Multimodal Data Fusion: An Overview of Methods, Challenges, and Prospects
Open accessThe DOI matches its Crossref record; 214 of the 218 references it cites were found in a registry or an index.
Abstract
In various disciplines, information about the same phenomenon can be acquired from different types of detectors, at different conditions, in multiple experiments or subjects, among others. We use the term “modality” for each such acquisition framework. Due to the rich characteristics of natural phenomena, it is rare that a single modality provides complete knowledge of the phenomenon of interest. The increasing availability of several modalities reporting on the same system introduces new degrees of freedom, which raise questions beyond those related to exploiting each modality separately. As we argue, many of these questions, or “challenges,” are common to multiple domains. This paper deals with two key issues: “why we need data fusion” and “how we perform it.” The first issue is motivated by numerous examples in science and technology, followed by a mathematical framework that showcases some of the benefits that data fusion provides. In order to address the second issue, “diversity” is introduced as a key concept, and a number of data-driven solutions based on matrix and tensor decompositions are discussed, emphasizing how they account for diversity across the data sets. The aim of this paper is to provide the reader, regardless of his or her community of origin, with a taste of the vastness of the field, the prospects, and the opportunities that it holds.
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
“There are three main types of data fusion that are used in machine learning; early (data-level), intermediate (joint), and late (decision-level)30.”
From Multimodal machine learning in precision health: A scoping review (2022) · cites this paper as [30]
In the citing paper
“These methods vary considerably in their models and applications but generally involve extensions of traditional multivariate analysis techniques such as independent component analysis, canonical correlation analysis, and singular value decomposition (Lahat et al. 2015).”
From Similarity-based multimodal regression (2024) · cites this paper as Lahat et al. 2015
In the citing paper
“While late fusion requires less data and allows for easier integration of multiple sensing strategies and algorithms, it may not fully leverage the complementary strengths of different modalities115.”
From AI-assisted multi-modal information for the screening of depression: a systematic review and meta-analysis (2025) · cites this paper as [115]
In the citing paper
“but to the best of our knowledge, there is no recent work that directly addresses the latest advances in deep multimodal learning particularly for the computer vision community.”
From A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets (2022) · cites this paper as [36]
In the citing paper
“Furthermore, some cutting-edge works [34, 36] have been proposed in recent years that address the mechanism of integrating and fusing multimodal representations inside deep learning architectures by showing the reader the possibilities this opens up for the artificial intelligence community.”
From A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets (2022) · cites this paper as [36]
Citations
Cites
Horn, R. A., & Johnson, C. R. (1985) · Cited by 22,203
Complex brain networks: graph theoretical analysis of structural and functional systems
Bullmore, E., & Sporns, O. (2009) · Nature Reviews Neuroscience · doi:10.1038/nrn2575 · Cited by 11,820 · cited 2×
“Bullmore and Sporns [165] study brain networks by first constructing separate models of structural and functional networks based on several brain imaging modalities and fuse them using a graph-theoretical framework.”
BackgroundTensor Decompositions and Applications
Kolda, T. G., & Bader, B. W. (2009) · SIAM Review · doi:10.1137/07070111x · Cited by 10,301 · cited 2×
“More properties of tensor decompositions and their uses in various engineering applications can be found for example in [64], [65], [106] and references therein.”
BackgroundHorn, R. A., & Johnson, C. R. (1985) · Cambridge University Press eBooks · doi:10.1017/cbo9780511810817 · Cited by 10,280
An Introduction to Multivariate Statistical Analysis
Muirhead, R. J., & Anderson, T. W. (1986) · Journal of Business & Economic Statistics · doi:10.2307/1391399 · Cited by 9,082
Independent component analysis, A new concept?
Comon, P. (1994) · Signal Processing · doi:10.1016/0165-1684(94)90029-9 · Cited by 8,205 · cited 2×
“Under these assumptions, separation can be achieved if the statistically independent sources are non-stationary, non-white, or nonGaussian [71], [80]–[82].”
Partial least-squares regression: a tutorial
Geladi, P., & Kowalski, B. R. (1986) · Analytica Chimica Acta · doi:10.1016/0003-2670(86)80028-9 · Cited by 6,992 · cited 1×
“We mention PLS [62], [203] and its multilinear extensions N -way PLS [62], [150] and higher-order PLS (HOPLS) [141].”
MethodPlanck 2013 results. XVI. Cosmological parameters
Planck Collaboration, Ade, P. A. R., Aghanim, N., Armitage-Caplan, C., Arnaud, M., Ashdown, M., Atrio-Barandela, F., Aumont, J., Baccigalupi, C., Banday, A. J., et al. (2014) · Astronomy & Astrophysics · doi:10.1051/0004-6361/201321591 · Cited by 6,521 · cited 1×
“surveys, galaxy clustering [54], [55], and stacked gravitational lensing, also serve as important cosmological probes [51], [52].”
BackgroundHearing lips and seeing voices
MCGURK, H., & MACDONALD, J. (1976) · Nature · doi:10.1038/264746a0 · Cited by 6,183 · cited 4×
“Most human verbal communication involves seeing the speaker [18].”
BackgroundInfluentialCombining labeled and unlabeled data with co-training
Blum, A., & Mitchell, T. (1998) · Proceedings of the eleventh annual conference on Computational learning theory · doi:10.1145/279943.279962 · Cited by 5,495
RELATIONS BETWEEN TWO SETS OF VARIATES
HOTELLING, H. (1936) · Biometrika · doi:10.1093/biomet/28.3-4.321 · Cited by 5,263
NINE-YEAR WILKINSON MICROWAVE ANISOTROPY PROBE ( WMAP ) OBSERVATIONS: COSMOLOGICAL PARAMETER RESULTS
Hinshaw, G., Larson, D., Komatsu, E., Spergel, D. N., Bennett, C. L., Dunkley, J., Nolta, M. R., Halpern, M., Hill, R. S., Odegard, N., et al. (2013) · The Astrophysical Journal Supplement Series · doi:10.1088/0067-0049/208/2/19 · Cited by 5,121 · cited 2×
“surveys, galaxy clustering [54], [55], and stacked gravitational lensing, also serve as important cosmological probes [51], [52].”
BackgroundHämäläinen, M., Hari, R., Ilmoniemi, R. J., Knuutila, J., & Lounasmaa, O. V. (1993) · Reviews of Modern Physics · doi:10.1103/revmodphys.65.413 · Cited by 4,684 · cited 1×
“obtained using spatial constraints from fMRI [12], [22], [30].”
MethodCarroll, J. D., & Chang, J.-J. (1970) · Psychometrika · doi:10.1007/bf02310791 · Cited by 4,678 · cited 26×
“It should be noted that the uniqueness results for coupled CPD [90] (Example III-D.2) require at least one tensor of order larger than two in the coupled set and thus they cannot be applied to IVA. x ( M ) dependentstatistically statistically dependent Example III-D.2: Coupled Tensor Decompositions.”
BackgroundMethodInfluentialMultimodality image registration by maximization of mutual information
Maes, F., Collignon, A., Vandermeulen, D., Marchal, G., & Suetens, P. (1997) · IEEE Transactions on Medical Imaging · doi:10.1109/42.563664 · Cited by 4,547 · cited 1×
“One approach uses information theory and maximizes mutual information [148], [149].”
BackgroundA Multilinear Singular Value Decomposition
De Lathauwer, L., De Moor, B., & Vandewalle, J. (2000) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/s0895479896305696 · Cited by 4,106 · cited 4×
“Such are PARAFAC (Section III-C2), generalized singular value decomposition (GSVD) [170] and its higher-order generalization [171], the higher-order SVD (HOSVD) [172], and more.”
BackgroundInfluentialIntroduction to Multivariate Statistical Analysis.
Madow, W. G., & Anderson, T. W. (1959) · The American Mathematical Monthly · doi:10.2307/2308777 · Cited by 3,878 · cited 1×
“[199] T.”
Some Mathematical Notes on Three-Mode Factor Analysis
Tucker, L. R. (1966) · Psychometrika · doi:10.1007/bf02289464 · Cited by 3,492 · cited 1×
“Relaxing the sum-ofrank-1-terms constraint in PARAFAC leads to more flexible tensor decompositions such as Tucker [6], [7], block term decomposition (BTD) [135], three-way decomposition into directional components (DEDICOM) [136], and others [137].”
BackgroundA method for making group inferences from functional MRI data using independent component analysis
Calhoun, V. D., Adali, T., Pearlson, G. D., & Pekar, J. J. (2001) · Human Brain Mapping · doi:10.1002/hbm.1048 · Cited by 2,994 · cited 3×
“In joint ICA [173] and group ICA [174], [175], several ICA problems share a mixing matrix or source subspace, respectively, by concatenating the observation matrices in rows or columns.”
