Study representation rings and dimension functions for fusion systems.
problem Understanding the structure of representations in fusion systems.
method Define representation ring, use Grothendieck ring, study dimension functions via transfer map.
result Find conditions for dimension functions of stable representations.
Enhances KWS in vehicles with multi-source fusion.
problem Improving precision and recall rates in vehicle keyword spotting.
method Integrates vehicle information into a DNN for speech classification and selects optimal sensitivity parameters.
result Significantly improved performance metrics (precision, recall, MSE) compared to baseline.
Improved robustness in multi-modal sensor fusion with deep learning.
problem Inconsistency in fusion weights leading to poor performance under sensor failures.
method Proposes deep multi-modal sensor fusion architectures with fusion weight regularization and target learning.
result Proposed architectures outperform existing deep learning methods under sensor failures.
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 simple fusion of deep and shallow learning improves acoustic scene classification.
problem Improving acoustic scene classification accuracy.
method Combining a deep learning approach and a feature engineering approach using a late fusion strategy.
result The fused system achieves 72.8% classification accuracy, outperforming individual methods.
A framework combines diverse power grid data for a unified view.
problem Unified view of complex power grids with distributed resources.
method Belief Propagation for probabilistic data fusion.
result Efficient distributed inference algorithm for grid state quantification.
Adversarial approach enhances sensor fusion for robust target detection.
problem Improving target detection and classification using multi-modal sensor fusion.
method Generative network learns latent space from various sensor modalities, then detects damaged sensors and safeguards performance.
result Automatic robustness against noisy/damaged sensors achieved.
Optimized deep learning architectures improve sensor fusion performance.
problem Sensor fusion in autonomous systems.
method Proposed two optimized architectures: coarser-grained and two-stage gated.
result Significant performance improvements and robustness in noisy conditions.
For most problems in science and engineering we can obtain data sets that describe the observed system from various perspectives and record the behavior of its individual components. Heterogeneous data sets can be collectively mined by data fusion. Fusion can focus on a specific target relation and exploit directly ass…
Proposes a new CNN approach for multimodal biometric identification.
problem Improving biometric identification accuracy across multiple modalities.
method Uses a bank of modality-specific CNNs, fuses their outputs, and optimizes the system.
result Significantly outperforms unimodal systems and demonstrates reduction in parameters.
This thesis tackles data fusion issues across different biological scales and types.
problem Heterogeneity in data types and scales in systems biology.
method Developed statistical methods to fuse heterogeneous data sets.
result Advantages of proposed methods assessed through simulations and real data analysis.
Deep Fusion improves audio-video emotion recognition accuracy.
problem Challenges in automatic emotion recognition due to abstract concept and multiple expressions of emotion.
method Introduces factorized bilinear pooling (FBP) with embedded attention mechanism to integrate audio and video features.
result Achieves an accuracy of 62.48% on AFEW database, outperforming state-of-the-art results.
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…
Paper proposes RMFN for multimodal language analysis.
problem Modeling interactions between language, visual, and acoustic modalities.
method Recurrent Multistage Fusion Network (RMFN) decomposes fusion into stages focusing on subsets of multimodal signals.
result RMFN achieves state-of-the-art performance across multimodal sentiment analysis, emotion recognition, and speaker traits recognition datasets.
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.
Proposes LVGP for multi-source data fusion in science and engineering.
problem Differences in quality and comprehensiveness of data sources.
method Latent Variable Gaussian Process (LVGP) framework.
result Improved predictions for sparse-data problems.
New theory shows interpretable models can outperform black-box models in decision-making systems.
problem The importance of interpretability in machine learning models.
method Characterized performance of two-node data fusion systems using distributed detection theory.
result A human with an interpretable classifier outperforms one with a black-box classifier.
Seq2seq models predict complex multi-physics systems' time evolution.
problem Predicting the time-evolution of complex multi-physics systems.
method Sequence-to-sequence models applied to multi-physics simulations.
result Seq2seq models accurately emulate complex systems and predict their evolution.
Cooperative perception improves 3D object detection in autonomous vehicles.
problem Limited field-of-view and occlusion in single sensor data.
method Early fusion of point clouds from multiple sensors, late fusion of independently detected bounding boxes, and hybrid combination.
result Early fusion approach outperforms late fusion by significantly higher recall (95%) compared to single-point sensing (30%).
Bayesian framework integrates prior and data knowledge for nonlinear dynamical systems.
problem Fusing diverse prior knowledge with data for accurate model learning.
method General-purpose Bayesian inference and learning framework combining explicit and implicit prior knowledge.
result Efficient parameter marginalization and closed-form densities for online and offline inference.
AECF improves multimodal inference robustness and calibration.
problem Robustness and calibration issues in multimodal systems with missing inputs.
method Adaptive Entropy-Gated Contrastive Fusion (AECF) layer.
result Improves masked-input mAP by +18 pp at a 50% drop rate.
Study builds complex network from multimodal physiological data.
problem Understanding dynamic interactions in biological systems.
method Network-based multimodal data fusion using recurrence plots and temporal metrics.
result Model accurately characterizes emotional states through physiological responses.
Combining feature importance estimates improves reliability of machine learning predictions.
problem Lack of consensus on feature importance quantification makes explanations unreliable.
method Proposes a feature importance fusion framework combining multiple quantifiers.
result Feature importance ensembles reduce prediction error by 15%.
GAR generalizes autoregression for efficient multi-fidelity fusion.
problem Efficiently combining low-fidelity and high-fidelity simulation results.
method Generalized autoregression (GAR) using tensor formulation and latent features.
result GAR outperforms state-of-the-art methods with a large margin in RMSE.
