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.

169,341 papers · 148 categories

Trend · papers per month

62125187249 · Jun 202019922001200920182026
48 results for multiple-view images

Maximizes mutual info across views for better image representations.

problem Improving image representation learning through multiple views.
method Maximizing mutual information between features from multiple views.
result ImageNet accuracy of 68.1% using linear evaluation, significantly outperforming prior methods.

Study differential invariants of objects and their images under surjective maps.

problem Reconstruction of objects from multiple-view images.
method Analysis of differential invariants under surjective maps, considering projectable and non-projectable cases.
result Constructible isomorphism between object and image invariants in the projectable case.

A new method clusters subjects based on brain networks without vectorizing fMRI data.

problem Distortion of clustering results when simplifying fMRI data structure.
method Wishart mixture models for multiple-view clustering of brain networks.
result Identifies multiple underlying pairs of associations between subject clusters and brain sub-networks.

GMBL uses graph embedding to learn binary codes from multiple views for clustering.

problem Lack of complete structure and complementary information from multiple views in single-view hash clustering methods.
method Graph-based Multi-view Binary Learning (GMBL) using Laplacian matrix to preserve data structure and assign weights to views.
result GMBL outperforms previous methods in clustering performance on multiple datasets.

New method finds dependent subspaces of multiple views for better data retrieval.

problem Finding relationships between multiple data views for analysis and prediction.
method Optimizes mappings for each view to maximize cross-view similarity between neighborhoods of data samples.
result The method outperforms alternatives in preserving cross-view neighborhood similarities and detecting local dependencies.

Unsupervised pre-training preserves multiple views from input distribution.

problem Learning from multiple views of supervision in unsupervised settings.
method Investigates unsupervised pre-training under information theory, focusing on disentanglement and multiple views.
result Unsupervised pre-training helps conserve multiple views from input distribution, improving model performance.

A new method integrates multi-label and multi-view features for image classification.

problem Combining multi-label and multi-view information for effective image classification.
method Introduces MV3\mathbf{^3}MR, a method that exploits the complementary property of different features and discovers intrinsic local geometry.
result MV3\mathbf{^3}MR outperforms existing methods on PASCAL VOC' 07 and MIR Flickr datasets.

Proposes a method for multi-view clustering that integrates consistent and complementary graph regularizers.

problem Multi-view clustering where views have both consistent and complementary information.
method Consistent and complementary graph-regularized multi-view subspace clustering (GRMSC).
result The proposed method outperforms state-of-the-art methods on benchmark datasets.

Enhances hashing for cross-modal retrieval using multi-view features.

problem Limited improvement in single-view hashing for cross-modal retrieval.
method Exploits multiple views to enrich feature information, learning discriminative hash codes.
result Superior performance compared to state-of-the-art methods on various datasets.

DEMVC improves multi-view clustering with collaborative training and deep autoencoders.

problem Existing multi-view clustering methods have high computation and space complexities or lack representation capability.
method DEMVC learns embedded representations of multiple views individually using deep autoencoders and collaboratively trains all views.
result DEMVC achieves significant improvements over state-of-the-art methods on multi-view datasets.

Proposes a method to learn from multiple views with low-rank embeddings.

problem Learning from multiple views with varying correlations is challenging.
method Multi-view Locality Low-rank Embedding (MvL2E) method that uses low-rank representations and centroid-based scheme.
result MvL2E achieves comparable performance with previous methods on benchmark datasets.

New method recovers latent sources from multiple noisy views using deep neural networks.

problem Recovering a common latent source from multiple nonlinearly mixed views.
method Novel identifiability proofs using deep neural networks.
result Independent latent sources can be recovered from multiple noisy views using deep neural networks.

This paper proposes a multi-view representation learning approach for robust node representations.

problem Learning robust node representations across multiple types of network views.
method Promotes collaboration between different views using an attention mechanism.
result The proposed approach outperforms existing methods for network representation learning.

In this paper we present a fully Bayesian latent variable model which exploits conditional nonlinear(in)-dependence structures to learn an efficient latent representation. The latent space is factorized to represent shared and private information from multiple views of the data. In contrast to previous approaches, we i…

2012-06-18abs ↗pdf ↗

Proposes C2AF network for multi-view time series classification.

problem Improving multi-view time series classification performance.
method Two-stream structured encoder, graph-based correlation matrix, channel-aware fusion mechanism.
result Extensive experimental results show superior performance over state-of-the-art methods.

