SV-RCNet: Workflow Recognition From Surgical Videos Using Recurrent Convolutional Network
The DOI matches its Crossref record; 48 of the 50 references it cites were found in a registry or an index.
Abstract
We propose an analysis of surgical videos that is based on a novel recurrent convolutional network (SV-RCNet), specifically for automatic workflow recognition from surgical videos online, which is a key component for developing the context-aware computer-assisted intervention systems. Different from previous methods which harness visual and temporal information separately, the proposed SV-RCNet seamlessly integrates a convolutional neural network (CNN) and a recurrent neural network (RNN) to form a novel recurrent convolutional architecture in order to take full advantages of the complementary information of visual and temporal features learned from surgical videos. We effectively train the SV-RCNet in an end-to-end manner so that the visual representations and sequential dynamics can be jointly optimized in the learning process. In order to produce more discriminative spatio-temporal features, we exploit a deep residual network (ResNet) and a long short term memory (LSTM) network, to extract visual features and temporal dependencies, respectively, and integrate them into the SV-RCNet. Moreover, based on the phase transition-sensitive predictions from the SV-RCNet, we propose a simple yet effective inference scheme, namely the prior knowledge inference (PKI), by leveraging the natural characteristic of surgical video. Such a strategy further improves the consistency of results and largely boosts the recognition performance. Extensive experiments have been conducted with the MICCAI 2016 Modeling and Monitoring of Computer Assisted Interventions Workflow Challenge dataset and Cholec80 dataset to validate SV-RCNet. Our approach not only achieves superior performance on these two datasets but also outperforms the state-of-the-art methods by a significant margin.
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
“Another line of work uses CV to recognize distinct phases of surgery during operations, towards developing context-aware computer assistance systems 126,127 .”
From Deep learning-enabled medical computer vision (2021) · cites this paper as [126]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 4×
“Specifically, we exploit the very deep residual network, the ResNet [21], to extract highly discriminative visual features from the video frames.”
BackgroundMethodInfluentialGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
A survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332
Learning Deep Features for Discriminative Localization
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.319 · Cited by 11,428 · cited 1×
“networks on an image and intercept the learned information of networks [37], [38].”
BackgroundCaffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077 · cited 1×
“Our framework is implemented with C++ and Python based on the Caffe [35] deep learning library, using a TITAN X GPU for acceleration.”
MethodShin, H.-C., Roth, H. R., Gao, M., Lu, L., Xu, Z., Nogues, I., Yao, J., Mollura, D., & Summers, R. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2528162 · Cited by 5,759
Long-term recurrent convolutional networks for visual recognition and description
Donahue, J., Hendricks, L. A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Darrell, T., & Saenko, K. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298878 · Cited by 5,228 · cited 2×
“HMM, we propose to tap into the temporal dimension of the surgical video data using the LSTM [31], [32], which has been demonstrated as a very powerful tool to model temporal concepts.”
MethodDeep learning in medical image analysis
Shen, D., Wu, G., & Suk, H.-I. (2017) · Annual Review of Biomedical Engineering · doi:10.1146/annurev-bioeng-071516-044442 · Cited by 4,968
Deep visual-semantic alignments for generating image descriptions
Karpathy, A., & Fei-Fei, L. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298932 · Cited by 4,902
Generating Sequences With Recurrent Neural Networks
Graves, A. (2013) · arXiv · doi:10.48550/arxiv.1308.0850 · Cited by 2,894 · cited 1×
“HMM, we propose to tap into the temporal dimension of the surgical video data using the LSTM [31], [32], which has been demonstrated as a very powerful tool to model temporal concepts.”
MethodHierarchical recurrent neural network for skeleton based action recognition
Du, Y., Wang, W., & Wang, L. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298714 · Cited by 1,895 · cited 1×
“It is powerful in handling sequential data by non-linearly modeling longrange temporal dependencies [27], and has been successfully applied to many challenging tasks [28]–[30].”
