A new framework learns shared features from multi-view data with many-to-many associations.
problem Learning shared features from multi-view data with many-to-many associations.
method Probabilistic Multi-view Graph Embedding (PMvGE) using neural networks.
result PMvGE outperforms existing multi-view methods in large-scale datasets.
Paper proposes StarGAN-VC for non-parallel voice conversion.
problem Non-parallel many-to-many voice conversion.
method Variant of GAN called StarGAN for simultaneous many-to-many mappings.
result Obtained higher sound quality and speaker similarity than state-of-the-art methods.
New method analyzes complex multivariate pathways in high-dimensional data.
problem High-dimensional mediation analysis of multivariate exposures, mediators, and outcomes.
method Simultaneous variable selection, indirect effect matrix estimation, and prediction of multivariate outcomes.
result Identifies biologically interpretable genetic-neural-cognitive pathways.
Graphs provide an efficient tool for object representation in various computer vision applications. Once graph-based representations are constructed, an important question is how to compare graphs. This problem is often formulated as a graph matching problem where one seeks a mapping between vertices of two graphs whic…
Many-to-Many VTN improves voice conversion across multiple speakers.
problem Voice conversion across multiple speakers.
method Sequence-to-sequence learning framework with many-to-many VTN architecture.
result Improved sound quality and speaker similarity compared to baseline methods.
AUTOVC converts voices without parallel data, achieving state-of-the-art results.
problem Non-parallel many-to-many voice conversion and zero-shot voice conversion.
method Only an autoencoder with a carefully designed bottleneck is used, training on a self-reconstruction loss.
result AUTOVC achieves state-of-the-art results in many-to-many voice conversion with non-parallel data and performs zero-shot voice conversion.
Paper proposes ACVAE-VC for non-parallel voice conversion.
problem Non-parallel many-to-many voice conversion with attribute class label retention.
method Uses ACVAE with fully convolutional networks, information-theoretic regularization, and auxiliary classifier.
result Successfully retains attribute class labels and avoids buzzy speech.
ConvS2S-VC converts voice characteristics and pitch contour using a fully convolutional seq2seq model.
problem Voice conversion with preservation of pitch contour and duration.
method Fully convolutional seq2seq architecture with conditional batch normalization.
result ConvS2S-VC outperforms baseline methods in sound quality and speaker similarity.
Improved autoencoder for F0-consistent voice conversion.
problem Non-parallel many-to-many voice conversion with prosodic information leakage.
method Conditional autoencoder with information-constraining bottlenecks.
result Controlled F0 contour and improved speech quality.
We present a novel approximate graph matching algorithm that incorporates seeded data into the graph matching paradigm. Our Joint Optimization of Fidelity and Commensurability (JOFC) algorithm embeds two graphs into a common Euclidean space where the matching inference task can be performed. Through real and simulated …
Paper develops real-time through-wall human pose imaging using RF signals.
problem Developing real-time vision through opaque objects.
method Many-to-Many Encoder/Decoder Paradigm, student/teacher learning, Residual CNN, RPN, LSTM.
result Accurately predicts human pose through visual occlusion using RF signals.
Modified Hungarian algorithm solves special OT problems efficiently.
problem Computing empirical Wasserstein distance in independence tests.
method Modified Hungarian algorithm for special OT problems.
result The modified algorithm solves special OT problems with complexity O(m2n). Framework converts singer identity and vocal technique from non-parallel corpora.
problem Converts singer identity and vocal technique from non-parallel corpora.
method Uses variational autoencoders with separate encoders for singer identity and vocal technique.
result Successfully disentangles and converts singer identity and vocal technique.
A fast voice conversion method using diffusion models.
problem One-shot many-to-many voice conversion.
method Diffusion probabilistic modeling with Fast Maximum Likelihood Sampling Scheme.
result Superior quality compared to state-of-the-art approaches.
Blow converts non-parallel raw audio voices efficiently.
problem Voice conversion with non-parallel data.
method Single-scale normalizing flow with hypernetwork conditioning.
result Blow outperforms existing flow-based architectures in voice conversion.