BackgroundMethodBlind beamforming for non-gaussian signals
Cardoso, J. F., & Souloumiac, A. (1993) · IEE Proceedings F Radar and Signal Processing · doi:10.1049/ip-f-2.1993.0054 · Cited by 2,738 · cited 2×
“These properties can be reformulated algebraically as a symmetric joint diagonalization (JD) of several matrices [81], [83], i.”
BackgroundMethodA Measurement of Excess Antenna Temperature at 4080 Mc/s.
Penzias, A. A., & Wilson, R. W. (1965) · The Astrophysical Journal · doi:10.1086/148307 · Cited by 2,604 · cited 1×
“Therefore, since the first experimental discovery of the CMB in 1965 [53], there has been an ongoing effort to obtain better and more accurate”
BackgroundNine-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Cosmological Parameter Results
WRIGHT, E. L. (2016) · NASA STI Repository (National Aeronautics and Space Administration) · doi:10.15781/t2st7f05x · Cited by 2,601
Harshman, R. A. (1970) · Cited by 2,255
Multisensor data fusion: A review of the state-of-the-art
Khaleghi, B., Khamis, A., Karray, F. O., & Razavi, S. N. (2013) · Information Fusion · doi:10.1016/j.inffus.2011.08.001 · Cited by 2,074 · cited 10×
“Following from [8], [9], [16], [19] (and others), and further”
BackgroundInfluentialSimultaneous Factor Analysis in Several Populations
Jöreskog, K. G. (1971) · Psychometrika · doi:10.1007/bf02291366 · Cited by 2,051
Improved cosmological constraints from a joint analysis of the SDSS-II and SNLS supernova samples
Betoule, M., Kessler, R., Guy, J., Mosher, J., Hardin, D., Biswas, R., Astier, P., El-Hage, P., Konig, M., Kuhlmann, S., et al. (2014) · Astronomy & Astrophysics · doi:10.1051/0004-6361/201423413 · Cited by 1,905 · cited 1×
“surveys, galaxy clustering [54], [55], and stacked gravitational lensing, also serve as important cosmological probes [51], [52].”
BackgroundBlind signal separation: statistical principles
Cardoso, J.-F. (1998) · Proceedings of the IEEE · doi:10.1109/5.720250 · Cited by 1,885
Planck 2013 results. I. Overview of products and scientific results
Planck Collaboration, Ade, P. A. R., Aghanim, N., Alves, M. I. R., Armitage-Caplan, C., Arnaud, M., Ashdown, M., Atrio-Barandela, F., Aumont, J., Aussel, H., et al. (2014) · Astronomy & Astrophysics · doi:10.1051/0004-6361/201321529 · Cited by 1,738
Multimodal Learning with Deep Boltzmann Machines
Srivastava, N., & Salakhutdinov, R. (2012) · Journal of Machine Learning Research · doi:10.5555/2627435.2697059 · Cited by 1,659
Relations Between Two Sets of Variates
Hotelling, H. (1936) · Biometrika · doi:10.2307/2333955 · Cited by 1,645
Kruskal, J. B. (1977) · Linear Algebra and its Applications · doi:10.1016/0024-3795(77)90069-6 · Cited by 1,619 · cited 5×
“even for R > 1, under very mild constraints on A, B, C [66], [67], [88].”
BackgroundInfluentialHandbook of Blind Source Separation, Independent Component Analysis and Applications
Comon, P., & Jutten, C. (2010) · HAL (Le Centre pour la Communication Scientifique Directe) · Cited by 1,501
Self-citationCichocki, A., Mandic, D., De Lathauwer, L., Zhou, G., Zhao, Q., Caiafa, C., & PHAN, H. A. (2015) · IEEE Signal Processing Magazine · doi:10.1109/msp.2013.2297439 · Cited by 1,384 · cited 15×
“Generalized linked-mode for multiway data [8] and LMWCA [65] mention explicitly that they can be defined both with “soft” or “hard” links.”
BackgroundInfluentialThe Expression of a Tensor or a Polyadic as a Sum of Products
Hitchcock, F. L. (1927) · Journal of Mathematics and Physics · doi:10.1002/sapm192761164 · Cited by 1,345 · cited 1×
“When (8) holds and is irreducible in the sense that R is minimal, it is sometimes referred to as the canonical polyadic decomposition (CPD) [4], [87].”
BackgroundIntroduction to Multivariate Statistical Analysis
Kendall, M. G., & Anderson, T. W. (1959) · Econometrica · doi:10.2307/1909376 · Cited by 1,339
A Critical Comparison Among Pansharpening Algorithms
Vivone, G., Alparone, L., Chanussot, J., Dalla Mura, M., Garzelli, A., Licciardi, G. A., Restaino, R., & Wald, L. (2015) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2014.2361734 · Cited by 1,303 · cited 2×
“Hence, there exists a tradeoff between spectral and spatial resolution [39], [40] [13, Chapter 9].”
BackgroundRelational learning via collective matrix factorization
Singh, A. P., & Gordon, G. J. (2008) · Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1401890.1401969 · Cited by 1,204 · cited 4×
“combinations of the basic building blocks, thus leading to new mathematical models, algorithms and concepts [8], [16], [163], [164].”
BackgroundInfluentialCoupled Nonnegative Matrix Factorization Unmixing for Hyperspectral and Multispectral Data Fusion
Yokoya, N., Yairi, T., & Iwasaki, A. (2012) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2011.2161320 · Cited by 1,180 · cited 5×
“This type of optimization is used in group NMF [186], coupled NMF [182], certain SCA-based methods [98], [176]–[178], and numerous coupled tensor decompositions, see e.g., [16], [99], [124] and references therein.”
MethodInfluentialMulti‐Way Analysis with Applications in the Chemical Sciences
Smilde, A., Bro, R., & Geladi, P. (2004) · Wiley eBooks · doi:10.1002/0470012110 · Cited by 1,176
Spatial Pattern Analysis of Functional Brain Images Using Partial Least Squares
McIntosh, A. R., Bookstein, F. L., Haxby, J. V., & Grady, C. L. (1996) · NeuroImage · doi:10.1006/nimg.1996.0016 · Cited by 1,114 · cited 3×
“The fact that there is no ground truth is reflected in the very broad range of methods and approaches that are being proposed [12], [15], [17], [21], [28]–[31].”
BackgroundMultiple dipole modeling and localization from spatio-temporal MEG data
Mosher, J. C., Lewis, P. S., & Leahy, R. M. (1992) · IEEE Transactions on Biomedical Engineering · doi:10.1109/10.141192 · Cited by 1,048 · cited 1×
“Often formulated as a linear inverse problem, it is ill-posed: many different spatial current patterns within the skull can give rise to identical measurements [33].”
BackgroundJoint Analysis of BICEP2/ Keck Array and Planck Data
Ade, P. A. R., Aghanim, N., Ahmed, Z., Aikin, R. W., Alexander, K. D., Arnaud, M., Aumont, J., Baccigalupi, C., Banday, A. J., Barkats, D., et al. (2015) · Physical Review Letters · doi:10.1103/physrevlett.114.101301 · Cited by 1,013 · cited 3×
“Power spectra are useful to compare outcomes of different experiments that measure the CMB, e.g., Planck and BICEP2/Keck [168], whereas cosmological parameters form the link, via the ΛCDM model, with datasets that do not involve astrophysical observations, e.g., high-energy physics at CERN [56].”
BackgroundInfluentialVirtanen, T. (2007) · IEEE Transactions on Audio, Speech and Language Processing · doi:10.1109/tasl.2006.885253 · Cited by 1,005 · cited 1×
“In such cases, the link is often defined as some correspondence between datasets that can be interpreted as similarity, smoothness or continuity [169].”
BackgroundCanonical analysis of several sets of variables
KETTENRING, J. R. (1971) · Biometrika · doi:10.1093/biomet/58.3.433 · Cited by 896
A survey of multi-view machine learning
Sun, S. (2013) · Neural Computing and Applications · doi:10.1007/s00521-013-1362-6 · Cited by 878 · cited 1×
“A survey of techniques for multi-view machine learning can be found in [206].”
BackgroundTensorial extensions of independent component analysis for multisubject FMRI analysis
Beckmann, C. F., & Smith, S. M. (2005) · NeuroImage · doi:10.1016/j.neuroimage.2004.10.043 · Cited by 761 · cited 25×
“As an example, a solution that maximally retains the joint information while also ensuring that the decomposed sources are independent from each other, in the context of a “joint ICA”-based approach, is proposed in [117].”