MethodGreenspan, H., van Ginneken, B., & Summers, R. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2553401 · Cited by 1,700
Srivastava, R. K., Greff, K., & Schmidhuber, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1507.06228 · Cited by 1,246
Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks
Yu, L., Chen, H., Dou, Q., Qin, J., & Heng, P.-A. (2017) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2642839 · Cited by 1,140 · cited 1×
“The importance of network depth for extracting discriminative features has been manifested by both computational theories [22], [23] and practical applications [24]–[26].”
BackgroundSelf-citationEndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos
Twinanda, A. P., Shehata, S., Mutter, D., Marescaux, J., de Mathelin, M., & Padoy, N. (2017) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2593957 · Cited by 1,096 · cited 10×
“in [11].”
BackgroundMethodInfluentialDeep Visual-Semantic Alignments for Generating Image Descriptions
Karpathy, A., & Fei-Fei, L. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2598339 · Cited by 1,048
3D deeply supervised network for automated segmentation of volumetric medical images
Dou, Q., Yu, L., Chen, H., Jin, Y., Yang, X., Qin, J., & Heng, P.-A. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.05.001 · Cited by 613 · cited 1×
“Deep learning techniques, extracting the high-level features, have successfully addressed many tasks [42]–[44].”
BackgroundSelf-citationComputational limitations of small-depth circuits
Håstad, J. (1987) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 465
Statistical modeling and recognition of surgical workflow
Padoy, N., Blum, T., Ahmadi, S.-A., Feussner, H., Berger, M.-O., & Navab, N. (2012) · Medical Image Analysis · doi:10.1016/j.media.2010.10.001 · Cited by 279 · cited 2×
“Diverse attempts have been made to recognize the surgical workflow or phase, by using various information, including binary instrument usage signals [7], RFID tags [8], data acquired via sensors on tool tracking devices [9], and surgical robots [10].”
BackgroundMethodContext awareness in health care: A review
Bricon-Souf, N., & Newman, C. R. (2007) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2006.01.003 · Cited by 263 · cited 2×
“it = σ(Wrirt + Whi ht−1 + bi), ft = σ(Wr f rt + Wh f ht−1 + b f ), ot = σ(Wrort + Whoht−1 + bo), c̃t = φ(Wrcrt + Whcht−1 + bc), ct = ft ct−1 + it c̃t , ht = ot φ(ct ), (2) where the hyperbolic tangent function φ(a)= ea−e−a ea+e−a squashes the activations into [−1, 1], and the sigmoid nonlinear function σ(a)= 1 1+e−a s…”
BackgroundOn the power of small-depth threshold circuits
H�stad, J., & Goldmann, M. (1991) · Computational Complexity · doi:10.1007/bf01272517 · Cited by 247 · cited 1×
“The importance of network depth for extracting discriminative features has been manifested by both computational theories [22], [23] and practical applications [24]–[26].”
BackgroundCombining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation
Chen, J., Yang, L., Zhang, Y., Alber, M., & Chen, D. Z. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.01006 · Cited by 212 · cited 1×
“Moreover, it is worth emphasizing that comparing with separately trained CNN-LSTM architectures [29], [45], [46], our SV-RCNet with utilizing joint learning mechanism enables networks to take full advantage of complementary of visual and temporal information and therefore produces more discriminative spatio-temporal f…”
BackgroundChen, H., Dou, Q., Ni, D., Cheng, J.-Z., Qin, J., Li, S., & Heng, P.-A. (2015) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-24553-9_62 · Cited by 180 · cited 1×
“Moreover, it is worth emphasizing that comparing with separately trained CNN-LSTM architectures [29], [45], [46], our SV-RCNet with utilizing joint learning mechanism enables networks to take full advantage of complementary of visual and temporal information and therefore produces more discriminative spatio-temporal f…”
BackgroundSelf-citationDiscriminative Localization in CNNs for Weakly-Supervised Segmentation of Pulmonary Nodules
Feng, X., Yang, J., Laine, A. F., & Angelini, E. D. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-66179-7_65 · Cited by 168 · cited 1×
“networks on an image and intercept the learned information of networks [37], [38].”
