (2007) · Springer eBooks · doi:10.1007/978-3-540-75703-0_8 · Cited by 40
Variational Semi-Supervised Aspect-Term Sentiment Analysis via Transformer
Cheng, X., Xu, W., Wang, T., Chu, W., Huang, W., Chen, K., & Hu, J. (2019) · Conference on Computational Natural Language Learning · doi:10.18653/v1/k19-1090 · Cited by 38
Action2MotionPreprint
Guo, C., Zuo, X., Wang, S., Zou, S., Sun, Q., Deng, A., Gong, M., & Cheng, L. (2020) · arXiv (Cornell University) · Cited by 9
Cited by
Generating Diverse and Natural 3D Human Motions from Text
Guo, C., Zou, S., Zuo, X., Wang, S., Ji, W., Li, X., & Cheng, L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00509 · Cited by 575
MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model
Zhang, M., Cai, Z., Pan, L., Hong, F., Guo, X., Yang, L., & Liu, Z. (2022) · arXiv · doi:10.48550/arxiv.2208.15001 · Cited by 437
MotionDiffuse: Text-Driven Human Motion Generation With Diffusion Model
Zhang, M., Cai, Z., Pan, L., Hong, F., Guo, X., Yang, L., & Liu, Z. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3355414 · Cited by 424
Autonomous driving system: A comprehensive survey
Zhao, J., Zhao, W., Deng, B., Wang, Z., Zhang, F., Zheng, W., Cao, W., Nan, J., Lian, Y., & Burke, A. F. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122836 · Cited by 361
Executing your Commands via Motion Diffusion in Latent Space
Chen, X., Jiang, B., Liu, W., Huang, Z., Fu, B., Chen, T., & Yu, G. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01726 · Cited by 356
Metadata
- Authors
- Petrovich, M., Black, M. J., & Varol, G.
- Venue
- 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2021-10
- Pages
- 10965-10975
- OpenAlex
- W3153832461
- Cited by
- 493
- References
- 76
- FWCI
- 125.28
- Type
- conference paper
- Language
- en
- Open access
- green
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.