Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

491317 · May 201919922001200920182026
48 results for feature-level fusion

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.

Proposes deep multimodal fusion for biometric identification.

problem Improving biometric identification accuracy with multiple modalities.
method Joint optimization of multiple modality-specific CNNs at different feature abstraction levels.
result Significant improvement in multimodal person identification performance.

Dictionary learning algorithms have been successfully used for both reconstructive and discriminative tasks, where an input signal is represented with a sparse linear combination of dictionary atoms. While these methods are mostly developed for single-modality scenarios, recent studies have demonstrated the advantages …

2015-02-04abs ↗pdf ↗

A fusion approach combines audio and video features for emotion recognition.

problem Continuous emotion recognition using both visual and auditory modalities.
method Pre-trained CNN features from video frames and minimalistic auditory descriptors. Fusion at feature or prediction level. SVR for prediction.
result Improves CCCs of 0.749 and 0.565 for arousal and valence respectively.

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.

New deep fusion methods improve human action recognition using depth and inertial sensor data.

problem Existing multimodal HAR frameworks lack mid-level feature fusion.
method Proposes three deep multilevel multimodal fusion frameworks, transforming depth and inertial sensor data into images and using convolution with Prewitt filter to create modality within modality.
result Supremacy of proposed fusion frameworks over existing methods on three publicly available datasets.

Proposes a model to decompose feature-level variation in high-dimensional data.

problem Interpreting complex high-dimensional data for understanding feature-level variability.
method Covariate Gaussian Process Latent Variable Model (c-GPLVM) for structured kernel decomposition.
result Extracts low-dimensional structures from high-dimensional data sets while explaining feature-level variability.

Proposes a feature leveling method to improve interpretability of deep neural networks.

problem Deep neural networks are hard to interpret due to mixed feature levels.
method Introduces a feature leveling architecture to isolate low and high level features.
result Modified models achieve competitive results and improved interpretability.

Domain adaptation is the supervised learning setting in which the training and test data are sampled from different distributions: training data is sampled from a source domain, whilst test data is sampled from a target domain. This paper proposes and studies an approach, called feature-level domain adaptation (FLDA), …

2015-12-15abs ↗pdf ↗

A novel multi-modal active learning approach using RL for engagement estimation.

problem Challenges in labeling multi-modal human data for accurate user state estimation.
method Deep reinforcement learning for optimal data selection and multi-modal data fusion.
result The proposed approach outperforms existing methods in engagement estimation.

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.

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.

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.

Paper proposes methods to reduce adversarial vulnerability in neural networks.

problem Adversarial vulnerability of deep neural networks in safety-critical applications.
method Defining vulnerability, proposing Vulnerability Suppression (VS) loss, and a Bayesian feature pruning method.
result Improves adversarial robustness and clean example performance with minimal parameter reduction.

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…

2007-04-02abs ↗pdf ↗

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.

Topology-GS improves 3D GS for better structural and feature integrity.

problem Compromised pixel-level and feature-level integrity in 3D GS.
method Incorporates Local Persistent Voronoi Interpolation (LPVI) and PersLoss based on persistent homology.
result Topology-GS outperforms existing methods in PSNR, SSIM, and LPIPS metrics.

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.

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.

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…

2012-07-04abs ↗pdf ↗

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.

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.

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.

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.

A new framework explains GNN predictions by simulating graph structure and feature changes.

problem Lack of transparency in GNN predictions hinders understanding.
method TraP2 framework using a three-layer architecture: Translation, Perturbation, and Paraphrase layers.
result TraP2 achieves 10.2% higher explanation accuracy than state-of-the-art methods.

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.

Paper proposes MDAT to stabilize domain alignment in label-scarce settings.

problem Stable and comprehensive domain alignment in label-scarce settings.
method Max-margin Domain-Adversarial Training (MDAT) with Adversarial Reconstruction Network (ARN).
result MDAT stabilizes gradient reversing and achieves strong robustness to hyper-parameters.