Multimodal Fused Emotion Recognition About Expression-EEG Interaction and Collaboration Using Deep Learning
Open accessThe DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
The proposed emotion recognition model is based on the hierarchical long-short term memory neural network (LSTM) for video-electroencephalogram (Video-EEG) signal interaction. The inputs are facial-video and EEG signals from the subjects when they are watching the emotion-stimulated video. The outputs are the corresponding emotion recognition results. Facial-video features and corresponding EEG features are extracted based on a fully connected neural network (FC) at each time point. These features are fused through hierarchical LSTM to predict the key emotional signal frames at the next time point until the emotion recognition result is calculated at the last time point. Specially, a self-attention mechanism is applied to show the correlation of the stacked LSTM at different hierarchies. In this process, the “selective focus” is used to analyze the human-emotional temporal sequences in each model, which improves the utilization of the key spatial EEG signals. Moreover, the process includes the temporal attention mechanism to predict the key signal frame at next time point, which utilizes the key emotion data in temporal domain. The experimental results prove that the classification rate (CR) and F1-score of the proposed emotion recognition model are significantly increased by at least 2% and 0.015, respectively, compared to other methods.
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.
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?
The cited source says what the claim attributes to it.
In the citing paper
“Feature extraction and fusion are the key steps in multimodal emotion recognition [3].”
From Multimodal Emotion Recognition Using a Hierarchical Fusion Convolutional Neural Network (2021) · cites this paper as [3]
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
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Salovey, P., & Mayer, J. D. (1990) · Imagination, Cognition and Personality · doi:10.2190/dugg-p24e-52wk-6cdg · Cited by 10,484
An argument for basic emotions
Ekman, P. (1992) · Cognition and Emotion · doi:10.1080/02699939208411068 · Cited by 9,646 · cited 1×
“Thebasic theory proves that when emotions arise, a variety reaction of human physiological and external behavior are activated [15].”
BackgroundDEAP: A Database for Emotion Analysis ;Using Physiological Signals
Koelstra, S., Muhl, C., Soleymani, M., Lee, J.-S., Yazdani, A., Ebrahimi, T., Pun, T., Nijholt, A., & Patras, I. (2012) · IEEE Transactions on Affective Computing · doi:10.1109/t-affc.2011.15 · Cited by 5,093
Toward machine emotional intelligence: analysis of affective physiological state
Picard, R. W., Vyzas, E., & Healey, J. (2001) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.954607 · Cited by 2,334 · cited 1×
“Picard et al. [11] used four signals, including electromyogram, blood pressure, gal-vanic skin response and heart rate, to identify eight emotions (grief, pleasure, anger, annoyance, neutrality, and reverence), resulting in 81% classification accuracy.”
BackgroundAffect Detection: An Interdisciplinary Review of Models, Methods, and Their Applications
Calvo, R. A., & D'Mello, S. (2010) · IEEE Transactions on Affective Computing · doi:10.1109/t-affc.2010.1 · Cited by 1,893 · cited 2×
“RELATED RESEARCH External features, such as the facial expression, body gesture and voice, are widely used in traditional emotion recognition methods [9].”
MethodEmotionMeter: A Multimodal Framework for Recognizing Human Emotions
Zheng, W.-L., Liu, W., Lu, Y., Lu, B.-L., & Cichocki, A. (2019) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2797176 · Cited by 1,276 · cited 1×
“The future human-computer emotional interaction research tends to: use the complementarity for the multimodal signals to emotional state, build a more robust emotional recognition model, and establish a multimodal emotional interaction algorithm combined outer performance with body signals [7], [8].”
BackgroundLearning Representations from EEG with Deep Recurrent-Convolutional Neural Networks
Bashivan, P., Rish, I., Yeasin, M., & Codella, N. (2015) · arXiv · doi:10.48550/arxiv.1511.06448 · Cited by 836 · cited 1×
“Next, referring the data processing proposed by Bashivan et al. [24], the EEG signals are divided into different segments with a duration of T (1/T is the frame rate of facial video), then spectral energy are extracted from three types of waves ( α, β and θ ) at t th data segment.”
