The DOI matches its Crossref record; 61 of the 61 references it cites were found in a registry or an index.
Separating Style and Content with Bilinear Models
Abstract
Perceptual systems routinely separate “content” from “style,” classifying familiar words spoken in an unfamiliar accent, identifying a font or handwriting style across letters, or recognizing a familiar face or object seen under unfamiliar viewing conditions. Yet a general and tractable computational model of this ability to untangle the underlying factors of perceptual observations remains elusive (Hofstadter, 1985). Existing factor models (Mardia, Kent, & Bibby, 1979; Hinton & Zemel, 1994; Ghahramani, 1995; Bell & Sejnowski, 1995; Hinton, Dayan, Frey, & Neal, 1995; Dayan, Hinton, Neal, & Zemel, 1995; Hinton & Ghahramani, 1997) are either insufficiently rich to capture the complex interactions of perceptually meaningful factors such as phoneme and speaker accent or letter and font, or do not allow efficient learning algorithms. We present a general framework for learning to solve two-factor tasks using bilinear models, which provide sufficiently expressive representations of factor interactions but can nonetheless be fit to data using efficient algorithms based on the singular value decomposition and expectation-maximization. We report promising results on three different tasks in three different perceptual domains: spoken vowel classification with a benchmark multi-speaker database, extrapolation of fonts to unseen letters, and translation of faces to novel illuminants.
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
“GeAN also uses the bilinear model [29,30] to distil the knowledge interwoven in these representations by allowing each node and edge to collaboratively modulate each other's contributions through a shared learning space.”
From TVGeAN: Tensor Visibility Graph-Enhanced Attention Network for Versatile Multivariant Time Series Learning Tasks (2024) · cites this paper as [29]
Citations
Cites
Maximum Likelihood from Incomplete Data Via the EM Algorithm
Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1977.tb01600.x · Cited by 50,444
Neural networks for pattern recognition
Bishop, C. (1994) · Choice Reviews Online · doi:10.5860/choice.31-5500 · Cited by 18,537
Press, W. H., Teukolsky, S. A., Vetterling, W. T., & Flannery, B. P. (1994) · Cited by 15,411
Turk, M., & Pentland, A. (1991) · Journal of Cognitive Neuroscience · doi:10.1162/jocn.1991.3.1.71 · Cited by 13,733
(1973) · CERN Document Server (European Organization for Nuclear Research) · Cited by 12,895
Numerical recipes in Pascal: the art of scientific computing
(1990) · Choice Reviews Online · doi:10.5860/choice.27-5158 · Cited by 12,040
An Information-Maximization Approach to Blind Separation and Blind Deconvolution
Bell, A. J., & Sejnowski, T. J. (1995) · Neural Computation · doi:10.1162/neco.1995.7.6.1129 · Cited by 8,986
Shape and motion from image streams under orthography: a factorization method
Tomasi, C., & Takeo Kanade, A. (1992) · International Journal of Computer Vision · doi:10.1007/bf00129684 · Cited by 2,879
Matrix Differential Calculus with Applications in Statistics and Econometrics.
Magnus, J. R., & Neudecker, H. (1988) · Biometrics · doi:10.2307/2531754 · Cited by 2,729
Classical Electrodynamics (2nd edn)
Brereton, M. (1976) · Physics Bulletin · doi:10.1088/0031-9112/27/8/041 · Cited by 2,612
Cited by
Sorted by citations
Items 701–800 of 839
Domain adaptive multiple kemel learning for handwritten digit recognition
Hosseinzadeh, H., & Razzazi, F. (2016) · Iranian Conference on Electrical Engineering · doi:10.1109/iraniancee.2016.7585829 · Cited by 1
“Tenenbaum and Freeman [17] have studied a bilinear model for separating the style and the content knowledge in a group of patterns.”
