Bayesian model fuses multiple classifiers with explicit correlation modeling.
problem Combining outputs of multiple classifiers with explicit correlation.
method Hierarchical Bayesian model with correlated Dirichlet distribution.
result Fused classifier performance can be Bayes optimal even for highly correlated base classifiers.
Automatic emotion recognition (AER) is a challenging task due to the abstract concept and multiple expressions of emotion. Although there is no consensus on a definition, human emotional states usually can be apperceived by auditory and visual systems. Inspired by this cognitive process in human beings, it's natural to…
We seek to improve deep neural networks by generalizing the pooling operations that play a central role in current architectures. We pursue a careful exploration of approaches to allow pooling to learn and to adapt to complex and variable patterns. The two primary directions lie in (1) learning a pooling function via (…
A new Fusion method combines multiple distributions efficiently.
problem Combining multiple distributions for big data or privacy.
method Recursive divide-and-conquer Monte Carlo approach.
result A robust Fusion method for many sub-posteriors.
New TTP framework fuses control arms while controlling Type-I error.
problem Bias in borrowing control data from previous trials.
method Kernel two-sample testing via MMD and equivalence testing.
result Higher power than standard TTP methods while maintaining error control.
A hybrid model reduces graph complexity for improved classification accuracy.
problem High computational complexity and large number of parameters in higher-order graph convolutional networks.
method Weight sharing mechanism and novel fusion pooling layer to reduce parameters and complexity.
result The proposed model achieves highest classification accuracy with fewer trainable parameters.
A new probabilistic mixup framework improves deep learning generalization.
problem Improving deep learning generalization performance.
method Introduces a novel probabilistic mixup framework for conditional density estimation.
result Empirical results show benefits over existing mixup variants.
The paper integrates multiple Gaussian process predictions using Monte Carlo sampling.
problem Accurate prediction of variables using multiple models.
method Log-linear pooling of Gaussian process predictions, combined with Monte Carlo sampling.
result The log-linear pooling method improves prediction accuracy compared to linear pooling.
Develops a novel global pooling framework using optimal transport.
problem Sub-optimal performance in global pooling operations.
method Regularized Optimal Transport (ROT) for generalized global pooling.
result ROTP layers can improve performance in various machine learning scenarios.
This paper predicts stock prices using LLMs and news embeddings.
problem Predicting stock prices with high accuracy and relevance.
method Integrates LLMs with stock name embeddings and attention mechanisms for news filtering.
result Reduces MAE by 7.11% compared to baseline.
Proposes a low-rank bilinear pooling model for link prediction in knowledge graphs.
problem Link prediction in incomplete knowledge graphs.
method Factorized bilinear pooling model with Tucker decomposition constraints.
result Efficient and parameter-efficient model with low-rank approximation.
A new tracking method using expert selection and feature fusion.
problem Efficient visual tracking with multiple component trackers.
method Pre-event selection of experts based on past performance and feature fusion.
result Superior performance compared to ensembled trackers on public datasets.
New method for clustering tasks with heterogeneous data.
problem Clustered multitask learning with semiparametric and heterogeneous nuisances.
method Adaptive fused orthogonal estimator with Neyman-orthogonal losses and data-driven fusion penalties.
result Achieves exact clustering recovery and pooled parametric convergence rates.
Sensor fusion has wide applications in many domains including health care and autonomous systems. While the advent of deep learning has enabled promising multi-modal fusion of high-level features and end-to-end sensor fusion solutions, existing deep learning based sensor fusion techniques including deep gating architec…
Proposes Fusion Recurrent Neural Network for sequence data.
problem Improving sequence learning for practical applications.
method Fusion module and Transport module for sequence data.
result Fusion RNN performs comparably to state-of-the-art RNNs.
Meta Fusion integrates various multimodal data fusion strategies into a unified framework.
problem Improving predictive power of machine learning methods across diverse applications.
method Meta Fusion constructs a cohort of models based on latent representations across modalities, sharing soft information to boost performance.
result Meta Fusion consistently outperforms conventional fusion strategies in simulation and real-world applications.