MethodEEG-based emotion recognition during watching movies
Nie, D., Wang, X.-W., Shi, L.-C., & Lu, B.-L. (2011) · 2011 5th International IEEE/EMBS Conference on Neural Engineering · doi:10.1109/ner.2011.5910636 · Cited by 360 · cited 1×
“In 2011, Nie et al. [12] extracted energy values from five frequency bands after the short-time Fourier transform of the EEG signals and achieved 87.53% recognition accuracy.”
BackgroundInfluentialVerma, G. K., & Tiwary, U. S. (2014) · NeuroImage · doi:10.1016/j.neuroimage.2013.11.007 · Cited by 354 · cited 1×
“For instance, Verma and Tiwary [18] recognized thirteen emotions using EEG, GSR, blood pressure, breath model, skin temperature, EMG and EOG signals.”
Background
Research works printed but not linked: 2
- huang, 2018, Fusion of facial expressions and EEG for emotion recognition, Comput Syst Appl, 27, 9
- chang, 2017, Using reinforce learning to train multi attention model, ACTA Automatica Sinica, 43, 1563
Cited by
A systematic review on affective computing: emotion models, databases, and recent advances
Wang, Y., Song, W., Tao, W., Liotta, A., Yang, D., Li, X., Gao, S., Sun, Y., Ge, W., Zhang, W., et al. (2022) · Information Fusion · doi:10.1016/j.inffus.2022.03.009 · Cited by 615
Emotion recognition in EEG signals using deep learning methods: A review
Jafari, M., Shoeibi, A., Khodatars, M., Bagherzadeh, S., Shalbaf, A., García, D. L., Gorriz, J. M., & Acharya, U. R. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107450 · Cited by 240
Multimodal Emotion Recognition with Deep Learning: Advancements, challenges, and future directions
A.V., G., T., M., D., P., & E., U. (2024) · Information Fusion · doi:10.1016/j.inffus.2023.102218 · Cited by 225
A review on EEG-based multimodal learning for emotion recognition
Pillalamarri, R., & Shanmugam, U. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11126-9 · Cited by 183
Deep Learning for Intelligent Human–Computer Interaction
Lv, Z., Poiesi, F., Dong, Q., Lloret, J., & Song, H. (2022) · Applied Sciences · doi:10.3390/app122211457 · Cited by 174
“The next generation of revolutionary HCI technology may not impact the whole industry, such as the emergence of graphical interfaces and touch technology, but may use data-driven intelligence to realize the potential revolution of HCI [8].”
BackgroundMultimodal Emotion Recognition Using a Hierarchical Fusion Convolutional Neural Network
Zhang, Y., Cheng, C., & Zhang, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3049516 · Cited by 84
“Feature extraction and fusion are the key steps in multimodal emotion recognition [3].”
BackgroundMuhammad, F., Hussain, M., & Aboalsamh, H. (2023) · Diagnostics · doi:10.3390/diagnostics13050977 · Cited by 36
“Wu et al. [72] propose a model for facial expression and EEG data fusion based on hierarchical LSTM.”
TMNet: Transformer-fused multimodal framework for emotion recognition via EEG and speech
Alam, M. M., Dini, M. A., Kim, D., & Jun, T. (2025) · ICT Express · doi:10.1016/j.icte.2025.04.007 · Cited by 27
Singh, K., Ahirwal, M. K., & Pandey, M. (2022) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-022-04495-4 · Cited by 27
“…and Kose 2018; Cui et al. 2020), graph convolutional neural networks (GCNN) (Song et al. 2020), long-short term memories neural networks (LSTM) (Wu et al. 2020), and others have recently achieved cutting-edge performance in the fields of EEG-based emotion recognition, owing to their remarkable…”
BackgroundMethodInfluentialSanthosh, J., Pai, A. P., & Ishimaru, S. (2024) · IEEE Access · doi:10.1109/access.2024.3350745 · Cited by 26
“The visual modality (facial expression, voice, gesture, posture, etc.) may also be integrated with multimodal physiological signals for visual-physiological affective analysis [52].”
BackgroundEEG-Based Human Emotion Prediction Using an LSTM Model
Mohsen, S., & Alharbi, A. G. (2021) · IEEE International Midwest Symposium on Circuits and Systems (MWSCAS) · doi:10.1109/mwscas47672.2021.9531707 · Cited by 24
“[3] proposed multimodal fused emotion recognition via long short-term memory (LSTM) model; however, it did not achieve the desired accuracy.”