BackgroundSource Printer Authentication for Printed Documents Based on Factor Analysis
Jin, C., Liao, H., & Chen, Y. (2016) · Communications in computer and information science · doi:10.1007/978-981-10-3005-5_34 · Cited by 1
Face synthesis based on parts-based sparse component analysis face representation
Wang, C., Li, J., & Wang, B. (2017) · Optik · doi:10.1016/j.ijleo.2017.05.026 · Cited by 1
Improve Deep Learning with Unsupervised Objective
Zhang, S., Huang, K., Zhang, R., & Hussain, A. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-70087-8_74 · Cited by 1
Learning Shared and Specific Factors for Multi-modal Data
Yin, Q., Huang, Y., Wu, S., et al. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-7302-1_8 · Cited by 1
Efficient Cross-Modal Retrieval Using Social Tag Information Towards Mobile Applications
He, J., Wang, S., Qu, Q., et al. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-73521-4_10 · Cited by 1
Decoupling Respiratory and Angular Variation in Rotational X-ray Scans Using a Prior Bilinear Model
Geimer, T., Keall, P., Breininger, K., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-12939-2_40 · Cited by 1
A Deep Multimodal Approach for Map Image Classification
Sawada, T., & Katsurai, M. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054767 · Cited by 1
“Bilinear models [18], the origin of MCB pooling, calculates the outer product of the two feature vectors, enabling all the elements in the two vectors to participate in the training.”
BackgroundCompletely Unsupervised Cross-Modal Hashing
Duan, J., Zhang, P.-F., & Huang, Z. H. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59410-7_11 · Cited by 1
Cross-Modal Image Matching Based on Coupled Convolutional Sparse Coding and Feature Space Learning
Wang, C., Zhang, K., Gao, C., et al. (2020) · IEEE International Conference on Signal and Image Processing (ICSIP) · doi:10.1109/icsip49896.2020.9339467 · Cited by 1
“Tang&Wang [17] 81.0% PLS [18] 93.6% CCCA [19] 94.0% SliM [20] 94.0% Bilinear [21] 94.2% SCDL [7] 95.2% Yang.et al [5] 95.4% CDL [8] 97.4% CCSCL 98.0% In this paper, we proposed a cross-modal image matching method based on the coupled convolutional sparse coding and feature space learning.”
MethodInfluentialSet-Based Face Recognition Beyond Disentanglement: Burstiness Suppression With Variance Vocabulary
Wang, J., Zhao, Z., & Wu, F. Q. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3547794 · Cited by 1
“Disentangled representation learning (DRL) has been previously studied on the bilinear models [44], restricted Boltzmann machines [10, 37] and variational autoencoders [6, 16, 21, 23].”
MethodYamada, Y., Okoshi, T., & Nakazawa, J. (2023) · Journal of Information Processing · doi:10.2197/ipsjjip.31.246 · Cited by 1
FDDS: Feature Disentangling and Domain Shifting for Domain Adaptation
Chen, H., Gao, F., & Zhang, Q. (2023) · Mathematics · doi:10.3390/math11132995 · Cited by 1
Zhang, Y., Yamakata, Y., & Tajima, K. (2025) · Journal of Information Processing · doi:10.2197/ipsjjip.33.104 · Cited by 1
A Study of Synthesizing New Human Motions from Sampled Motions Using Tensor Decomposition
Rovshan, K., Cho, J., & Ohya, J. (2005) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2005.1521674 · Cited by 1
Computerized Face Recognition in Renaissance Portrait Art
Srinivasan, R., Roy–Chowdhury, A. K., & Rudolph, C. (2015) · eScholarship (California Digital Library) · Cited by 1
Investigating the Role of Saliency for Face Recognition
Srinivasan, R. (2015) · Cited by 1
Cross-Modal Learning with Images, Texts and Their Semantics
Xu, X. (2016) · Studies in computational intelligence · doi:10.1007/978-3-319-46245-5_10 · Cited by 1
Deep Temporal Feature Encoding for Action Recognition
Li, L., Zhang, Z., Huang, Y., et al. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8546263 · Cited by 1
Learning Discriminative and Complementary Patches for Face Recognition
Liu, Z., Tang, M., Hu, G., et al. (2019) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg.2019.8756598 · Cited by 1
“Group (2) can be further classified as (i) unsupervised learning [16], [27] or (ii) supervised learning [1], [4].”