BackgroundInfluentialMultiway calibration. Multilinear PLS
Bro, R. (1996) · Journal of Chemometrics · doi:10.1002/(sici)1099-128x(199601)10:1<47::aid-cem400>3.0.co;2-c · Cited by 714 · cited 4×
“Frequently-used models such as multiway partial least squares (PLS) [150] and PARAFAC [62] are less adequate when the underlying profiles change shape from sample to sample.”
BackgroundMethodInfluentialHyperspectral and Multispectral Image Fusion Based on a Sparse Representation
Wei, Q., Bioucas-Dias, J., Dobigeon, N., & Tourneret, J.-Y. (2015) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2014.2381272 · Cited by 698
Prostate Cancer: Multiparametric MR Imaging for Detection, Localization, and Staging
Hoeks, C. M. A., Barentsz, J. O., Hambrock, T., Yakar, D., Somford, D. M., Heijmink, S. W. T. P. J., Scheenen, T. W. J., Vos, P. C., Huisman, H., van Oort, I. M., et al. (2011) · Radiology · doi:10.1148/radiol.11091822 · Cited by 677 · cited 2×
“One of the main challenges is the automation of such decision procedures, in order to improve correct interpretation, as well as save costs and time [35].”
Hyperspectral and LiDAR Data Fusion: Outcome of the 2013 GRSS Data Fusion Contest
Debes, C., Merentitis, A., Heremans, R., Hahn, J., Frangiadakis, N., van Kasteren, T., Liao, W., Bellens, R., Pizurica, A., Gautama, S., et al. (2014) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2014.2305441 · Cited by 653 · cited 3×
“Examples include multi-sensor [9], HMI [10] and remote sensing [42] applications.”
BackgroundInformation combination operators for data fusion: a comparative review with classification
Bloch, I. (1996) · IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans · doi:10.1109/3468.477860 · Cited by 639
Scalable tensor factorizations for incomplete data
Acar, E., Dunlavy, D. M., Kolda, T. G., & Mørup, M. (2011) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2010.08.004 · Cited by 602 · cited 1×
“It turns out that the same applies also in the case of missing values, see [16], [99], [160]–[162] and references therein.”
BackgroundBlind PARAFAC receivers for DS-CDMA systems
Sidiropoulos, N. D., Giannakis, G. B., & Bro, R. (2000) · IEEE Transactions on Signal Processing · doi:10.1109/78.824675 · Cited by 560 · cited 3×
“astrophysics [59], biomedics [60], telecommunications [61], audio-vision [23], chemometrics [62], and more.”
BackgroundHyvärinen, A., & Hoyer, P. (2000) · Neural Computation · doi:10.1162/089976600300015312 · Cited by 533 · cited 1×
“[131] A.”
On the uniqueness of multilinear decomposition ofN-way arrays
Sidiropoulos, N. D., & Bro, R. (2000) · Journal of Chemometrics · doi:10.1002/1099-128x(200005/06)14:3<229::aid-cem587>3.0.co;2-n · Cited by 525 · cited 3×
“This is analogous to the previously-mentioned result (Section III-C2) for a single tensor, that increasing its order N relaxes the bound on R [57], [91].”
BackgroundResultPARAFAC: Parallel factor analysis
Harshman, R. A., & Lundy, M. E. (1994) · Computational Statistics & Data Analysis · doi:10.1016/0167-9473(94)90132-5 · Cited by 522 · cited 1×
“since they yield non-interpretable results [69].”
Environmental Monitoring by Wireless Communication Networks
Messer, H., Zinevich, A., & Alpert, P. (2006) · Science · doi:10.1126/science.1120034 · Cited by 512 · cited 2×
“primarily attenuation due to rainfall [46], [47].”
BackgroundFetal electrocardiogram extraction by blind source subspace separation
de Lathauwer, L., de Moor, B., & Vandewalle, J. (2000) · IEEE Transactions on Biomedical Engineering · doi:10.1109/10.841326 · Cited by 502
Multimodal interaction: A review
Turk, M. (2014) · Pattern Recognition Letters · doi:10.1016/j.patrec.2013.07.003 · Cited by 496 · cited 7×
“, [21], [27], [58] (biomedical imaging) and [10], [11] (HMI).”
BackgroundInfluentialDecompositions of a Higher-Order Tensor in Block Terms—Part II: Definitions and Uniqueness
De Lathauwer, L. (2008) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/070690729 · Cited by 479 · cited 3×
“Tensor decompositions that can be reformulated as M ( m ) ( ( z )) include rank-1 decompositions (CPD, PARAFAC), decompositions into rank 1 terms, Tucker, BTD, PARAFAC2 [70], and many others.”
BackgroundContributions to mathematical psychology
Frederiksen, N., & Gulliksen, H. O. (1964) · Medical Entomology and Zoology · Cited by 458
Research methods for multimode data analysis
Law, H. G. (1984) · Medical Entomology and Zoology · Cited by 425
Image Fusion. Algorithms and Applications
(2009) · Sensor Review · doi:10.1108/sr.2009.08729cae.001 · Cited by 417
Multidimensional independent component analysis
Cardoso, J.-F. (2002) · Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181) · doi:10.1109/icassp.1998.681443 · Cited by 403
A review of multivariate methods for multimodal fusion of brain imaging data
Sui, J., Adali, T., Yu, Q., Chen, J., & Calhoun, V. D. (2012) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2011.10.031 · Cited by 401 · cited 2×
“astrophysics [59], biomedics [60], telecommunications [61], audio-vision [23], chemometrics [62], and more.”
BackgroundMethodDecomposing EEG data into space–time–frequency components using Parallel Factor Analysis
Miwakeichi, F., Martı́nez-Montes, E., Valdés-Sosa, P. A., Nishiyama, N., Mizuhara, H., & Yamaguchi, Y. (2004) · NeuroImage · doi:10.1016/j.neuroimage.2004.03.039 · Cited by 374 · cited 2×
“However, it has been proposed to augment this data using a third type of diversity, electrode ⇥ time ⇥ frequency [101]– [103].”
BackgroundSignal Processing based on Multilinear Algebra
Lathauwer, L. D. (1997) · OpenGrey (Institut de l'Information Scientifique et Technique) · Cited by 360
Tensors : A brief introduction
Comon, P. (2014) · IEEE Signal Processing Magazine · doi:10.1109/msp.2014.2298533 · Cited by 347 · cited 3×
“A second generalization is by combining several types of constraints and assumptions: for example, PARAFAC may be combined with statistical independence [104], [138], nonnegativity, sparsity, as well as structure of the latent factors: Vandermonde [72]–[75], Toeplitz [76], among others [16], [65], [106], [139].”
BackgroundJoint Blind Source Separation by Multiset Canonical Correlation Analysis
Li, Y.-O., Adali, T., Wang, W., & Calhoun, V. D. (2009) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2009.2021636 · Cited by 337 · cited 3×
“second-order statistics (SOS) alone [110], [111].”
BackgroundConcurrent EEG/fMRI analysis by multiway Partial Least Squares
Martı́nez-Montes, E., Valdés-Sosa, P. A., Miwakeichi, F., Goldman, R. I., & Cohen, M. S. (2004) · NeuroImage · doi:10.1016/j.neuroimage.2004.03.038 · Cited by 326 · cited 2×
“Despite decades of study, the underlying relationship between EEG and fMRI is far from being understood [17], [29], [30], [32].”
BackgroundLinked independent component analysis for multimodal data fusion
Groves, A. R., Beckmann, C. F., Smith, S. M., & Woolrich, M. W. (2011) · NeuroImage · doi:10.1016/j.neuroimage.2010.09.073 · Cited by 319 · cited 4×
“Linked tensor ICA [154] has one factor matrix”
BackgroundMethodInfluentialNunez, P. L., & Silberstein, R. B. (2000) · Brain Topography · doi:10.1023/a:1026683200895 · Cited by 307 · cited 3×
“It is a well-accepted paradigm in neuroscience that EEG and fMRI carry complementary information about brain function [26], [28].”
BackgroundAlter, O., Brown, P. O., & Botstein, D. (2003) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0530258100 · Cited by 304 · cited 8×
“Ponna-palli et al. [171] extend this GSVD-based approach to more than two datasets.”