BackgroundDriving Fatigue Detection with Three Non-Hair-Bearing EEG Channels and Modified Transformer Model
Wang, J., Xu, Y., Tian, J., Li, H., Jiao, W., Sun, Y., & Li, G. (2022) · Entropy · doi:10.3390/e24121715 · Cited by 24
Residual multimodal Transformer for expression‐EEG fusion continuous emotion recognition
Jin, X., Xiao, J., Jin, L., & Zhang, X. (2024) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.12346 · Cited by 23
Erdem Güler, S., & Patlar Akbulut, F. (2025) · IEEE Access · doi:10.1109/access.2025.3538642 · Cited by 21
“The benefits of combining facial expressions with EEG signals were further highlighted by research by Wu et al. [17] and and Rayatdoost et al. [18].”
Wang, X., Li, C., Sun, Z., & Xu, Y. (2025) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2024.3523342 · Cited by 14
“Wu et al. [24] proposed a hierarchical LSTM for video-EEG signal interaction increasing the accuracy and F1-score.”
EEG-based fusion approaches in multimodal emotion recognition: An in-depth review
Yılmaz, B. H., Yılmaz, Ç. M., & Köse, C. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132235 · Cited by 13
Mohsen, S., Ghoneim, S. S. M., Alzaidi, M. S., Alzahrani, A., & Hassan, A. M. A. (2023) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.038758 · Cited by 13
Reddy, C. N., Mahesh, S., & Manjunathachari, K. (2023) · Computer Methods in Biomechanics & Biomedical Engineering · doi:10.1080/10255842.2023.2252551 · Cited by 13
“The ensemble (Zhang 2020) technique has the potential to enhance multi-modal emotion recognition.”
State-of-the-art Multimodal Emotion Recognition: A comprehensive survey and taxonomy
Yazici, A., Kucukyilmaz, T., Dokeroglu, T., Sharipbay, A., Lee, M.-H., & Tyler, B. (2026) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2026.200642 · Cited by 11
Wu, Q., Zhu, M., Xu, W., Wang, J., Mao, Z., Gao, Q., & Song, Y. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3400341 · Cited by 11
“Wu et al. [32] extracted facial expression and EEG features based on fully connected (FC) neural networks, and fused these features using layered LSTM. Wang et al. [33] used the pretrained CNN to extract facial expression features and then applied the attention mechanism to extract critical facial…”
MethodMuniyandi, A. P., Padmanandam, K., Karthika, S., Khadidos, A. O., Khadidos, A. O., Deepa, N., & Selvarajan, S. (2025) · Scientific Reports · doi:10.1038/s41598-025-89904-2 · Cited by 9
He, X., & Fu, S. (2022) · Journal of Mathematics · doi:10.1155/2022/8944570 · Cited by 9
“In the framework of instructional design based on in-depth learning, the determination of unit objectives needs to be guided by the core literacy of the discipline, based on the needs, cognitive development law, and learning status of and contents of the [7].”
RetractedEmotion Recognition from Physiological Signals Using Continuous Wavelet Transform and Deep Learning
Jalal, L., & Peer, A. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17618-0_8 · Cited by 9
Loaiza-Arias, M., Álvarez-Meza, A. M., Peña, D. A. C., Orozco, A. A., & Castellanos-Dominguez, G. (2024) · Applied Sciences · doi:10.3390/app142311208 · Cited by 7
EEG Emotion Recognition Using an Attention Mechanism Based on an Optimized Hybrid Model
Jiang, H., Wu, D., Tang, X., Li, Z., & Wu, W. (2022) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2022.027856 · Cited by 7
Self-citationPan, Y. (2025) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2025.0160613 · Cited by 6
“Wu et al.[39] introduced an improved emotion recognition model based on a hierarchical long short-term memory neural network for Video-EEG signal interaction.”
Multi-Modal Emotion Detection and Tracking System Using AI Techniques
Mostert, W., Kurien, A. M., & Djouani, K. (2025) · Computers · doi:10.3390/computers14100441 · Cited by 6
EEG data based human attention recognition using various machine learning techniques: a review
Devi, A., & Rathna, R. (2023) · Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization · doi:10.1080/21681163.2023.2299096 · Cited by 6
“The outcomes of Ensemble EMD are more trustworthy (Wu et al. 2020).”