BackgroundEnd-to-end response selection based on multi-level context response matching
Boussaha, B. E. A., Hernández, N., Jacquin, C., & Morin, E. (2020) · Computer Speech & Language · doi:10.1016/j.csl.2020.101080 · Cited by 1
Sheng, G., Zhang, C., Wu, H., et al. (2020) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-02112-w · Cited by 1
Temporal Bilinear Encoding Network of Audio-Visual Features at Low Sampling Rates
Hu, F., Mohedano, E., O'Connor, N. E., et al. (2020) · Dublin City University Open Access Institutional Repository (Dublin City University) · doi:10.48550/arxiv.2012.10283 · Cited by 1
“Compact Bilinear Pooling Second-order pooling methods (Tenenbaum and Freeman, 2000) have been shown to be effective at encoding local spatial information for fine-grained visual recognition tasks using CNN models (Lin et al., 2015; Yu et al., 2018).”
MethodMPNet: A Multiprocess Convolutional Neural Network for Animal Classification
Jiang, B., Huang, W., Huang, Y., et al. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-2540-4_42 · Cited by 1
Deep Learning Image Transfer by Simulation
Ammar, A. M., Ellafi, A. Y., Bozed, K. A., & Zerek, A. R. (2021) · IEEE International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA) · doi:10.1109/mi-sta52233.2021.9464412 · Cited by 1
Fine-Grained Image Recognition
Wei, X.-S. (2023) · Synthesis lectures on computer vision · doi:10.1007/978-3-031-31374-5_4 · Cited by 1
Classifying Multiple Imbalanced Attributes in Relational Data
Ghanem, A. S., Venkatesh, S., & WEST, G. A. W. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-10439-8_23 · Cited by 1
Learning Basis Representations of Inverse Dynamics Models for Real-Time Adaptive Control
Horiguchi, Y., Matsubara, T., & Kidode, M. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-17534-3_82 · Cited by 1
“Note that the learning procedure is inspired by the studies referred to as style content separation in several different contexts such as face recognition [ 8 ], the synthesis of human-like graphics [9] and learning stylistic movement primitives [10].”
MethodTensor Methods in Computer Vision
Cyganek, B. (2013) · doi:10.1002/9781118618387.ch2 · Cited by 1
Classification of double attributes via mutual suggestion between a pair of classifiers
Hiraoka, K., & Mishima, T. (2003) · International Conference on Neural Information Processing · doi:10.1109/iconip.2002.1198994 · Cited by 1
Bimode Mode for Face Recognition
Yan, H., Wang, J., & Yang, J. (2010) · Chinese Conference on Pattern Recognition · doi:10.1109/ccpr.2010.5659172 · Cited by 1
Facial Expression Analysis and Synthesis : a Bilinear Approach
Chang, J., Zheng, Y., & Wang, Z. (2007) · IEEE International Conference on Information Acquisition · doi:10.1109/icia.2007.4295777 · Cited by 1
“Then the shape of Based on linear suppose, multi-linear analysis [14], and texture of an exemplar face can be represented by [21]has been proved to be a powerful tool for the separation vectors Cex = ((X1i Yi, Z1) ... .,(K, YK, ZK)) C R3K which of content and style.”
MethodComplementary Discriminant Analysis for Classification of Double Attributes
Hiraoka, K., & Mishima, T. (2002) · Cited by 1
Towards a local-global visual feature-based framework for recognition
Zhao, Z. (2009) · Rutgers University Community Repository (Rutgers University) · doi:10.7282/t3bk1chq · Cited by 1
“[80] have applied a bilinear model to factor out the style”
MethodRelational clustering for knowledge discovery in life sciences
Giordani, I. (2010) · BOA (University of Milano-Bicocca) · Cited by 1
Numerical Linear Algebra in Data Mining
Eld, L. E. (2006) · Cited by 1
Compact discrete representations for scalable similarity search
Norouzi, M. (2016) · TSpace (University of Toronto) · Cited by 1
Preference modeling and Accuracy in Recommender Systems
Sharma, M. K. (2017) · University of Minnesota Digital Conservancy (University of Minnesota) · Cited by 1
Open-Ended Content-Style Recombination Via Leakage FilteringPreprint
Ridgeway, K., & Mozer, M. C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.00110 · Cited by 1
“Following tradition (Tenenbaum & Freeman, 2000), we refer to between-and within-class variation as content and style , respectively.”