Sequence to sequence learning has recently emerged as a new paradigm in supervised learning. To date, most of its applications focused on only one task and not much work explored this framework for multiple tasks. This paper examines three multi-task learning (MTL) settings for sequence to sequence models: (a) the onet…
Recently, multiple formulations of vision problems as probabilistic inversions of generative models based on computer graphics have been proposed. However, applications to 3D perception from natural images have focused on low-dimensional latent scenes, due to challenges in both modeling and inference. Accounting for th…
Proposes CHDP for modeling cooperative hierarchical structures with Dirichlet processes.
problem Lack of flexible topic modeling for cooperative hierarchical structures.
method Introduces Cooperative Hierarchical Dirichlet Processes (CHDP) with superposition and maximization measures.
result Demonstrates improved modeling of cooperative hierarchical structures with CHDP.
We derive a mapping between MSE and CCC, revealing counterintuitive insights.
problem Missing mapping between mean square error and concordance correlation coefficient.
method Derive mathematical formula connecting MSE and CCC, analyze graphical implications.
result Formula uncovers counterintuitive insights and precise range for CCC given MSE.
The paper proves impossibilities and positive results for universal machine translation.
problem Learning shared sentence representations across multiple language pairs.
method Formal proofs and analysis of natural generative processes.
result Lower bound on translation error and positive results under natural structure.
New method discovers nonlinear associations using copula entropy.
problem Linear association measures have theoretical limitations.
method Proposes a new method using copula entropy.
result Demonstrates more meaningful nonlinear associations.
A novel cross-modal auto-encoder associates different data types efficiently.
problem Cross-modal data association in heterogeneous datasets.
method Bayesian inference framework with variational auto-encoders and associators.
result Successfully associates visual and auditory data with minimal paired data.
Study explores associated groups of symmetric quandles and their properties.
problem Understanding the structure and relationships of symmetric quandles and their associated groups.
method Group-theoretic analysis and characterization of associated groups.
result Characterization and properties of associated groups of symmetric quandles.
When response variables are nominal and populations are cross-classified with respect to multiple polytomies, questions often arise about the degree of association of the responses with explanatory variables. When populations are known, we introduce a nominal association vector and matrix to evaluate the dependence of …
We study deformations of associative submanifolds Y3⊂M7 of a G2 manifold M7. We show that the deformation space can be perturbed to be smooth, and it can be made compact and zero dimensional by constraining it with an additional equation. This allows us to associate local invariants to associative subm…
This study addresses transitions in conically singular associative submanifolds and their desingularizations.
problem Counting closed associative submanifolds of G2-manifolds and understanding transitions arising from degenerations. method Analysis of moduli spaces, transversality results, and desingularization techniques for conically singular associative submanifolds.
result For generic co-closed G2-structures, there are no CS associative submanifolds with stability-index greater than 0 or 1. Study of associative submanifolds in Berger space SO(5)/SO(3).
problem Characterizing and classifying associative submanifolds in Berger space.
method Geometric correspondence with pseudo-holomorphic curves, analysis of special Gauss maps.
result Existence of infinitely many topological types of compact associative 3-folds.
Model for associative submanifolds in K3 fibrations.
problem Understanding singularity formation in associative submanifolds.
method Graphs in a 3-manifold with locally gradient flow lines.
result Produces analogues of known singularity formation phenomena.
This paper studies the associativity of gluing of trajectories in Morse theory. We show that the associativity of gluing follows from of the existence of compatible manifold with face structures on the compactified moduli spaces. Using our previous work, we obtain the associativity of gluing in certain cases. In partic…
It is well-known that in any codimension a simply connected Euclidean minimal surface has an associated one-parameter family of minimal isometric deformations. In this paper, we show that this is just a special case of the associated family to any simply connected elliptic surface for which all curvature ellipses of a …
A new method counts associative submanifolds and Seiberg-Witten monopoles.
problem Counting associative submanifolds and Seiberg-Witten monopoles in G2-manifolds.
method Floer homology groups generated by associative submanifolds and solutions of Seiberg-Witten equations.
result Construction of Floer homology groups associated with G2-manifolds.
Study constructs associative submanifolds in G2-manifolds from orbifolds.
problem Constructing associative submanifolds in G2-manifolds from orbifolds. method Using Joyce's generalised Kummer construction.
result The volume of associative submanifolds tends to zero as they approach orbifolds.