BackgroundAbgeena, A., & Garg, S. (2025) · Cognitive Neurodynamics · doi:10.1007/s11571-025-10328-9 · Cited by 5
Model-driven validation of visual explanations for multimodal emotion recognition
Gagliardi, G., Alfeo, A. L., Catrambone, V., Cimino, M. G. C. A., Vos, M. D., & Valenza, G. (2025) · Machine Learning · doi:10.1007/s10994-025-06921-y · Cited by 4
“Transformer-based attention mechanisms have been recently utilized to selectively emphasize and amalgamate complementary input features within emotion recognition tasks (Di et al., 2020 ).”
EEG-based multimodal emotion recognition with optimal trained hybrid classifier
Chakravarthy, G. K., Suchithra, M., & Thatavarti, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17489-x · Cited by 4
“It is an emotion that suggests one’s behaviour in the situation [2, 3].”
[Retracted] Detection Method of Limb Movement in Competitive Sports Training Based on Deep Learning
Qin, C., & Huo, S. (2022) · Journal of Mathematics · doi:10.1155/2022/8643234 · Cited by 4
“Many depth sensors with high sample rates and inexpensive prices have lately been launched, owing to the fast development of depth-sensing technology [8].”
RetractedMultimodal emotion recognition from physiological signals and facial expressions
Wu, Y. (2023) · theses.fr (ABES) · doi:10.70675/62534f92z5bf0z4c11z878bz70609f3f17fc · Cited by 4
Emo-Spots: Detection and Analysis of Emotional Attributes Through Bio-Inspired Facial Landmarks
Bakkialakshmi, V. S., Sudalaimuthu, T., & Maheswari, B. U. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-8136-4_9 · Cited by 3
Kaya, Ş. M. (2026) · Applied Sciences · doi:10.3390/app16094394 · Cited by 2
A Systematic Literature Review of Multimodal Emotion Recognition
Rahayu, Y. D., Muharom, L. A., Windiarti, I. S., & Sugianto, A. H. (2023) · Scientific Journal of Informatics · doi:10.15294/sji.v10i2.43792 · Cited by 2
“Classical classification methods are used (Decision Tree, and SVM [168]–[171]) or deep learning (CNN, DNN, RNN) [40], [42], [73], [108], [112], [130], [172]–[188] and deep learning with enrichment [189].”
MethodSaisanthiya, D., & Perumal, S. (2023) · Traitement du signal · doi:10.18280/ts.400619 · Cited by 2
“This paper employs the strongest EEG functional connectivity network parameter, or strength [35], to further evaluate its discriminating capability in recognizing emotions on the SEED and DEAP datasets.”
Unique Covariate Identity (UCI) Detection for Emotion Recognition Through EEG Signals
Bakkialakshmi, V. S., & Sudalaimuthu, T. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-3481-2_56 · Cited by 1
A Review of Machine Learning-Based Assessment of Depression
Wang, Z., Cai, Z., Dong, S., & Hei, W. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-3755-3_15 · Cited by 1
EEG-Based Emotion Recognition Using Multi-Axis Adapter Transformer
Wang, Z., Liu, P., Zhang, J., He, L., & He, Y. (2026) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2026.3672612 · Cited by 1
“With the development of deep learning, a variety of neural architectures—including CNN-based models [8], [9], RNN-based models [10], and Transformer-based frameworks [11], [12]—have been proposed for automatic feature extraction.”
Self-citationPillalamarri, R., & Shanmugam, U. (2026) · Journal on Information Security · doi:10.1186/s13635-026-00230-0 · Cited by 1
Detection method of limb movement in competitive sports training based on deep learning
Wang, Y., Zhang, P., & Wang, Y. (2023) · Journal of Computational Methods in Sciences and Engineering · doi:10.3233/jcm-226688 · Cited by 1
“Especially with the rapid development of depth sensing technology recently, many depth sensors with high sampling rate and low price have been released [8].”