MethodHigher-order Count Sketch: Dimensionality Reduction That Retains Efficient Tensor OperationsPreprint
Shi, Y., & Anandkumar, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.11261 · Cited by 1
“It has been used in a wide range of applications such as bilinear models (Tenenbaum and Freeman, 2000).”
MethodResonator Circuits for factoring high-dimensional vectorsPreprint
Kent, S. J., Frady, E. P., Sommer, F. T., et al. (2019) · arXiv (Cornell University) · Cited by 1
Alpha-Integration Pooling for Convolutional Neural NetworksPreprint
Eom, H., & Choi, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.03436 · Cited by 8
“This pooling method has arithmetic average-pooling and bilinear pooling [20] as a special case, but max-pooling is not included.”
MethodDisentangling images with Lie group transformations and sparse codingPreprint
Chau, H. Y., Qiu, F., Chen, Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.12071 · Cited by 1
“…an important task that many previous works have attempted to address using architectures such as bilinear models, manifold models and modified VAEs (Tenenbaum & Freeman, 2000; Grimes & Rao, 2005; Olshausen et al., 2007; DiCarlo & Cox, 2007; Cadieu & Olshausen, 2011; Bengio et al., 2013; Cheung et…”
BackgroundMethodInfluentialWill Multi-modal Data Improves Few-shot Learning?Preprint
Zhang, Z., Ma, S., & Zhang, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.11853 · Cited by 1
“Bilinear Pooling is adapted by [25] and [4].”
MethodChen, Y., Pan, Y., & Dong, D. (2021) · arXiv (Cornell University) · Cited by 1
Natural Scene Text Editing Based on AIPreprint
Zhang, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.15475 · Cited by 1
ChatGPT’s Studio Ghibli-style images show its creative power – but raise new copyright problems
Riemer, K., & Peter, S. (2025) · doi:10.64628/aa.an9ucwwat · Cited by 1
Learned Factorization Models to Explain Variability in Natural Image Sequences
Culpepper, B. J. (2011) · eScholarship (California Digital Library)
Face and Facial Expression Recognition using Three Dimensional Data
(2012) · SpringerReference · doi:10.1007/springerreference_72864
Wavelet-based Recognition of Facial Expressions and Faces
Poursaberi, A. (2014) · Libraries and Cultural Resources (University of Calgary) · doi:10.11575/prism/28676
Contributions au recalage d'images et à la reconstruction 3D de scènes rigides et déformables
Bartoli, A. (2008) · HAL
Face Recognition System Invariant to Light-Camera Setup
Dauthal, N., Prakash, S., & Gupta, P. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-27387-2_12
Modeling the fMRI signal via Hierarchical Clustered Hidden Process Models.
Niculescu, R. S., Mitchell, T. M., & Rao, R. B. (2007) · PubMed
Conversão de voz inter-linguística
Machado, A. F. (2013) · doi:10.11606/t.45.2013.tde-04062013-130812
“Uma boa alternativa para transformação destes parâmetros é a utilização de modelos bilineares [39; 59; 193; 266], que apresentam a vantagem de serem mais simples que os não-lineares e, em geral, mais expressivos que o modelo linear.”