BackgroundInfluentialPlanck 2013 results. XII. Diffuse component separation
Planck Collaboration, Ade, P. A. R., Aghanim, N., Armitage-Caplan, C., Arnaud, M., Ashdown, M., Atrio-Barandela, F., Aumont, J., Baccigalupi, C., Banday, A. J., et al. (2014) · Astronomy & Astrophysics · doi:10.1051/0004-6361/201321580 · Cited by 294
Multiset canonical correlations analysis and multispectral, truly multitemporal remote sensing data
Nielsen, A. A. (2002) · IEEE Transactions on Image Processing · doi:10.1109/83.988962 · Cited by 293 · cited 2×
“1); covariations, as in CCA [1] and its extension to more than two matrices, multiset CCA (MCCA) [3], [58], [110], [118],”
BackgroundMethodChallenges and Opportunities of Multimodality and Data Fusion in Remote Sensing
Dalla Mura, M., Prasad, S., Pacifici, F., Gamba, P., Chanussot, J., & Benediktsson, J. A. (2015) · Proceedings of the IEEE · doi:10.1109/jproc.2015.2462751 · Cited by 286 · cited 1×
“contest of the IEEE Geoscience and Remote Sensing Society (GRSS) (see dedicated paper in this issue [44]).”
BackgroundIndependent Vector Analysis: An Extension of ICA to Multivariate Components
Kim, T., Eltoft, T., & Lee, T.-W. (2006) · Lecture Notes in Computer Science · doi:10.1007/11679363_21 · Cited by 284 · cited 3×
“P (m) = P that applies to all the involved mixtures [82], [109].”
BackgroundCanonical Analysis of Several Sets of Variables
Kettenring, J. R. (1971) · Biometrika · doi:10.2307/2334380 · Cited by 282
Cattell, R. B. (1944) · Psychometrika · doi:10.1007/bf02288739 · Cited by 279 · cited 3×
“, attach physical meaning to the output [2], [5].”
BackgroundLiu, J., Pearlson, G., Windemuth, A., Ruano, G., Perrone‐Bizzozero, N. I., & Calhoun, V. (2009) · Human Brain Mapping · doi:10.1002/hbm.20508 · Cited by 269 · cited 2×
“Parallel ICA [188] and IVA [108]–[111] (Example III-D.”
BackgroundMethodMultiway analysis of epilepsy tensors
Acar, E., Aykut-Bingol, C., Bingol, H., Bro, R., & Yener, B. (2007) · Bioinformatics · doi:10.1093/bioinformatics/btm210 · Cited by 267
Canonical Correlation Analysis for Data Fusion and Group Inferences
Correa, N., Adali, T., Li, Y.-O., & Calhoun, V. (2010) · IEEE Signal Processing Magazine · doi:10.1109/msp.2010.936725 · Cited by 264 · cited 6×
“, [21], [27], [58] (biomedical imaging) and [10], [11] (HMI).”
BackgroundMethodInfluentialNonparametric factor analysis with beta process priors
Paisley, J., & Carin, L. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553474 · Cited by 263 · cited 1×
“Another approach is to use sparsity [77]– [79].”
MethodNonrigid Image Registration Using Conditional Mutual Information
Loeckx, D., Slagmolen, P., Maes, F., Vandermeulen, D., & Suetens, P. (2010) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2009.2021843 · Cited by 257 · cited 1×
“One approach uses information theory and maximizes mutual information [148], [149].”
BackgroundRank, decomposition, and uniqueness for 3-way and n -way arrays
Kruskal, J. B. (1989) · Medical Entomology and Zoology · Cited by 253
An integrated approach to hydrologic data assimilation: interpolation, smoothing, and filtering
McLaughlin, D. (2002) · Advances in Water Resources · doi:10.1016/s0309-1708(02)00055-6 · Cited by 249 · cited 3×
“, [19], [47], [48] and references therein.”
BackgroundAdali, T., Anderson, M., & Fu, G.-S. (2014) · IEEE Signal Processing Magazine · doi:10.1109/msp.2014.2300511 · Cited by 232 · cited 25×
“The ability of IVA to obviate the need to match the outputs of M separate ICA soon turned out useful far beyond convolutive mixtures: it has since been applied to fMRI group data analysis [112], [113], multimodal fusion of several brain-imaging modalities [114], and the analysis of temporal dynamic changes [115].”
BackgroundInfluentialOn Kruskal’s uniqueness condition for the Candecomp/Parafac decomposition
Stegeman, A., & Sidiropoulos, N. D. (2007) · Linear Algebra and its Applications · doi:10.1016/j.laa.2006.08.010 · Cited by 228 · cited 2×
“, [72], [92]) where denotes the column-wise Khatri-Rao product and kA is the Kruskal-rank of matrix A, equal to the largest integer kA such that every subset of kA columns of A is linearly independent [67].”
BackgroundJoint Blind Source Separation With Multivariate Gaussian Model: Algorithms and Performance Analysis
Anderson, M., Adali, T., & Li, X.-L. (2012) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2011.2181836 · Cited by 225
Feature-Based Fusion of Medical Imaging Data
Calhoun, V. D., & Adali, T. (2009) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2008.923773 · Cited by 225 · cited 7×
“, [21], [27], [58] (biomedical imaging) and [10], [11] (HMI).”
BackgroundMethodInfluentialTensor decompositions for feature extraction and classification of high dimensional datasets
Phan, A. H., & Cichocki, A. (2010) · Nonlinear Theory and Its Applications, IEICE · doi:10.1587/nolta.1.37 · Cited by 210 · cited 1×
“ization (CMTF) [99], linked multiway component analysis (LMWCA) [65], and others [140]–[142].”
Sorber, L., Van Barel, M., & De Lathauwer, L. (2015) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2015.2400415 · Cited by 209 · cited 19×
“Following from [8], [9], [16], [19] (and others), and further”
BackgroundMethodInfluentialCramer-Rao lower bounds for low-rank decomposition of multidimensional arrays
Liu, X., & Sidiropoulos, N. D. (2001) · IEEE Transactions on Signal Processing · doi:10.1109/78.942635 · Cited by 206 · cited 9×
“For example, a specific arrangement of a receive antenna array or other properties of a communication system may be imposed via a Vandermonde [72]–[75] or Toeplitz [76] structure.”
BackgroundInfluentialEra of Big Data Processing: A New Approach via Tensor Networks and Tensor Decompositions
Cichocki, A. S. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1403.2048 · Cited by 201 · cited 1×
“Third, modularity of the formulation makes it easier to adapt it to computational challenges such as large-scale data [16], [65], [162], [210], [211].”
BackgroundNeuronal chronometry of target detection: Fusion of hemodynamic and event-related potential data
Calhoun, V. D., Adali, T., Pearlson, G. D., & Kiehl, K. A. (2006) · NeuroImage · doi:10.1016/j.neuroimage.2005.08.060 · Cited by 194
Longbotham, N., Pacifici, F., Glenn, T., Zare, A., Volpi, M., Tuia, D., Christophe, E., Michel, J., Inglada, J., Chanussot, J., et al. (2012) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2011.2179638 · Cited by 182 · cited 1×
“Problems addressed include multi-modal change detection, in which the purpose is to detect changes in an area before and after an event (a flood, in this case), given SAR and multispectral imaging [45], using either all or part of the modalities; multi-”
MethodVervliet, N., Debals, O., Sorber, L., & De Lathauwer, L. (2014) · IEEE Signal Processing Magazine · doi:10.1109/msp.2014.2329429 · Cited by 179 · cited 2×
“Third, modularity of the formulation makes it easier to adapt it to computational challenges such as large-scale data [16], [65], [162], [210], [211].”
BackgroundAnalysis of Multimodal Neuroimaging Data
Bießmann, F., Plis, S., Meinecke, F. C., Eichele, T., & Müller, K. (2011) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2011.2170675 · Cited by 177 · cited 11×
“EEG and MEG data are a set of timeseries signals reflecting voltage or neuromagnetic field changes recorded at each of the (usually a few dozen of) electrodes attached to the scalp (EEG) or fixed within an MEG scanner helmet.”
BackgroundMethodInfluentialMa, S., Calhoun, V. D., Phlypo, R., & Adalı, T. (2014) · NeuroImage · doi:10.1016/j.neuroimage.2013.12.063 · Cited by 174 · cited 1×
“brain-imaging modalities [114], and the analysis of temporal dynamic changes [115].”
BackgroundHow can EEG/MEG and fMRI/PET data be combined?
Horwitz, B., & Poeppel, D. (2002) · Human Brain Mapping · doi:10.1002/hbm.10057 · Cited by 172 · cited 2×
“The fact that there is no ground truth is reflected in the very broad range of methods and approaches that are being proposed [12], [15], [17], [21], [28]–[31].”
BackgroundData Fusion: Concepts and Ideas
Mitchell, H. B. (2012) · Springer eBooks · doi:10.1007/978-3-642-27222-6 · Cited by 155
Domanov, I., & Lathauwer, L. D. (2013) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/120877258 · Cited by 155
Sørensen, M., & Lathauwer, L. D. (2013) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2013.2276416 · Cited by 155 · cited 2×
“A second generalization is by combining several types of constraints and assumptions: for example, PARAFAC may be combined with statistical independence [104], [138], nonnegativity, sparsity, as well as structure of the latent factors: Vandermonde [72]–[75], Toeplitz [76], among others [16], [65], [106], [139].”