BackgroundUltrasound Standard Plane Detection Using a Composite Neural Network Framework
Chen, H., Wu, L., Dou, Q., Qin, J., Li, S., Cheng, J.-Z., Ni, D., & Heng, P.-A. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2685080 · Cited by 164 · cited 1×
“Moreover, it is worth emphasizing that comparing with separately trained CNN-LSTM architectures [29], [45], [46], our SV-RCNet with utilizing joint learning mechanism enables networks to take full advantage of complementary of visual and temporal information and therefore produces more discriminative spatio-temporal f…”
BackgroundSelf-citationModeling and Segmentation of Surgical Workflow from Laparoscopic Video
Blum, T., Feußner, H., & Navab, N. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15711-0_50 · Cited by 151 · cited 4×
“as intensity and gradient [12], shape, color and texture-based”
BackgroundMethodInfluentialRecognizing Surgical Activities with Recurrent Neural Networks
DiPietro, R. S., Lea, C., Malpani, A., Ahmidi, N., Vedula, S. S., Lee, G. I., Lee, M. R., & Hager, G. D. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46720-7_64 · Cited by 137 · cited 1×
“pituitary surgery as well as robotic surgery [6], [48], [49].”
BackgroundLalys, F., Riffaud, L., Bouget, D., & Jannin, P. (2011) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2011.2181168 · Cited by 131 · cited 2×
“descriptors [13].”
MethodAutomatic data-driven real-time segmentation and recognition of surgical workflow
Dergachyova, O., Bouget, D., Huaulmé, A., Morandi, X., & Jannin, P. (2016) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-016-1371-x · Cited by 129 · cited 4×
“However, collecting these signals mostly requires tedious manual annotation or extra equipment installation, which would introduce extra workload in the surgery process [2].”
BackgroundInfluentialSurgical Gesture Segmentation and Recognition
Tao, L., Zappella, L., Hager, G. D., & Vidal, R. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40760-4_43 · Cited by 121 · cited 1×
“dom field [18], and derivations of hidden markov model (HMM) [19], [20].”
BackgroundRecognizing End-Diastole and End-Systole Frames via Deep Temporal Regression Network
Kong, B., Zhan, Y., Shin, M., Denny, T., & Zhang, S. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46726-9_31 · Cited by 107 · cited 1×
“With these considerations, instead of inputting the complete video into the network [32], [34], we propose to cut the surgical video into short video clips and conduct truncated backpropagation which alleviates the training difficulty and the limitation of computational memory.”
Chen, H., Zheng, Y., Park, J.-H., Heng, P.-A., & Zhou, S. K. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46723-8_56 · Cited by 106
Self-citationAutomatic Detection and Segmentation of Robot-Assisted Surgical Motions
Lin, H. C., Izhak Shafran, J., Murphy, T. E., Okamura, A. M., Yuh, D. D., & Hager, G. D. (2005) · Lecture notes in computer science · doi:10.1007/11566465_99 · Cited by 89
On-line Recognition of Surgical Activity for Monitoring in the Operating Room
Padoy, N., Blum, T., Feußner, H., Berger, M., Navab, N., Lorraine, L. I., & Isar, K. R. D. (2008) · Cited by 86
Phase recognition during surgical procedures using embedded and body-worn sensors
Bardram, J. E., Doryab, A., Jensen, R. M., Lange, P. M., Nielsen, K. L. G., & Petersen, S. T. (2011) · 2011 IEEE International Conference on Pervasive Computing and Communications (PerCom) · doi:10.1109/percom.2011.5767594 · Cited by 76 · cited 1×
“Diverse attempts have been made to recognize the surgical workflow or phase, by using various information, including binary instrument usage signals [7], RFID tags [8], data acquired via sensors on tool tracking devices [9], and surgical robots [10].”