BackgroundTHREE DIMENSIONAL MODELING AND ANIMATION OF FACIAL EXPRESSIONS
Lin, A. J. (2011) · UKnowledge (University of Kentucky)
Motion transformation by example
Popović, J., & Hsu, E. (2008) · DSpace@MIT (Massachusetts Institute of Technology)
Task Specific Factors for Video Characterization
Ranjeeth Kumar, M., Manikandan, S., & Jawahar, C. V. (2006) · Lecture notes in computer science · doi:10.1007/11949619_34
Rahman, M. M., & Ishikawa, S. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-30549-1_14
Speech Motion Decomposition and Editing
Cao, Y., Faloutsos, P., & Pighin, F. P. (2007) · Springer eBooks · doi:10.1007/978-1-84628-907-1_10
“Based on factorization [3, 4 ], their method produces a bilinear model that extracts emotion and content from input video sequences.”
Cross modal metric learning with multi-level semantic relevance
Yan, H., Wang, S., Zhao, Z., et al. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025625
“Query Others COLAR PLS[14] BLM [15] CCA[6] SM[6] SCM[6] GMMFA[7] GMLDA[7]”
BackgroundTransfer facial expressions with identical topology
Lin, A. J., & Cheng, F. F. (2013) · International Conference on Computer Games: AI, Animation, Mobile, Interactive Multimedia, Educational & Serious Games (CGAMES) · doi:10.1109/cgames.2013.6632622
“Vector-based muscle models place the heuristic muscles under the surface of the face [2, 3].”
BackgroundA multi-affine model for tensor decomposition
Yang, Y., Zhang, L., Wang, S., Jiang, H., Murphy, C. J., & Hoeve, J. V. (2011) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2011.6130408
“Tensor analysis has found applications in many computer vision and graphics problems, such as general factor analysis [5], geometric analysis [1], texture modeling [7, 10], face image recognition [9], 3D face transfer [8], and most recently face contour modeling [6].”
MethodSub-pattern bilinear model and its application in pose estimation of work-pieces
Ou, Z., Wang, P., Su, J., et al. (2011) · Neurocomputing · doi:10.1016/j.neucom.2011.12.012
“It is assumed that z is given by the general bilinear form [1]:”
BackgroundMethodInfluentialA Subspace Learning Based on a Rank Symmetric Relation for Fuzzy Kernel Discriminant Analysis
Yan, M. (2013) · Journal of Computers · doi:10.4304/jcp.8.2.380-387
“Most traditional algorithms, such as traditional principal component analysis (PCA) [1-3] and linear discriminant analysis (LDA) [4-9] put an image object as a 1-”
MethodDevelopment of invariant feature maps via a computational model of simple and complex cells
Huang, W., Ji, Z., Brumby, S. P., Kenyon, G. T., & Bettencourt, L. M. A. (2012) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2012.6252521
“However, instead of using third-order tensor for weight parameters (as presented in bilinear models [17], [18]), our model provides a factorized approach by the product of two second-order tensor for weight parameters, and thus makes learning simpler and more efficient (See the discussion part in Sec.”
BackgroundMethodVoice conversion using Bilinear Model integrated with joint GMM-based classification
Sun, X., Zhang, X., Yang, J., et al. (2013) · IEEE International Conference on Information Science and Technology (ICIST) · doi:10.1109/icist.2013.6747758
“It has been successfully applied in different perceptual tasks [1]: spoken vowel classification with a multi-speaker database, extrapolation of fonts to unseen letters, and translation of faces to novel illuminants.”
MethodInfluentialA Multifactor Winner-Take-All Dynamics
Zhu, J. (2011) · Neural Computation · doi:10.1162/neco_a_00136
“The factors, schematically termed content and style (Tenenbaum & Freeman, 2000 ), represent underlying causes that enable a parsimonious description or understanding of the world.”
BackgroundMethodInfluentialAdaptation of Acoustic Models in Joint Speaker and Noise Space Using Bilinear Models
Jeong, Y., & Kim, H. S. (2014) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e97.d.2195
“Thus, the bilinear model [4], the extension of the linear model to two factors, is a good candidate for the adaptation of acoustic models to both speaker and noise.”
MethodInfluentialView Independent Gait Identification Using a Particle Filter
Emoto, M., Hayashi, A., Suematsu, N., et al. (2006) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2006.116
“Using a Bilinear model [11], Cuzzolin et al.”