BackgroundIndependent vector analysis (IVA): Multivariate approach for fMRI group study
Lee, J., Lee, T.-W., Jolesz, F. A., & Yoo, S. (2007) · NeuroImage · doi:10.1016/j.neuroimage.2007.11.019 · Cited by 153 · cited 1×
“The ability of IVA to obviate the need to match the outputs of M separate ICA soon turned out useful far beyond convolutive mixtures: it has since been applied to fMRI group data analysis [112], [113], multimodal fusion of several”
MethodHigher Order Partial Least Squares (HOPLS): A Generalized Multilinear Regression Method
Zhao, Q., Caiafa, C. F., Mandic, D. P., Chao, Z. C., Nagasaka, Y., Fujii, N., Zhang, L., & Cichocki, A. S. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.254 · Cited by 152
Correa, N. M., Eichele, T., Adalı, T., Li, Y.-O., & Calhoun, V. D. (2010) · NeuroImage · doi:10.1016/j.neuroimage.2010.01.062 · Cited by 151 · cited 2×
“An approach that merges the two, and thus expected to better exploit the whole raw data, is proposed in [166] for the fusion of fMRI and EEG.”
BackgroundA Unified View of Matrix Factorization Models
Singh, A. P., & Gordon, G. J. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-87481-2_24 · Cited by 150 · cited 4×
“, [16], [161], [163] and references therein.”
BackgroundInfluentialOmberg, L., Golub, G. H., & Alter, O. (2007) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0709146104 · Cited by 149
Data preprocessing and the extended PARAFAC model
Harshman, R. A. (1984) · Medical Entomology and Zoology · Cited by 148
Link prediction in heterogeneous data via generalized coupled tensor factorization
Ermiş, B., Acar, E., & Cemgil, A. T. (2013) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-013-0341-y · Cited by 144 · cited 5×
“Depending on the analytical framework that we choose (Section V-C), each data set or the whole ensemble is attributed with a loss/objective function DðmÞð ; Þ, between observed and modeled data [153], [156], [161].”
BackgroundMethodInfluentialA unified framework for group independent component analysis for multi-subject fMRI data
Guo, Y., & Pagnoni, G. (2008) · NeuroImage · doi:10.1016/j.neuroimage.2008.05.008 · Cited by 144 · cited 1×
“[201] propose a tensor extension to group ICA [174], [175] and to tensor ICA [104] that can accom-”
BackgroundSui, J., He, H., Pearlson, G. D., Adali, T., Kiehl, K. A., Yu, Q., Clark, V. P., Castro, E., White, T., Mueller, B. A., et al. (2013) · NeuroImage · doi:10.1016/j.neuroimage.2012.10.051 · Cited by 143 · cited 1×
“As an example, a solution that maximally retains the joint information while also ensuring that the decomposed sources are independent from each other, in the context of a “joint ICA”-based approach, is proposed in [117].”
BackgroundDetermination and Proof of Minimum Uniqueness Conditions for PARAFAC1
Harshman, R. A. (1972) · Cited by 143
Audiovisual Information Fusion in Human–Computer Interfaces and Intelligent Environments: A Survey
Shivappa, S. T., Trivedi, M. M., & Rao, B. D. (2010) · Proceedings of the IEEE · doi:10.1109/jproc.2010.2057231 · Cited by 141 · cited 13×
“, [21], [27], [58] (biomedical imaging) and [10], [11] (HMI).”
BackgroundInfluentialIndependent component analysis and (simultaneous) third-order tensor diagonalization
Lathauwer, L. D., Moor, B. D., & Vandewalle, J. P. L. (2001) · IEEE Transactions on Signal Processing · doi:10.1109/78.950782 · Cited by 138
Constraint on neutrino masses from SDSS-III/BOSS Lyα forest and other cosmological probes
Palanque-Delabrouille, N., Yéche, C., Lesgourgues, J., Rossi, G., Borde, A., Viel, M., Aubourg, É., Kirkby, D., LeGoff, J., Rich, J., et al. (2014) · Journal of Cosmology and Astroparticle Physics · doi:10.1088/1475-7516/2015/02/045 · Cited by 134 · cited 1×
“surveys, galaxy clustering [54], [55], and stacked gravitational lensing, also serve as important cosmological probes [51], [52].”
BackgroundNonparametric Bayesian sparse factor models with application to gene expression modeling
Knowles, D. A., & Ghahramani, Z. (2011) · The Annals of Applied Statistics · doi:10.1214/10-aoas435 · Cited by 132 · cited 1×
“Another approach is to use sparsity [77]– [79].”
MethodJoint Matrices Decompositions and Blind Source Separation
Chabriel, G., Kleinsteuber, M., Moreau, É., Shen, H., Tichavský, P., & Yeredor, A. (2014) · ASEP · doi:10.1109/msp.2014.2298045 · Cited by 127 · cited 1×
“We mention [111], [190], [191] as just a few examples; further discussion is beyond the scope of this paper.”
BackgroundDomanov, I., & Lathauwer, L. D. (2013) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/120877234 · Cited by 125
Domanov, I., & Lathauwer, L. D. (2014) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/130916084 · Cited by 124 · cited 3×
“In the presence of two datasets, or in a noise-free scenario, many matrix-and tensor-based methods can be reformulated as GEVD [197].”
MethodSørensen, M., & Lathauwer, L. D. (2015) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/140956853 · Cited by 121 · cited 20×
“As noted, e.g., by [4], [5], [70], [89], [105], the CPD can be thought of as a generalization of FA, as follows.”
BackgroundInfluentialDomanov, I., Lieven, & Lathauwer, D. (2016) · Cited by 121
Non-EEG seizure-detection systems and potential SUDEP prevention: State of the art
de Vel, A. V., Cuppens, K., Bonroy, B., Milošević, M., Jansen, K., Huffel, S. V., Vanrumste, B., Lagae, L., & Ceulemans, B. (2013) · Seizure · doi:10.1016/j.seizure.2013.02.012 · Cited by 120 · cited 2×
“Due to the fact that epileptic seizures vary within and across patients, and due to the complex relations between different body systems, it is likely that any such system should rely on more than one modality [38].”
BackgroundIdentifiability results for blind beamforming in incoherent multipath with small delay spread
Sidiropoulos, N. D., & Liu, X. (2001) · IEEE Transactions on Signal Processing · doi:10.1109/78.890366 · Cited by 120 · cited 1×
“[74] N.”
On the Definition of Information Fusion as a Field of Research
Boström, H., Andler, S. F., Brohede, M., Johansson, R., Karlsson, A., van Laere, J., Niklasson, L., Nilsson, M., Persson, A., & Ziemke, T. (2007) · Cited by 119
A graphical model for audiovisual object tracking
Beal, M. J., Jojić, N., & Attias, H. T. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1206512 · Cited by 114 · cited 3×
“[24] propose a graphical model for audio-visual object tracking in which they”
BackgroundMethodKruskal, J. B. (1976) · Psychometrika · doi:10.1007/bf02293554 · Cited by 112 · cited 5×
“trices A,B,C need not be full column rank [67], [89] [90, Theorem 2.”
BackgroundInfluentialIndependent Vector Analysis: Definition and Algorithms
Kim, T., Lee, I., & Lee, T.-W. (2006) · doi:10.1109/acssc.2006.354986 · Cited by 111 · cited 20×
“It should be noted that the uniqueness results for coupled CPD [90] (Example III-D.2) require at least one tensor of order larger than two in the coupled set and thus they cannot be applied to IVA. x ( M ) dependentstatistically statistically dependent Example III-D.2: Coupled Tensor Decompositions.”
BackgroundMethodInfluentialPonnapalli, S. P., Saunders, M. A., Loan, C. F. V., & Alter, O. (2011) · PLoS ONE · doi:10.1371/journal.pone.0028072 · Cited by 108
Understanding data fusion within the framework of coupled matrix and tensor factorizations
Acar, E., Rasmussen, M. A., Savorani, F., Næs, T., & Bro, R. (2013) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2013.06.006 · Cited by 107 · cited 12×
“ization (CMTF) [99], linked multiway component analysis (LMWCA) [65], and others [140]–[142].”
BackgroundInfluentialAn Algorithm For Generic and Low-Rank Specific Identifiability of Complex Tensors
Chiantini, L., Ottaviani, G., & Vannieuwenhoven, N. (2014) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/140961389 · Cited by 107
Fetal electrocardiogram extraction by source subspace separation
Lathauwer, L. D., Moor, B. D., & Vandewalle, J. P. L. (1995) · Cited by 106
Constraining Inert Dark Matter by R γγ and WMAP data
Krawczyk, M., Sokołowska, D., Swaczyna, P., & Świeżewska, B. (2013) · Journal of High Energy Physics · doi:10.1007/jhep09(2013)055 · Cited by 98 · cited 1×
“as the Large Hadron Collider Higgs data [56].”