We propose a generalized class of multimodal fusion operators for the task of visual question answering (VQA). We identify generalizations of existing multimodal fusion operators based on the Hadamard product, and show that specific non-trivial instantiations of this generalized fusion operator exhibit superior perform…
New insights into knot fusion numbers via cabling.
problem Understanding fusion numbers of ribbon knots and their behavior under cabling.
method Utilizing knot Floer homology and cabling formulas to analyze fusion numbers.
result The fusion number and strong homotopy fusion number of (p,1)-cable knots are preserved.
We introduce semisimple 2-categories, fusion 2-categories, and spherical fusion 2-categories. For each spherical fusion 2-category, we construct a state-sum invariant of oriented singular piecewise-linear 4-manifolds.
A new memory-based fusion layer improves multi-modal deep learning performance.
problem Improving performance of multi-modal deep learning by addressing long-term dependencies.
method Introducing a Memory based Attentive Fusion (MBAF) layer that incorporates both current and long-term dependencies.
result The MBAF layer enhances fusion and improves performance across different modalities and networks.
Algorithms that fuse multiple input sources benefit from both complementary and shared information. Shared information may provide robustness against faulty or noisy inputs, which is indispensable for safety-critical applications like self-driving cars. We investigate learning fusion algorithms that are robust against …
This paper improves model fusion by training-time neuron alignment, reducing barriers in multi-model fusion.
problem Diverse neuron permutations across different settings hinder model fusion performances.
method Training-time neuron alignment using fixed neuron anchors to reduce training-time permutations.
result Training-time neuron alignment improves fusion of pretrained models and federated learning performances.
We classify all fusion categories for a given set of fusion rules with three simple object types. If a conjecture of Ostrik is true, our classification completes the classification of fusion categories with three simple object types. To facilitate the discussion we describe a convenient, concrete and useful variation o…
Convolutional neural networks (CNNs) have achieved remarkable performance in many applications, especially in image recognition tasks. As a crucial component of CNNs, sub-sampling plays an important role for efficient training or invariance property, and max-pooling and arithmetic average-pooling are commonly used sub-…
Novel fusion network combines polarization and radiomics features for liver cancer classification.
problem Challenges in histopathological diagnosis of HCC and ICC.
method Two-tier fusion approach: feature-level and classification-level.
result Significantly enhances classification accuracy, even at reduced resolutions.
Study fusion methods for financial image views to improve robustness against attacks.
problem Improving robustness of financial image views for next-day direction prediction.
method Same-source multi-view learning with early fusion and late fusion, using OHLCV and technical-indicator views, and evaluating pixel-space L-infinity attacks.
result Early fusion can suffer negative transfer under noisy settings, while late fusion is more reliable once labels stabilize.
New proof and formula linking fusion trees to quantum knot invariants.
problem Quantum knot invariants encoding in non-semisimple TQC.
method Connection between fusion trees and Lawrence representations, using graphical calculus.
result Explicit encoding of quantum knot invariants via fusion trees.
Paper proposes a new method for Bayesian linear regression using spike-and-slab priors.
problem Identifying predictors with similar relationships in linear regression models.
method Hierarchical Bayesian models with spike-and-slab priors and a Gibbs sampler.
result The proposed method outperforms previous methods in simulations and real data analysis.
Study Coxeter groups over fusion rings and their geometric realisations.
problem Understanding Coxeter groups and their embeddings.
method Investigate faithful realisations and Vinberg systems.
result Induce embeddings of hyperplane complements.
A lot of attention has been devoted to multimedia indexing over the past few years. In the literature, we often consider two kinds of fusion schemes: The early fusion and the late fusion. In this paper we focus on late classifier fusion, where one combines the scores of each modality at the decision level. To tackle th…
Gradient descent constructs tight fusion frames.
problem Constructing tight fusion frames from prescribed subspaces.
method Gradient descent and symplectic geometry.
result Gradient descent can be used to construct tight fusion frames.
Constructs a fusion product on spinor bundle over loop space.
problem Describes a fusion product on the spinor bundle over loop space.
method Uses Connes fusion of von Neumann bimodules and string structures.
result Establishes a novel relation between string structures, loop fusion, and Connes fusion of Fock spaces.