Novel co-learning method for manifolds with group actions using multiple fibre bundles.

problem Learning from manifolds with group actions without labeled data.
method Representation theory to associate multiple fibre bundles, leveraging group actions for unsupervised learning.
result Improved robust nearest neighbor search and community detection on cryo-electron microscopy images.

Proposes LMSSC for multi-view semi-supervised classification.

problem Leveraging multiple complementary views for improved classification.
method Semi-supervised classification with latent multi-view representation learning.
result Unified framework for latent representation learning, graph construction, and label propagation.

A method for combining classifiers from multiple views using Bregman divergences.

problem Combining classifiers from multiple views with limited labeled data.
method Jointly learns view-specific and overall weighted majority vote classifiers using Bregman divergences.
result Empirical results show improved classifier performance with limited labeled data.

This paper proposes a multi-view learning framework for dimension reduction.

problem Challenges in learning low-dimensional spaces from multiple heterogeneous features.
method Similarity-consensus regularized multi-view learning framework.
result The proposed method achieves comparable performance to previous multi-view learning approaches.

A new method learns to prioritize and use multiple views of an environment for better decision-making.

problem Learning from multiple views of an environment to improve decision-making.
method Attention-based deep reinforcement learning to dynamically attend to views of the environment.
result The method improves performance in complex 3D environments with obstacles.

Proposes KMvDA for object recognition from multi-view data.

problem Recognizing objects from different views, even when views are heterogeneous.
method Introduces kernel multi-view discriminant analysis (KMvDA) and uses random Fourier features (RFF) for large-scale learning.
result KMvDA and RFF approximation improve object recognition from multi-view data.

Novel algorithm estimates local permutations in unlabeled multi-view sensing.

problem Estimating local permutations in unlabeled multi-view sensing.
method Graph alignment and Gromov-Wasserstein alignment exploiting multiple views.
result The proposed algorithm is scalable and applicable to challenging SNR regimes.

Proposes a method to improve reinforcement learning in multi-view environments.

problem Improving policy learning in environments with partial observability.
method Actor-Critic-Attention Mechanism for generating a single feature representation from multiple views.
result Our method outperforms state-of-the-art baselines on various complex 3D environments.

End-to-end deep learning for multi-view clustering improves accuracy across various data types.

problem Limited multi-view clustering methods for general data types and suboptimal two-stage process.
method Permutation-based canonical correlation objective for fused representations; pseudo-labels for clustering; theoretical error bound.
result Proposed model provides meaningful fused representations and effective clustering across multiple views.

New method reconstructs moving parts of proteins in cryo-EM.

problem Reconstructing non-rigid molecules with moving parts in cryo-EM.
method Graph Laplacian construction from multiple projection images, followed by spectral volume expansion.
result High-resolution visualization of molecular dynamics using spectral volumes.

Proposes MANE for multi-view network embedding, improving node representations.

problem Learning low-dimensional representations from multiple views of networks.
method MANE combines diversity and collaboration, including second-order collaboration, and attention-based extension MANE+.
result MANE+ outperforms state-of-the-art approaches on real-world multi-view networks.

Proposes a new multi-view graph learning framework to model consistency and inconsistency.

problem Graph learning methods often neglect inconsistency across multiple views, making them vulnerable to noisy datasets.
method Proposes a unified objective function to simultaneously model consistency and inconsistency, iteratively learning consistent and unified graphs.
result Demonstrates robustness and efficiency of the proposed approach on twelve multi-view datasets.

DTCCA learns nonlinear transformations of multi-view data for high-order correlation.

problem Learning complex nonlinear transformations of multiple data views.
method Maximizes high-order canonical correlation by jointly learning transformations of each view using a reformulated tensor decomposition.
result DTCCA efficiently handles high-dimensional and large number of views, overcoming scalability issues.

A new model for multiview data analysis using graph autoencoders.

problem Nonlinear multiview canonical correlation analysis for large datasets.
method Variational approach with graph convolutional neural networks.
result Competitive performance on classification, clustering, and recommendation tasks.

RényiCL uses Rényi divergence for robust contrastive learning with stronger data augmentations.

problem Learning useful representations from multiple data views with hard augmentations.
method RényiCL employs Rényi divergence for contrastive learning, using a novel variational objective to manage hard negative sampling.
result RényiCL achieves better performance with stronger augmentations compared to other methods.

Proposes MvLPE for better multi-view representation learning.

problem Learning representations from multi-view data with varying correlations.
method Integrates multi-view data into a centroid view while maintaining low-rank reconstruction relations.
result MvLPE outperforms existing methods on benchmark datasets.