MethodKiers, H. A. L., & ten Berge, J. M. F. (1994) · British Journal of Mathematical and Statistical Psychology · doi:10.1111/j.2044-8317.1994.tb01027.x · Cited by 95 · cited 2×
“SCA-based methods [98], [176]–[178], and numerous cou-”
MethodMulti-Modal and Multi-Temporal Data Fusion: Outcome of the 2012 GRSS Data Fusion Contest
Berger, C. R., Voltersen, M., Eckardt, R., Eberle, J., Heyer, T., Salepci, N., Hese, S., Schmullius, C., Tao, J., Auer, S., et al. (2013) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2013.2245860 · Cited by 93 · cited 3×
“modal multi-temporal data fusion of optical, SAR and LiDAR images taken at different years over the same urban area [41], where suggested applications include assessing urban density, change detection and overcoming adverse illumination conditions for optical sensors; and proposing new methods for fusing hyperspectral…”
BackgroundMethodInfluentialBlind Deconvolution of DS-CDMA Signals by Means of Decomposition in Rank-(1, L, L) Terms
Lathauwer, L. D., & de Baynast, A. (2008) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2007.910469 · Cited by 92 · cited 4×
“be combined with statistical independence [104], [138], nonnegativity, sparsity, as well as structure of the latent factors: Vandermonde [72]–[75], Toeplitz [76], among others [16], [65], [106], [139].”
BackgroundInfluentialDomanov, I., & Lathauwer, L. D. (2016) · Linear Algebra and its Applications · doi:10.1016/j.laa.2016.10.019 · Cited by 89 · cited 1×
“2: Coupled Tensor Decompositions: In multilinear algebra, an ongoing endeavour is to obtain uniqueness conditions on a tensor decomposition [67], [88], [92]–[97].”
BackgroundOverview of constrained PARAFAC models
Favier, G., & de Almeida, A. L. F. (2014) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/1687-6180-2014-142 · Cited by 87 · cited 1×
“Relaxing the sum-ofrank-1-terms constraint in PARAFAC leads to more flexible tensor decompositions such as Tucker [6], [7], block term decomposition (BTD) [135], three-way decomposition into directional components (DEDICOM) [136], and others [137].”
BackgroundJoint blind source separation by generalized joint diagonalization of cumulant matrices
Li, X.-L., Adalı, T., & Anderson, M. (2011) · Signal Processing · doi:10.1016/j.sigpro.2011.04.016 · Cited by 83 · cited 13×
“The goal of FA and BSS is to represent X as a sum of low-rank terms with interpretable factors [65], where the difference lies in the type of assumptions being used.”
BackgroundMethodInfluentialDavid, N., Alpert, P., & Messer, H. (2009) · Atmospheric chemistry and physics · doi:10.5194/acp-9-2413-2009 · Cited by 83
Independent Vector Analysis: Identification Conditions and Performance Bounds
Anderson, M., Fu, G.-S., Phlypo, R., & Adalı, T. (2014) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2014.2333554 · Cited by 81 · cited 1×
“Identifiability analysis of the multiple types of diversity in IVA is given in [82], [123].”
BackgroundBayesian fusion of hyperspectral and multispectral images
Wei, Q., Nicolas Dobigeon, B., & Tourneret, J. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6854186 · Cited by 81 · cited 1×
“and multispectral images [183], [184], rely on a Bayesian framework for the decomposition.”
MethodPreserving subject variability in group fMRI analysis: performance evaluation of GICA vs. IVA
Michael, A. M., Anderson, M., Miller, R. L., Adalı, T., & Calhoun, V. D. (2014) · Frontiers in Systems Neuroscience · doi:10.3389/fnsys.2014.00106 · Cited by 80 · cited 1×
“The ability of IVA to obviate the need to match the outputs of M separate ICA soon turned out useful far beyond convolutive mixtures: it has since been applied to fMRI group data analysis [112], [113], multimodal fusion of several”
MethodAudiovisual Speech Source Separation: An overview of key methodologies
Rivet, B., Wang, W., Naqvi, S. M., & Chambers, J. A. (2014) · IEEE Signal Processing Magazine · doi:10.1109/msp.2013.2296173 · Cited by 77 · cited 3×
“astrophysics [59], biomedics [60], telecommunications [61], audio-vision [23], chemometrics [62], and more.”
BackgroundGeneric Uniqueness Conditions for the Canonical Polyadic Decomposition and INDSCAL
Domanov, I., & Lathauwer, L. D. (2015) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/140970276 · Cited by 76
A Method for Judicious Fusion of Inconsistent Multiple Sensor Data
Kumar, M., Garg, D. P., & Zachery, R. A. (2007) · IEEE Sensors Journal · doi:10.1109/jsen.2007.894905 · Cited by 75 · cited 2×
“[159] propose a Bayesian approach that can identify and eliminate spurious data from a sensor.”
BackgroundAlves, J., Bertout, C., Combes, F., Ferrara, A., Forveille, T., Guillot, T., Napiwotzki, R., Peter, H., Shore, S., Tolstoy, E., et al. (2014) · Astronomy and Astrophysics · doi:10.1051/0004-6361/201425195 · Cited by 73
A generic linked-mode decomposition model for data fusion
Mechelen, I. V., & Smilde, A. K. (2010) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2010.04.012 · Cited by 72
Constraint on neutrino masses from SDSS-III/BOSS Lyα forest and other cosmological probes
Palanque‐Delabrouille, N., Yèche, C., Roe, N. A., Ross, N. P., Schneider, D. P., Weinberg, D. H., Julien Lesgourgues, A., Rossi, G., Borde, A., Viel, M., et al. (2015) · RWTH Publications (RWTH Aachen) · Cited by 72
Sørensen, M., Domanov, I., & Lathauwer, L. D. (2015) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/140956865 · Cited by 70 · cited 1×
“12] and its multiset extension [3], [110], joint BSS [111], and coupled tensor decompositions [200].”
BackgroundVos, M. D., Lathauwer, L. D., Vanrumste, B., Huffel, S. V., & Paesschen, W. V. (2007) · Computational Intelligence and Neuroscience · doi:10.1155/2007/58253 · Cited by 69 · cited 1×
“[102] M.”
Sidiropoulos, N. D., Papalexakis, E. E., & Faloutsos, C. (2014) · IEEE Signal Processing Magazine · doi:10.1109/msp.2014.2329196 · Cited by 69 · cited 1×
“Third, modularity of the formulation makes it easier to adapt it to computational challenges such as large-scale data [16], [65], [162], [210], [211].”
BackgroundBayesian Group Factor AnalysisPreprint
Virtanen, S., Arto Klami, A., Khan, S. A., & Samuel Kaski, A. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1110.3204 · Cited by 67 · cited 3×
“Another example is Bayesian group FA [180] and its tensor extensions [142], [181], where a dedicated factor matrix determines which of the factors in a common pool are active”
BackgroundMethodExploratory analysis and data modeling in functional neuroimaging
Sommer, F. T., & Wichert, A. (2003) · Cited by 60
Tensor Decompositions: A New Concept in Brain Data Analysis?Preprint
Cichocki, A. S. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1305.0395 · Cited by 60 · cited 6×
“Generalized linked-mode for multiway data [8] and LMWCA [65] mention explicitly that they can be defined both with “soft” or “hard” links.”
BackgroundInfluentialGroup Nonnegative Matrix Factorization for EEG Classification
Lee, H., & Choi, S. (2009) · Cited by 59
Introduction to Hyperspectral Imaging
Deshpande, S. S., & Inamdar, A. B. (2023) · CRC Press eBooks · doi:10.1201/9781003329312-2 · Cited by 56
SCA with rotation to distinguish common and distinctive information in linked data
Schouteden, M., Deun, K. V., Pattyn, S., & Mechelen, I. V. (2013) · Behavior Research Methods · doi:10.3758/s13428-012-0295-9 · Cited by 53 · cited 1×
“The proposed approach, called distinctive and common components with simultaneous-component analysis (DISCO-SCA) [177], [193], [194], may outperform GSVD in certain scenarios and can be straightforwardly generalized to more than two datasets.”
MethodGeneralizing Caratheodory's uniqueness of harmonic parameterization to N dimensions
Sidiropoulos, N. D. (2001) · IEEE Transactions on Information Theory · doi:10.1109/18.923759 · Cited by 53 · cited 1×
“[73] N.”