BackgroundReal-Time Task Recognition in Cataract Surgery Videos Using Adaptive Spatiotemporal Polynomials
Quellec, G., Lamard, M., Cochener, B., & Cazuguel, G. (2014) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2014.2366726 · Cited by 58 · cited 3×
“pituitary surgery as well as robotic surgery [6], [48], [49].”
BackgroundSurgical Phases Detection from Microscope Videos by Combining SVM and HMM
Lalys, F., Riffaud, L., Morandi, X., & Jannin, P. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-18421-5_6 · Cited by 56 · cited 1×
“dom field [18], and derivations of hidden markov model (HMM) [19], [20].”
BackgroundReal-time identification of operating room state from video
Bhatia, B., Oates, T., Xiao, Y., & Hu, P. (2007) · Cited by 53
Automatic feature generation in endoscopic images
Klank, U., Padoy, N., Feußner, H., & Navab, N. (2008) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-008-0223-8 · Cited by 50 · cited 1×
“However, it would be insufficient for these low-level features to represent the complicated surgical visual appearance [14].”
BackgroundA patient workflow management system built on guidelines.
Dazzi, L., Fassino, C., Saracco, R., Quaglini, S., & Mario Stefanelli, A. (1997) · Europe PMC (PubMed Central) · Cited by 45
Automatic phase prediction from low-level surgical activities
Forestier, G., Riffaud, L., & Jannin, P. (2015) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-015-1195-0 · Cited by 45 · cited 1×
“teams [5].”
Data-driven spatio-temporal RGBD feature encoding for action recognition in operating rooms
Twinanda, A. P., Alkan, E. O., Gangi, A., de Mathelin, M., & Padoy, N. (2015) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-015-1186-1 · Cited by 45 · cited 1×
“rooms in the future [47].”
Tool and Phase recognition using contextual CNN featuresPreprint
Sahu, M., Mukhopadhyay, A., Szengel, A., & Stefan Zachow, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.08854 · Cited by 36 · cited 1×
“[39] utilized an 8-layer AlexNet to extract visual features and modeled the temporal occurrences of surgical phases by fitting Gaussian distributions to further refine the prediction results.”
MethodAutomatic Phases Recognition in Pituitary Surgeries by Microscope Images Classification
Lalys, F., Riffaud, L., Morandi, X., & Jannin, P. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-13711-2_4 · Cited by 31 · cited 1×
“pituitary surgery as well as robotic surgery [6], [48], [49].”
BackgroundFeasibility of Real-Time Workflow Segmentation for Tracked Needle Interventions
Holden, M., Ungi, T., Sargent, D., McGraw, R. C., Chen, E. C. S., Ganapathy, S., Peters, T. M., & Gabor Fichtinger, A. (2014) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2014.2301635 · Cited by 30 · cited 1×
“Diverse attempts have been made to recognize the surgical workflow or phase, by using various information, including binary instrument usage signals [7], RFID tags [8], data acquired via sensors on tool tracking devices [9], and surgical robots [10].”
BackgroundSingle- and Multi-Task Architectures for Surgical Workflow Challenge at M2CAI 2016Preprint
Twinanda, A. P., Mutter, D., Marescaux, J., de Mathelin, M., & Padoy, N. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.08844 · Cited by 23 · cited 1×
“[41] also made use of an 8-layer AlexNet to extract visual features, followed by a hierarchical HMM for refinement, which is same as one method proposed in [11].”