MethodA Novel Hebbian Rules Based Method for Computation of Sparse Coding Basis Vectors
Zou, B., Miao, J., Yang, X., et al. (2009) · International Conference on Natural Computation (ICNC) · doi:10.1109/icnc.2009.624
“put forward double linear model for sparse coding [5],”
BackgroundPark, S. W., & Savvides, M. (2006) · Lecture notes in computer science · doi:10.1007/11848035_21
“Traditionally, to solve the problem of tensor factorization for unknown factors, Tenenbaum and Freeman assume that there are limited numbers of Gaussian mixtures in the distribution of face images, and apply EM algorithm to get parameters of the Gaussian mixture models [ 5 ].”
MethodA NEW BILINEAR APPROACH FOR INCREMENTAL VISUAL LEARNING AND RECOGNITION
Nakouri, H., & Limam, M. (2013) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001413560089
Task Recognition and Style Analysis in Dance Sequences
Perera, M., Shiratori, T., Kudoh, S., et al. (2006) · IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI) · doi:10.1109/mfi.2006.265645
“They used it for separating style and content factors, and displayed two-mode examples in extrapolating fonts for unseen letters and translating face postures to new illuminations [12].”
BackgroundVariational Approximate Inference in Latent Linear Models
Challis, E. (2013) · UCL Discovery (University College London)
Weakly-Labeled Data and Identity-Normalization for Facial Image Analysis
Rim, D. (2013) · PolyPublie (École Polytechnique de Montréal)
Homeomorphic Manifold Analysis (HMA): Untangling Complex Manifolds
Elgammal, A. (2015) · Advances in imaging and electron physics · doi:10.1016/bs.aiep.2014.12.002
The Minimum Information Principlein Learning and Neural DataAnalysis
Globerson, A. (2005)
Learning the manifolds of local features and their spatialarrangements
Torki, M. (2011) · Rutgers University Community Repository (Rutgers University) · doi:10.7282/t34m93kt
“Such subspace analysis has been extended to d compose multiple orthogonal factors using bilinear models [120] and multi-linear tensor analy sis [129].”
MethodInterpolation on data with multiple attributes by a neural network
Azumi, H., Hiraoka, K., & Mishima, T. (2002)
Probabilistic models for mining imbalanced relational data
Ghanem, A. S. (2009)
Tensorial factorization methods for manipulation of face videos
Manikandan, S., Kumar, R. S., & Jawahar, C. V. (2006) · IET International Conference on Visual Information Engineering (VIE) · doi:10.1049/cp:20060577
“The resulting morph sequence was visually smooth indicating that the method can be used for generation of good quality morph sequence.”
InfluentialIdentification of block-oriented nonlinear systems based on input-output data
Li, G. (2011) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/48668
“Another common yet more general model in science and engineering is the following bilinear model [74].”
BackgroundFacial expression analysis on manifolds
Turk, M., & Chang, Y. H. (2006)
Multilinear Modeling for Robust Identity Recognition from Gait
Fabio Cuzzolin, A. (2010) · IGI Global eBooks · doi:10.4018/978-1-60566-725-6.ch008
“Bilinear models in particular (Tenenbaum & Freeman, 2000) are the best studied and probably the most popular among multilinear models.”
BackgroundMethodInfluentialVehicle Tracking and Recognition
Fan, G., Fan, X., Venkataraman, V., & Havlicek, J. (2009) · CRC Press eBooks · doi:10.1201/9781439813300-c6
Discovering Mid-level Visual Connections in Space and Time
Lee, Y. J., Efros, A. A., & Hebert, M. (2016) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-319-25781-5_2
“The seminal paper on “style-content separation” [34] uses bilinear models to factor out the style and content components in pre-segmented, prealigned visual data (e.g., images of letters in different fonts).”