Soft Nonnegative Matrix Co-Factorization
Seichepine, N., Essid, S., Févotte, C., & Cappé, O. (2014) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2014.2360141 · Cited by 51 · cited 2×
“Regularization terms may impose certain types of sparsity, non-negativity [196], similarity [145], [189], or coherence [209], to name a few.”
BackgroundGROUP ICA OF FUNCTIONAL MRI DATA: SEPARABILITY, STATIONARITY, AND INFERENCE
Calhoun, V. D., Adalı, T., Pearlson, G. D., & Pekar, J. J. (2001) · Cited by 49
Sørensen, M., & Lathauwer, L. D. (2016) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2016.2614797 · Cited by 49 · cited 3×
“of the involved CPDs, full column rank of the shared factor C, or a specific structure such as a Vandermonde matrix, also reinforces the uniqueness of the whole decomposition [90], [124].”
BackgroundPerforming DISCO-SCA to search for distinctive and common information in linked data
Schouteden, M., Deun, K. V., Wilderjans, T. F., & Mechelen, I. V. (2013) · Behavior Research Methods · doi:10.3758/s13428-013-0374-6 · Cited by 47 · cited 2×
“The proposed approach, called distinctive and common components with simultaneous-component analysis (DISCO–SCA) [177], [193], [194], may outperform GSVD in certain scenarios and can be straightforwardly generalized to more than two data sets.”
MethodAudio-Video Sensor Fusion with Probabilistic Graphical Models
Beal, M. J., Attias, H. T., & Jojić, N. (2002) · Lecture notes in computer science · doi:10.1007/3-540-47969-4_49 · Cited by 45
Liberman, Y., Samuels, R., Alpert, P., & Messer, H. (2014) · Atmospheric measurement techniques · doi:10.5194/amt-7-3549-2014 · Cited by 45 · cited 4×
“, [19], [47], [48] and references therein.”
BackgroundMethodInfluentialSecond-Order Multidimensional ICA: Performance Analysis
Lahat, D., Cardoso, J.-F., & Messer, H. (2012) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2012.2199985 · Cited by 45 · cited 1×
“IVA) leads to independent subspace analysis (ISA) [128]–[132] (resp.”
BackgroundSelf-citationLei, X., Valdes-Sosa, P. A., & Yao, D. (2012) · Journal of Integrative Neuroscience · doi:10.1142/s0219635212500203 · Cited by 45 · cited 1×
“Recent technological advances allow recording data from several functional brain imaging techniques simultaneously [26], [27], thus further motivating advanced data fusion.”
BackgroundYokoya, N., Yairi, T., & Iwasaki, A. (2011) · Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing · doi:10.1109/whispers.2011.6080924 · Cited by 42 · cited 1×
“Hence, there exists a tradeoff between spectral and spatial resolution [39], [40] [13, Chapter 9].”
BackgroundThe Infinite Hierarchical Factor Regression ModelPreprint
Rai, P., & Daumé, H. (2009) · arXiv (Cornell University) · doi:10.48550/arxiv.0908.0570 · Cited by 42 · cited 1×
“[78] P.”
Structure-revealing data fusion model with applications in metabolomics
Acar, E., Lawaetz, A. J., Rasmussen, M. A., & Bro, R. (2013) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2013.6610925 · Cited by 41 · cited 5×
“in CMTF [196], model constraints may be defined in the form of sparse weights such that unshared components have norms equal or close to zero in one of the datasets.”
BackgroundInfluentialDISCO-SCA and Properly Applied GSVD as Swinging Methods to Find Common and Distinctive Processes
Deun, K. V., Mechelen, I. V., Thorrez, L., Schouteden, M., Moor, B. D., WERF, M. J. V. D., Lathauwer, L. D., Smilde, A. K., & Kiers, H. A. L. (2012) · PLoS ONE · doi:10.1371/journal.pone.0037840 · Cited by 39 · cited 2×
“The proposed approach, called distinctive and common components with simultaneous-component analysis (DISCO-SCA) [177], [193], [194], may outperform GSVD in certain scenarios and can be straightforwardly generalized to more than two datasets.”
MethodWilderjans, T. F., Ceulemans, E., & Mechelen, I. V. (2008) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2008.09.031 · Cited by 39
Challenges in Multimodal Data Fusion
Lahat, D., Adalı, T., & Christian Jutten, B. (2014) · Cited by 39
Self-citationGroup Study of Simulated Driving fMRI Data by Multiset Canonical Correlation Analysis
Li, Y., Eichele, T., Calhoun, V. D., & Adalı, T. (2011) · Journal of Signal Processing Systems · doi:10.1007/s11265-010-0572-8 · Cited by 37
Learning Bimodal Structure in Audio–Visual Data
Monaci, G., Vandergheynst, P., & Sommer, F. T. (2009) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2009.2032182 · Cited by 37 · cited 3×
“For audio-visual data fusion, a dictionary learning model where each atom consists of an audio and video component has been proposed in [144].”
BackgroundMethodInfluentialJoint Independent Subspace Analysis Using Second-Order Statistics
Lahat, D., & Christian Jutten, B. (2016) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2016.2526960 · Cited by 36 · cited 2×
“joint independent subspace analysis (JISA) [119]–[121]) as well”
BackgroundSelf-citationJoint Source Estimation and Localization
Sahnoun, S., & Comon, P. (2015) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2015.2404311 · Cited by 34 · cited 1×
“Regularization terms may impose certain types of sparsity, non-negativity [196], similarity [145], [189], or coherence [209], to name a few.”
BackgroundSimultaneous analysis of coupled data matrices subject to different amounts of noise
Wilderjans, T. F., Ceulemans, E., Mechelen, I. V., & van den Berg, R. A. (2010) · British Journal of Mathematical and Statistical Psychology · doi:10.1348/000711010x513263 · Cited by 32 · cited 12×
“In some cases, it may be better to tailor loss functions individually to each dataset, and use norms other than Frobenius [8], [153].”
BackgroundMethodInfluentialSimultaneous Factor Analysis of Several Gramian Matrices
Levin, J. (1966) · Psychometrika · doi:10.1007/bf02289472 · Cited by 32 · cited 1×
“, by [4], [5], [70], [89], [105], the CPD can be thought of as a generalization of FA, as follows.”
BackgroundSources indentification: a solution based on the cumulants
Lacoume, J., & Ruiz, P. (2003) · ASSP Workshop on Spectrum Estimation and Modeling · doi:10.1109/spect.1988.206191 · Cited by 31 · cited 1×
“) samples, mixed by an invertible A, cannot be blindly separated based on their observations x(t) alone [71], [107].”
BackgroundBlind Identification and Separation of Complex‐Valued Signals
Moreau, É., & Adalı, T. (2013) · Wiley eBooks · doi:10.1002/9781118579749 · Cited by 31
Bayesian Multi-view Tensor Factorization
Khan, S. A., & Kaski, S. (2014) · Lecture notes in computer science · doi:10.1007/978-3-662-44848-9_42 · Cited by 30 · cited 3×
“Another example is Bayesian group FA [180] and its tensor extensions [142], [181], where a dedicated factor matrix determines which of the factors in a common pool are active”
BackgroundMethodCoupled tensor decompositions for applications in array signal processing
Sørensen, M., & Lathauwer, L. D. (2013) · IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing · doi:10.1109/camsap.2013.6714049 · Cited by 29 · cited 1×
“Coupled tensor decompositions have already proven useful in telecommunications [125], multidimensional harmonic retrieval (MHR) [124], chemometrics and psychometrics [8], [99], and more.”
BackgroundIdentifying common and distinctive processes underlying multiset data
Deun, K. V., Smilde, A. K., Thorrez, L., Kiers, H. A. L., & Mechelen, I. V. (2013) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2013.07.005 · Cited by 27 · cited 2×
“Simultaneous factor analysis (FA) [152] and simultaneous component analysis (SCA)-based methods [98], [176]–[179] deal with multiway data that have at least one shared mode, but do not stack it in a single tensor (Section III-C2) due to various complicating factors, such as those mentioned in Section IV.”
BackgroundMethodA combination of parallel factor and independent component analysis
Vos, M. D., Nion, D., Huffel, S. V., & Lathauwer, L. D. (2012) · Signal Processing · doi:10.1016/j.sigpro.2012.05.032 · Cited by 27 · cited 1×
“A second generalization is by combining several types of constraints and assumptions: for example, PARAFAC may be combined with statistical independence [104], [138], nonnegativity, sparsity, as well as structure of the latent factors: Vandermonde [72]–[75], Toeplitz [76], among others [16], [65], [106], [139].”