Bayesian fusion improves radar target recognition for UAVs.
problem Improving radar target recognition for UAVs using multistatic radar configurations.
method Proposes a fully Bayesian RATR framework using Optimal Bayesian Fusion (OBF) to aggregate classification probability vectors from multiple radars.
result Empirical results show that the OBF method significantly enhances classification accuracy compared to other fusion methods and single radar configurations.
Computational modeling of human multimodal language is an emerging research area in natural language processing spanning the language, visual and acoustic modalities. Comprehending multimodal language requires modeling not only the interactions within each modality (intra-modal interactions) but more importantly the in…
Fusion of transformer networks using optimal transport for improved performance.
problem Improving performance of transformer-based models through fusion.
method Exploiting optimal transport for soft alignment of transformer components.
result Consistently outperforms vanilla fusion and individual parent models.
Paper proposes a method to preserve multimodal sentiment analysis fidelity.
problem Lack of fidelity in multimodal fusion for sentiment analysis.
method Variational autoencoder-based approach for modality fusion.
result Empirically shows superior performance over state-of-the-art methods.
The paper analyzes how shared priors affect Bayesian data fusion performance.
problem Effect of shared priors on Bayesian data fusion performance.
method Theoretical analysis using two divergences common in Bayesian inference.
result Theoretical analysis and experimental validation of performance behavior.
Partial fusion combines neural networks to balance accuracy and efficiency.
problem Balancing accuracy and computational cost in neural networks.
method Extending weight aggregation methods based on neuron-level similarity, using partial optimal transport to match similar neurons.
result Achieves a flexible tradeoff between computational cost and performance.
This paper reviews deep learning for multi-modality medical image segmentation.
problem Improving segmentation accuracy in medical images using multiple modalities.
method Overview of deep learning and multi-modal medical image segmentation, analysis of different network architectures and fusion strategies.
result Later fusion of modalities can lead to more accurate segmentation results.
Global catastrophe risk pools increase financial resilience by diversifying risk and including more countries.
problem Low- to middle-income countries rely heavily on foreign aid for recovery from extreme weather events, which is slow and uncertain.
method Developed a method to form global catastrophe risk pools that maximize risk diversification and select countries with low bilateral correlations or low shares in the pool risk.
result Global pooling increases risk diversification, lowers countries' shares in the pool risk, and increases the number of countries benefiting from risk pooling.
We present a baseline approach for cross-modal knowledge fusion. Different basic fusion methods are evaluated on existing embedding approaches to show the potential of joining knowledge about certain concepts across modalities in a fused concept representation.
New 4-manifold invariant defined from trisection diagrams.
problem Defining a new 4-manifold invariant from trisection diagrams.
method Algebraic data from bimodule categories and spherical fusion categories, described diagrammatically.
result Includes Hopf algebraic invariants and modular fusion category invariants.
Spinor bundle constructed on loop space for string manifolds.
problem Constructing spinor bundles for string manifolds.
method Using ideas from Stolz and Teichner, a spinor bundle and fusion product are defined for a string manifold.
result Existence of spinor bundle with fusion product on a manifold X if and only if X admits a string structure.
In most convolution neural networks (CNNs), downsampling hidden layers is adopted for increasing computation efficiency and the receptive field size. Such operation is commonly so-called pooling. Maximation and averaging over sliding windows (max/average pooling), and plain downsampling in the form of strided convoluti…
MNIST-NET10 fusion improves MNIST classification to 0.1% error rate.
problem Improving MNIST classification accuracy.
method Complex heterogeneous fusion architecture using degree of certainty aggregation.
result MNIST-NET10 achieves 0.1% error rate with 10 misclassifications.
New image classifier uses hierarchical max-pooling with local pooling.
problem Improving image classification accuracy with variable spatial relationships.
method Introduces a hierarchical max-pooling model with additional local pooling for convolutional neural networks.
result Demonstrates improved performance in estimating image features.
This paper develops a mathematical and computational framework for analyzing the expected performance of Bayesian data fusion, or joint statistical inference, within a sensor network. We use variational techniques to obtain the posterior expectation as the optimal fusion rule under a deterministic constraint and a quad…
EmbraceNet fusion model for multi-sensor activity recognition.
problem Human activity recognition using multiple sensors is challenging.
method Independent processing of each sensor, feature fusion with EmbraceNet, post-processing, and additional processes.
result Improved performance in SHL recognition challenge.