MethodCadène, R., Robert, T., Thome, N., & Cord, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.05541 · Cited by 18 · cited 3×
“Nevertheless, the better results of [36] than”
MethodInfluentialRecurrent Encoder-Decoder Networks for Time-Varying Dense Prediction
Zeng, T., Wu, B., Zhou, J., Davidson, I. A. K., & Ji, S. (2017) · Proceedings · doi:10.1109/icdm.2017.156 · Cited by 7
Research works printed but not linked: 2
- olah, 2015, Understanding LSTM networks, Proc GitHub Blog
- dergachyova, 0, Data-driven surgical workflow detection: Technical report for M2CAI 2016 surgical workflow challenge, M2CAI Challenge
Cited by
Deep learning-enabled medical computer vision
Esteva, A., Chou, K., Yeung, S., Naik, N., Madani, A., Mottaghi, A., Liu, Y., Topol, E., Dean, J., & Socher, R. (2021) · npj Digital Medicine · doi:10.1038/s41746-020-00376-2 · Cited by 1,406
Machine Learning for Surgical Phase Recognition: A Systematic Review
Garrow, C. R., Kowalewski, K.-F., Li, L., Wagner, M., Schmidt, M. W., Engelhardt, S., Hashimoto, D. A., Kenngott, H. G., Bodenstedt, S., Speidel, S., et al. (2021) · Annals of Surgery · doi:10.1097/sla.0000000000004425 · Cited by 311
“39,42,46,48,56,57 Other studies focused on bariatric surgery and colorectal studies, 51,54 with both achieving a phase recognition accuracy over 90% The same ML model was compared between LC and colorectal surgery 1 study, achieving 74% and 67% accuracy, respectively.”
BackgroundResultTeCNO: Surgical Phase Recognition with Multi-stage Temporal Convolutional Networks
Czempiel, T., Paschali, M., Keicher, M., Simson, W., Feussner, H., Kim, S. T., & Navab, N. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-59716-0_33 · Cited by 223
Multi-task recurrent convolutional network with correlation loss for surgical video analysis
Jin, Y., Li, H., Dou, Q., Chen, H., Qin, J., Fu, C.-W., & Heng, P.-A. (2020) · Medical Image Analysis · doi:10.1016/j.media.2019.101572 · Cited by 204
Self-citationMachine and deep learning for workflow recognition during surgery
Padoy, N. (2019) · Minimally Invasive Therapy & Allied Technologies · doi:10.1080/13645706.2019.1584116 · Cited by 181
Metadata
- Authors
- Jin, Y., Dou, Q., Chen, H., Yu, L., Qin, J., Fu, C.-W., & Heng, P.-A.
- Affiliations
- Chinese University of Hong Kong (HK)
- Hong Kong Polytechnic University (HK)
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2018-05
- Volume
- 37
- Issue
- 5
- Pages
- 1114-1126
- ISSN
- 0278-0062 (ISSN-L)
- 1558-254X
- OpenAlex
- W2777273430
- Cited by
- 316
- References
- 50
- Citations by year
- 2026: 32 · 2025: 55 · 2024: 37 · 2023: 45 · 2022: 45 · 2021: 50 · 2020: 30 · 2019: 17 · 2018: 4
- FWCI
- 14.22
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Medical Imaging (publishedVersion)
- PubMed (publishedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- PolyU Institutional Research Archive (Hong Kong Polytechnic University) (submittedVersion)
- Funders
- Research Grants Council of Hong Kong Special Administrative Region (CUHK 14202514, CUHK 14203115)
- Shenzhen Science and Technology Program (JCYJ20170413162617606)
- Hong Kong Polytechnic University (1-ZE8J)
- Topics
- Health Sciences › Medicine › Surgery › Surgical Simulation and Training
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Keywords
- surgical workflow recognition, surgical video analysis, recurrent convolutional networks, computer-assisted surgery, spatio-temporal features, Cholec80 dataset, ResNet, LSTM
- MeSH terms
- Algorithms, Humans, Image Processing, Computer-Assisted, Software, Databases, Factual, Neural Networks, Computer, Video-Assisted Surgery, Workflow
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.