Paper explores multimodal methods for detecting urban micro-events.
problem Detecting urban micro-events in cities with limited geographical coverage.
method Exploring multimodal fusion methods including early, late, hybrid fusion and representation learning.
result Multimodal approach yields higher performance than unimodal alternatives.
Enhanced Gaussian process regression for multi-fidelity data fusion.
problem Combining data of varying fidelity levels for accurate predictions.
method Gradient-enhanced Cokriging method (GE-Cokriging) for QoI and its gradients.
result GE-Cokriging outperforms conventional multi-fidelity Cokriging in predicting QoI and gradients.
THGFM models dynamic relational systems with cross-type and temporal fusion.
problem Learning on temporal heterogeneous graphs with diverse node and relation types.
method Dual-Path Architecture with Shared-Space and Relational Type-Partitioned Temporal Attention.
result THGFM outperforms baseline models on academic graph benchmarks.
Bayesian models fuse multiple sensor types for health monitoring in homes.
problem Challenges in fusing heterogeneous sensor data for health monitoring.
method Introduces Bayesian models for sensor fusion of multiple sensor types.
result Identifies most useful sensor modalities and features for activities.
Dual memory model learns from two asynchronous views.
problem Capturing long-term intra-view and inter-view interactions in multi-view sequential data.
method Two encoders for reading and writing to external memories, late-fusion and early-fusion modes of memory accessing.
result Competitive performance on synthetic and healthcare tasks.
Distributed sensors compress and send features to a fusion center for linear regression.
problem Efficiently compress and transmit features from distributed sensors to a fusion center under varying communication constraints.
method Designs a distributed and adaptive feature compression scheme using optimal quantizers and simple adaptive strategies.
result Demonstrates improved inference performance through simulated experiments.
Nonlinear filtering extracts relevant variables from multimodal sleep data.
problem Recover relevant variables from multiple sensor data.
method Diffusion-based manifold learning for nonlinear filtering.
result Method gives robust data-driven representation correlated with sleep process.
Revised proof shows ribbonness of surface-links in 4-sphere.
problem Determining ribbonness of surface-links in 4-sphere.
method Surgery along fusion 1-handle systems to prove ribbonness.
result Surface-links in 4-sphere are ribbon if certain conditions are met.
Inspired by brain's modality fusion, this paper detects active speakers from audio and video.
problem Detecting active speakers in noisy environments.
method Inspired by brain's superior colliculus, combines audio and visual data through specialized neural networks and a novel fusion layer.
result Achieved results greatly surpassing initial expectations, confirming the effectiveness of the proposed method.
Novel fusion of autoencoders predicts sleepiness from speech.
problem Predicting sleepiness from speech recordings.
method Attention-based and recurrent sequence to sequence autoencoders for unsupervised representation learning.
result Fusion of autoencoders' representations achieves higher correlation with sleepiness scales.
Paper reviews the evolution of alpha from human insight to AI-powered systems.
problem Exceeding market benchmarks in finance.
method Five-stage taxonomy integrating representation learning, multimodal data fusion, and LLM agents.
result Unified framework for evaluating and developing next-gen alpha systems.
Improved VQA accuracy with generalized fusion operators.
problem Enhancing multimodal fusion for better VQA performance.
method Generalized Hadamard-Product fusion operators with Nonlinearity Ensembling, Feature Gating, and post-fusion layers.
result 1.1% absolute improvement on VQA 2.0 test-dev set.
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.
A fusion of multiple classifiers improves indoor localization using visible light.
problem Indoor localization accuracy and robustness using visible light.
method Transmit different intensity modulated sinusoidal signals, capture peaks of PSD, train multiple classifiers, and combine their outputs using robust fusion algorithms.
result The proposed algorithms significantly improve localization accuracy and robustness compared to existing methods.
Generative x-vectors improve SV performance.
problem Improving text-independent speaker verification.
method Proposes a novel method to combine i-vectors and x-vectors using a transformation model derived from canonical correlation analysis.
result Generative x-vectors provide better performance than baseline systems, especially for long-duration utterances.
Invariants defined for braid systems under Hurwitz equivalence.
problem Invariants for braid systems under Hurwitz equivalence.
method Crossing matrix and polynomial invariant introduced.
result Invariant defined for surface braids and surface links.
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.
The study evaluates cross-modal knowledge fusion methods.
problem Combining knowledge from text, KGs, and images.
method Evaluation of different fusion methods using embeddings.
result Potential of cross-modal knowledge fusion.
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.
Study improves robustness of deep fusion models against single source noise.
problem Ensuring robustness of deep fusion models against noise added to a single input source.
method Proposed two approaches: a carefully designed loss function and a convolutional fusion layer.
result Deep fusion models become robust against noise applied to a single source, preserving performance on clean data.
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.
Model for dynamic relational data with regime changes.
problem Handling abrupt changes in dynamic relational data.
method Factorized fusion shrinkage model with global-local shrinkage priors.
result Posterior distribution attains minimax optimal rate up to logarithmic factors.
Innovative 2-categories create 4-manifold invariants.
problem Constructing invariants for 4-manifolds.
method Semisimple 2-categories, fusion 2-categories, and state-sum construction.
result Construct a state-sum invariant for 4-manifolds.
Proposes a framework to fuse heterogeneous data sources for better modeling.
problem Heterogeneous data sources with different input parameter spaces.
method Input mapping calibration (IMC) and latent variable Gaussian process (LVGP).
result Improved predictive accuracy over single source models.