Hybrid AI-Based Approach Utilizing EEG-Facial Expression fusion for Human-Machine Interaction
Roshdy, A. (2025) · theses.fr (ABES) · doi:10.70675/13353b00z0986z41ddza853zc4f75bf5368f · Cited by 1
Kaur, D., Misra, A., & Vyas, O. P. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-99-4284-8_35
Kumar, H., & Martín, A. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-8628-6_19
A Review on Facial Emotion Recognition of Subjects Using Deep Learning Techniques
Kumar, P. S., Nikhil, M., Rudresh, P. H. S., Kiran, K. S., Charan, K., & Prasad, K. S. (2024) · International Conference on Social and Sustainable Innovations in Technology and Engineering (SASI-ITE) · doi:10.1109/sasi-ite58663.2024.00016
Intelligent Human Computer Interface Devices based on Neural Network
Soni, R. (2025) · International Journal of Research & Technology · doi:10.64882/ijrt.v13.i4.436
“However, there is still a significant speech recognition bottleneck in complicated and loud environments [4].”
Denoise and Attend: An AE-Transformer Approach to EEG Emotion Recognition
Luo, M. (2025) · International Conference on Electrical Engineering and Computer Technology (IC2ECT) · doi:10.1109/ic2ect66838.2025.11291002
“Beyond single-modality EEG, multimodal systems fusing EEG with facial, speech, and peripheral signals demonstrate complementary gains [10–15].”
EEG-Based Mental Health Analysis and Classification for Healthy Brain Network(HBN)
Nikhara, A., Arya, A., Shridevi, S., & Won, D. (2025) · Innovations in Power and Advanced Computing Technologies (i-PACT) · doi:10.1109/i-pact65952.2025.11307890
Affect Recognition in Deaf Children Using Physiological Signal Measurements
Choudhary, K., & Prajapati, G. L. (2026) · SN Computer Science · doi:10.1007/s42979-025-04711-w
Alumnus, A. S., Alumnus, N. K., Alumnus, S. J. R., & Jayashree, M. J. (2025) · International Conference on Intelligent Computing, Information and Control Systems (ICOIICS) · doi:10.1109/icoiics67115.2025.11390230
“[4] developed a multi-model fused ER system.”
Thirugnana Sambandham, P., Mukilan, P., Lavanya, G., Maheswari, S., Saranya, K., & Devi, R. (2025) · IEEE International Conference on Emerging Trends in Computing and Communication (ETCOM) · doi:10.1109/etcom66606.2025.11436356
“These consist of manual feature extraction followed by classifiers like Decision Trees, k-Nearest Neighbors (k-NN), and Support Vector Machines (SVM) [3-4].”
Cárdenas, J. S. B. (2026) · Repositorio Digital (Escuela Politécnica Nacional)
The M-ArEye Database: A Multimodal Resource for Affect Recognition in Visually Impaired Children
Choudhary, K., & Prajapati, G. L. (2026) · IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI) · doi:10.1109/iatmsi68868.2026.11465269
“Hybrid models, such as CNN-LSTM [10], [13]and traditional classifiers, such as SVMs [19], are also common.”
Deep Learning for Facial Expression Recognition A Comprehensive Survey
Khodginkar, S. K. S. (2026) · INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · doi:10.55041/ijsrem65606
Emotion recognition and human-robot interaction: a systematic review of methods and applications
Barquin, I. S., Castano, J. A., Garate, V. R., & del‐Ama, A. J. (2026) · Frontiers in Robotics and AI · doi:10.3389/frobt.2026.1891746
Choudhary, K., & Prajapati, G. L. (2026) · Scientific Reports · doi:10.1038/s41598-026-72644-2
Metadata
- Authors
- Wu, D., Zhang, J., & Zhao, Q.
- Affiliations
- Qiqihar University (CN)
- Harbin Engineering University (CN)
- Venue
- IEEE Access
- Published
- 2020
- Volume
- 8
- Pages
- 133180-133189
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W3043900038
- Cited by
- 51
- References
- 23
- Citations by year
- 2026: 7 · 2025: 16 · 2024: 6 · 2023: 12 · 2022: 8 · 2021: 2
- FWCI
- 5.31
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundation of China (61672179, 61370083, 61402126)
- Specialized Research Fund for the Doctoral Program of Higher Education of China (20122304110012)
- Youth Science Foundation of Heilongjiang Province of China (QC2016083)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Keywords
- multimodal emotion recognition, facial expressions, EEG, hierarchical LSTM, self-attention, temporal attention, EEG features
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.