BackgroundLinked PARAFAC/CP Tensor Decomposition and Its Fast Implementation for Multi-block Tensor Analysis
Yokota, T., Cichocki, A. S., & Yamashita, Y. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-34487-9_11 · Cited by 25 · cited 1×
“A second generalization is by combining several types of constraints and assumptions: for example, PARAFAC may be combined with statistical independence [104], [138], nonnegativity, sparsity, as well as structure of the latent factors: Vandermonde [72]–[75], Toeplitz [76], among others [16], [65], [106], [139].”
BackgroundRoover, K. D., Ceulemans, E., Timmerman, M. E., Nezlek, J. B., & Onghena, P. (2013) · Psychometrika · doi:10.1007/s11336-013-9318-4 · Cited by 25 · cited 3×
“SCA-based methods [98], [176]–[178], and numerous cou-”
MethodMiron, S., Dossot, M., Carteret, C., Margueron, S. H., & Brie, D. (2010) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2010.10.005 · Cited by 22 · cited 1×
“variables) [98]; in chemometrics and metabolomics, (sample ⇥ frequency ⇥ emission profile ⇥ excitation profile) [8], [62], [99]; in polarized Raman spectroscopy, (polarization ⇥ spatial diversity ⇥ wavenumber) [100]; in EEG, (time ⇥ frequency ⇥ electrode) [101]–[103]; and in fMRI, (voxels ⇥ scans ⇥ subjects) [104].”
Multidataset independent subspace analysis extends independent vector analysis
Silva, R. F., Plis, S., Adalı, T., & Calhoun, V. D. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025579 · Cited by 22 · cited 1×
“[120] R.”
de Almeida, A. L. F., Luciani, X., Stegeman, A., & Comon, P. (2012) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2012.2208956 · Cited by 21 · cited 1×
“[85] A.”
A performance study of various brain source imaging approaches
Becker, H., Albera, L., Comon, P., Gribonval, R., Wendling, F., & Merlet, I. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6854729 · Cited by 20 · cited 1×
“A large number of solutions are based on adding various priors to the EEG data [34].”
BackgroundBayesian fusion of multispectral and hyperspectral images with unknown sensor spectral response
Wei, Q., Nicolas Dobigeon, B., & Tourneret, J. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025140 · Cited by 19
Wilderjans, T. F., Ceulemans, E., & Mechelen, I. V. (2012) · Psychometrika · doi:10.1007/s11336-012-9275-3 · Cited by 17 · cited 6×
“The link is established via the shared “patients” mode [155].”
BackgroundMethodInfluentialJoint BSS as a natural analysis framework for EEG-hyperscanning
Chatel-Goldman, J., Congedo, M., & Phlypo, R. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6637843 · Cited by 16 · cited 1×
“, non-spectrally-flat) or non-stationary sources [111], [122] (recall Section III-C1).”
On the added value of multiset methods for three-way data analysis
Roover, K. D., Timmerman, M. E., Mechelen, I. V., & Ceulemans, E. (2013) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2013.05.002 · Cited by 16 · cited 1×
“SCA-based methods [98], [176]–[178], and numerous cou-”
Blind Separation of Instantaneous Mixtures of Dependent Sources
Castella, M., & Comon, P. (2007) · Springer eBooks · doi:10.1007/978-3-540-74494-8_2 · Cited by 15 · cited 1×
“IVA) leads to independent subspace analysis (ISA) [128]–[132] (resp. joint independent subspace analysis (JISA) [119]–[121]) as well as other BSS models [133], [134].”
MethodOptimal weight learning for Coupled Tensor Factorization with mixed divergences
Şimşekli, U., Ermiş, B., Cemgil, A. T., & Acar, E. (2013) · Research at the University of Copenhagen (University of Copenhagen) · doi:10.5072/zenodo.24736 · Cited by 14 · cited 3×
“Such is the case in the GCTF framework [156], [161], for example.”
BackgroundMethodJoint Blind Source Separation of Multidimensional Components: Model and Algorithm
Lahat, D., & Jutten, C. (2014) · HAL (Le Centre pour la Communication Scientifique Directe) · Cited by 12
Self-citationSidiropoulos, N. D., & Bro, R. (2002) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2000.860918 · Cited by 11 · cited 10×
“Hence, the contribution of each “diversity” to the model can now be characterized and quantified [57], [82].”
BackgroundInfluentialSCREAM: A novel method for multi-way regression problems with shifts and shape changes in one mode
Marini, F., & Bro, R. (2013) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2013.09.012 · Cited by 11 · cited 1×
“A regression method that can accommodate such variability in multiway arrays is proposed in [151], and a multimodal audio-visual calibration technique is given in [25].”
Method
Research works printed but not linked: 11
- lederman, 2015, Common manifold learning using alternating-diffusion
- stompor, 0, Data analysis of massive data sets a Planck example, LOFAR Workshop
- seyyedi, 2010, Comparing satellite derived rainfall with ground based radar for North-Western Europe
- harshman, 1972, PARAFAC2: Mathematical and technical notes, UCLA Working Papers Phonet, 22, 30
- cardoso, 0, The three easy routes to independent component analysis; contrasts and geometry, Proc ICA, 1
- sorber, 2014, Tensorlab v2 0
- 0, Joint data analysis for enhanced knowledge discovery in metabolomics
- sørensen, 2013, Multidimensional harmonic retrieval via coupled canonical polyadic decomposition
- comon, 0, Supervised classification, a probabilistic approach, Proc Eur Symp Artif Neural Netw, 111
- harshman, 0, Models for analysis of asymmetrical relationships among $N$ objects or stimuli, Proc Joint Meeting of the Psychometric Society and the Society for Mathematical Psychology, 1
- adal?, 2013, IEEE Trans Multimedia, 15
Cited by
Tensor Decomposition for Signal Processing and Machine Learning
Sidiropoulos, N. D., De Lathauwer, L., Fu, X., Huang, K., Papalexakis, E. E., & Faloutsos, C. (2017) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2017.2690524 · Cited by 1,617
Deep multimodal learning: a survey on recent advances and trends
Ramachandram, D., & Taylor, G. W. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2738401 · Cited by 1,139
“For the purposes of our review, we adopt the definition provided by Lahat et al. [2], where we consider phenomena or systems that are observed using multiple sensors and each sensor output can be termed a modality associated with a single data set.”
MethodA survey on deep learning for multimodal data fusion
Gao, J., Li, P., Chen, Z., & Zhang, J. (2020) · Neural Computation · doi:10.1162/neco_a_01273 · Cited by 821
“The reasonable fusion of these multimodal data can help us better understand the event of interest, especially when one modality is incomplete (Khaleghi, Khamis, Karray, & Razavi, 2013; Lahat, Adali, & Jutten, 2015).”
BackgroundGeneralizing from a Few Examples: A Survey on Few-Shot Learning
Wang, Y., Yao, Q., Kwok, J. T.-Y., & Ni, L. M.-S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.05046 · Cited by 772
“in E to make the learning of the supervised targetT feasible. Existing FSL methods use prior knowledge from a single modality, which is the output of a sensor for observing some phenomena or systems [61], such as images, texts, and videos. However, multi-modality prior knowledge can be used to provide a prior knowledg…”
MethodDeep learning in multimodal remote sensing data fusion: A comprehensive review
Li, J., Hong, D., Gao, L., Yao, J., Zheng, K., Zhang, B., & Chanussot, J. (2022) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2022.102926 · Cited by 630
Metadata
- Authors
- Lahat, D., Adali, T., & Jutten, C.
- Affiliations
- Centre National de la Recherche Scientifique (FR)
- ORCID
- Lahat, Dana
- Venue
- Proceedings of the IEEE
- Published
- 2015-09
- Volume
- 103
- Issue
- 9
- Pages
- 1449-1477
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W1539811621
- Cited by
- 1,296
- References
- 218
- Citations by year
- 2026: 155 · 2025: 239 · 2024: 177 · 2023: 135 · 2022: 123 · 2021: 102 · 2020: 105 · 2019: 93 · 2018: 69 · 2017: 63 · 2016: 31 · 2015: 4
- FWCI
- 18.08
- Type
- journal article
- Language
- en
- Open access
- green
- hal.science
- Locations
- Proceedings of the IEEE (publishedVersion)
- HAL (submittedVersion, other-oa)
- Maryland Shared Open Access Repository (USMAI Consortium) (submittedVersion)
- Digital Repository at the University of Maryland (University of Maryland College Park)
- Funders
- Project CHESS (2012-ERC-AdG-320684))
- National Science Foundation (NSF) (IIS 1017718, CCF 1117056)
- Topics
- Physical Sciences › Mathematics › Computational Mathematics › Tensor decomposition and applications
- Physical Sciences › Engineering › Media Technology › Advanced Image Fusion Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- multimodal fusion, modality, diversity, matrix factorization, tensor decomposition
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.