DEDACT breaks down feature importance into direct and associative components.
problem Lack of clear distinction between direct and associative feature importance.
method DEDACT framework to decompose direct and associative importance measures.
result Provides insight into sources of prediction-relevant information and feature pathways.
The paper studies prolongations of Lie algebras associated with pseudo H-type Lie algebras.
problem Investigating prolongations of Lie algebras associated with pseudo H-type Lie algebras. method Analyzing prolongations of associated fundamental graded Lie algebra and associated conformal pseudo-subriemannian fundamental graded Lie algebra.
result The prolongation of the associated conformal pseudo-subriemannian fundamental graded Lie algebra coincides with that of the associated fundamental graded Lie algebra under certain conditions.
Extracts biological context from biomedical texts to associate with events.
problem Identifying biological context and associating it with biochemical events in texts.
method Analyzed an annotated corpus and developed classifiers using syntactic, distance, and frequency features.
result Developed and evaluated classifiers for context-event association.
Method constructs rigid associative submanifolds in twisted G2-manifolds.
problem Constructing rigid associative submanifolds in twisted G2-manifolds.
method Introducing a gluing theorem for asymptotically cylindrical associative submanifolds in ACyl G2-manifolds.
result Yields many new topological types of rigid associative submanifolds.
Proofs and descriptions of totally geodesic submanifolds in symmetric spaces.
problem Classifying totally geodesic submanifolds in symmetric spaces.
method Independent proof and descriptions using algebraic and geometric properties.
result Natural descriptions and classifications of totally geodesic submanifolds.
DeepDA uses LSTM to track multiple targets in clutter.
problem NP-hard combinatorial optimization in multi-target tracking with clutter.
method LSTM-based deep learning for data association.
result Significant performance on association ratio, target ID switching, and time-consuming tracking.
The associator of a non-associative algebra is the curvature of the Hochschild quasi-complex. The relationship ``curvature-associator'' is investigated. Based on this generic example, we extend the geometric language of vector fields to a purely algebraic setting, similar to the context of Gerstenhaber algebras. We int…
Bayesian approach to data association using Gaussian processes.
problem Separating data from different generating processes.
method Fully Bayesian approach with Gaussian process priors for structure encoding and doubly stochastic variational inference.
result Efficient learning scheme for deep Gaussian process priors.
A local classification of the Hermitian manifolds with flat associated connection is given. Hermitian manifolds admitting locally a conformal metric with flat associated connection are characterized by a curvature identity. Locally conformal Kaehler manifolds as well as Hermitian surfaces with vanishing associated conf…
Framework uncovers symmetric and asymmetric species associations from data.
problem Retrieving bidirectional species associations from co-occurrence data.
method Machine learning framework modeling latent embeddings and joint generative model.
result Framework successfully recovers known symmetric and asymmetric associations.
Deep learning optimizes user association in Massive MIMO networks.
problem Optimizing user cell association for maximum sum-rate in Massive MIMO networks.
method Training a deep neural network to learn optimal association rules based on user positions.
result The neural network achieves the same performance as traditional optimization methods with reduced computational complexity.
OMBA learns product and user representations for better online market basket analysis.
problem Limited ability to uncover rarely occurring and temporal associations in MBA.
method Jointly learns product and user representations, captures temporal dynamics, scalable online method.
result OMBA outperforms state-of-the-art methods by 21% on real-world datasets.
Computes quandle associated groups using group homology.
problem Computing associated groups of quandles.
method Using group homology theory to describe and compute associated groups.
result Computed second quandle homology groups of specific quandle families.
Develops G-MLKM for better data-target association in constrained spaces.
problem Data-target association problem in constrained spaces with limited sensor information.
method Graph-based multi-layer k-means++ (G-MLKM) method, including MLKM for local space and G-MLKM for general constrained space.
result Improves data-target association accuracy through error correction mechanisms.
New algebraic structure for vector bundles with special properties.
problem Developing new algebraic structures for vector bundles.
method Introducing para-associative algebroids and showing local triviality conditions.
result Existence of a differential connection is necessary and sufficient for local triviality.
New mechanics on non-associative octonions discovered.
problem Discrete mechanics on non-associative groups.
method Generalized Lagrangian and Hamiltonian mechanics to non-associative objects.
result Discrete mechanics on unitary octonions achieved.