BackgroundNonlinear dimensionality reduction with side information
Ghodsi, A. (2006)
Nonlinear Dimensionality Reduction withSide Information
Ghodsi, A. (2006)
Multi-modality face recognition: An information theoretic approach
Supriya, M., & Singh, S. (2017) · International Conference on Advances in Computing, Communications and Informatics (ICACCI) · doi:10.1109/icacci.2017.8125985
“Whereas in another work by Tenenbaum and Freeman [3] they presented a set of efficient yet simple learning algorithms for bi-linear models based on the SVD(Singular Value Decomposition) and Expectation Maximization(EM) techniques.”
MethodZhang, B., Zhang, H., Sun, J., Wang, Z., Wu, H., & Dong, X. M. (2018) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2018.p0611
Generalized Multiview Discriminative Projections with Spectral Reconstruction
Yuan, Y., Li, Y., Qiang, J., et al. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-02698-1_40
Learning Interval Representations from Polyphonic Music Sequences
Lattner, S., Grachten, M., & Widmer, G. (2018) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.1492502
Adaptive Objective Functions and Distance Metrics for Recommendation Systems
Burkhart, M. C., & Modarresi, K. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-22741-8_43
A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence RepresentationsPreprint
Chen, M., Tang, Q., Wiseman, S., & Gimpel, K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.01173 · Cited by 11
“There is a growing amount of work on learning interpretable or disentangled latent representations both in machine learning (Tenenbaum and Freeman, 2000; Reed et al., 2014; Makhzani et al., 2015; Mathieu et al., 2016; Higgins et al., 2016; Chen et al., 2016; Hsu et al., 2017) and in various NLP applications, including…”
BackgroundLearning visual attributes from contextual explanations
Murrugarra-Llerena, N. (2019) · D-Scholarship@Pitt (University of Pittsburgh)
Hybrid-Order and Multi-Stream Convolutional Neural Network for Fine-Grained Visual Recognition
Liu, Y., Gu, H., Li, C., Xu, Q., & Yang, L. (2019) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp.2019.8928066
“Bilinear model is first introduced by Tenenbaum et al. to evaluate the similarity of style in Style Transfer [5].”
BackgroundFood Image Categorization Using Attentional Bilinear Model
Nussiri, V., & Vateekul, P. (2019) · doi:10.1109/iciteed.2019.8929982
“In 2000, Tenenbaum and Freeman [12] proposed a bilinear model that separated style and content as a two-factor variation of the image.”
BackgroundModeling Musical Structure with Artificial Neural NetworksPreprint
Lattner, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.01720 · Cited by 1
“In machine learning, this principle was deployed in bi-linear models, for example, to separate person and pose of face images [Tenenbaum and Freeman, 2000].”
MethodDeep Learning of Paradigms: The Outlook
Jhansi, A., Lavanya, K., & Kavarakuntla, T. (2020) · Learning and analytics in intelligent systems · doi:10.1007/978-3-030-46943-6_8
Metadata
- Authors
- Tenenbaum, J. B., & Freeman, W. T.
- Affiliations
- Massachusetts Institute of Technology (US)
- Mitsubishi Electric Research Laboratories (United States) (US)
- Venue
- Neural Computation
- Publisher
- MIT Press
- Published
- 2000-06-01
- Volume
- 12
- Issue
- 6
- Pages
- 1247-1283
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W2170653751
- Semantic Scholar
- 7e85f7d59e37972ec52cbabfef0512588d87f125
- Cited by
- 840
- References
- 61
- Citations by year
- 2026: 2 · 2025: 17 · 2024: 20 · 2023: 31 · 2022: 38 · 2021: 61 · 2020: 58 · 2019: 70 · 2018: 49 · 2017: 39 · 2016: 56 · 2015: 34 · 2014: 27 · 2013: 39 · 2012: 30
- FWCI
- 13.29
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Neural Computation (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face and Expression Recognition
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Keywords
- bilinear model, factor models, perceptual learning, speaker accent, singular value decomposition, expectation-maximization algorithm, factor interactions
- MeSH terms
- Algorithms, Face, Humans, Learning, Pattern Recognition, Visual, Speech Perception, Linear Models, Neural Networks, Computer
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
