MCC algorithm predicts with partial modalities, outperforming full modalities.
problem Predicting with inconsistent and diverse multi-modal data.
method Instance-oriented Multi-modal Classifier Chains (MCC) algorithm.
result MCC outperforms full modalities in prediction.
HCL learns shared and modality-specific latent representations for multimodal data.
problem Binary shared-private decomposition inadequately represents shared information across subsets of modalities.
method Hierarchical Contrastive Learning framework combining latent-variable formulation, structural sparsity, and contrastive objective.
result HCL accurately recovers hierarchical structure and improves predictive performance on multimodal data.
Study reveals limits of PLS in multi-modal learning with correlated signals.
problem Understanding PLS performance in multi-modal learning with correlated signals.
method Random matrix theory analysis of spiked cross-covariance models.
result Identifies SNR and correlation regimes where PLS fails to recover any signal.
GPCCA integrates multi-modal data with missing values, improving clustering accuracy.
problem Integrating and analyzing multi-modal data with missing values and partial observations.
method Generalized Probabilistic Canonical Correlation Analysis (GPCCA) for unsupervised multi-modal data integration and dimensionality reduction.
result GPCCA outperforms existing methods in capturing essential patterns across modalities and provides robust low-dimensional embeddings.
Develops multi-modal neural network models for improved prediction and uncertainty quantification.
problem Improving prediction accuracy and uncertainty quantification for multi-modal data.
method Multi-modal Bayesian neural network models with conjugate last-layer estimation using SVI.
result Improved prediction accuracy and uncertainty quantification compared to uni-modal models.
Generative Multisensory Network learns 3D scene representations from multiple modalities.
problem Learning robust 3D scene representations from multiple sensory modalities.
method Amortized Product-of-Experts for efficient inference and cross-modal generation.
result The model can infer modality-invariant 3D scene representations efficiently from various sensory modalities.
Bayesian neural networks can be partially stochastic without losing predictive power.
problem The necessity of fully stochastic parameters in Bayesian neural networks.
method Theoretical and empirical investigation of partially stochastic networks compared to fully stochastic ones.
result Expressive predictive distributions require only small amounts of stochasticity, and partially stochastic networks can match or outperform fully stochastic networks.
This study optimizes multi-modal learning thresholds and algorithms in high dimensions.
problem Optimizing multi-modal learning performance in high-dimensional data.
method Analytical quantification and derivation of AMP algorithm with state evolution analysis.
result Bayes-optimal performance and recovery thresholds derived for multi-modal data.
Hashing has been widely adopted for large-scale data retrieval in many domains, due to its low storage cost and high retrieval speed. Existing cross-modal hashing methods optimistically assume that the correspondence between training samples across modalities are readily available. This assumption is unrealistic in pra…
Deep learning approximates PDE evolution operators from solution data.
problem Recovering unknown time-dependent PDEs from solution data.
method Approximate evolution operator in modal space, train deep neural network.
result Deep learning method accurately approximates PDE solutions.
MAESTRO improves multimodal learning for dynamic time series with adaptive attention and robustness.
problem Challenges in multimodal learning, especially in healthcare and daily living.
method Dynamic intra- and cross-modal interactions, symbolic tokenization, adaptive attention budgeting, sparse cross-modal attention, MoE mechanism.
result Average relative improvements of 4% and 8% over existing multimodal and multivariate approaches, respectively, under complete observations.
Classification using multimodal data arises in many machine learning applications. It is crucial not only to model cross-modal relationship effectively but also to ensure robustness against loss of part of data or modalities. In this paper, we propose a novel deep learning-based multimodal fusion architecture for class…
Proposes a multimodal deep generative model for semi-supervised learning with class imbalance.
problem Class imbalance in semi-supervised learning with partial supervision.
method Separate encoders for each modality, sharing latent variables, and using Student's t-distributions for prior, encoder, and decoder.
result Outperforms baseline methods in generalization and classification performance for partially labeled multimodal data.
Advances citation and subject label recommendation using multi-modal adversarial autoencoders.
problem Improving recommendation systems for citations and subject labels.
method Multi-modal adversarial autoencoders with adversarial regularization, sparsity, and input modality analysis.
result Adversarial regularization consistently improves recommendation performance.
One primary focus in multimodal feature extraction is to find the representations of individual modalities that are maximally correlated. As a well-known measure of dependence, the Hirschfeld-Gebelein-Rényi (HGR) maximal correlation becomes an appealing objective because of its operational meaning and desirable propert…
Pre-training on different modalities improves Transformer performance in offline reinforcement learning.
problem Improving Transformer-based models for offline reinforcement learning tasks.
method Empirical investigation of pre-training on language and vision data, analysis of internal representations, and fine-tuning with no context.
result Pre-trained Transformers with language data can utilize context-like information to solve reinforcement learning tasks efficiently.
New method trains partial Bayesian neural networks efficiently.
problem Challenges in approximating multi-modal latent variable distributions in pBNNs.
method Formulates pBNN training as a Feynman--Kac model and uses sequential Monte Carlo samplers.
result Proposed training scheme outperforms state of the art in predictive performance.
Adaptive anchor methods improve multi-modal learning by balancing intra-modal and inter-modal information.
problem Fixed anchor methods limit multi-modal learning by over-reliance on a single modality and inadequate cross-modal correlation.
method Adaptive anchor methods using centroid-based anchors from all modalities.
result Adaptive anchor methods like CentroBind consistently outperform fixed anchor methods across various datasets.
New method for partial matching of shapes with Varifolds.
problem Matching structures with topological or shape differences.
method Varifold shape representation and LDDMM framework.
result Effective partial matching despite topological differences.
KD-Net transfers knowledge from multi-modal to mono-modal segmentation networks.
problem Limited acquisition of multiple imaging modalities in clinical settings.
method Generalized distillation framework adapted for mono-modal networks.
result The student network outperforms baseline mono-modal networks in brain tumor segmentation.
MHVAE learns cross-modality inference inspired by human cognition.
problem Cross-modality inference in multimodal data.
method Hierarchical multimodal generative model with modality-specific and joint-modality distributions.
result MHVAE performs on par with state-of-the-art models on multimodal datasets.
The paper analyzes and proposes an algorithm for multi-modal nonlinear embeddings with theoretical performance bounds.
problem Generalizability of multi-modal nonlinear embeddings to unseen data.
method Theoretical analysis and a multi-modal nonlinear representation learning algorithm motivated by performance bounds.
result The proposed algorithm yields promising performance in multi-modal image classification and cross-modal image-text retrieval applications.
MMVAE learns multi-modal data with shared and private latent spaces.
problem Learning useful representations across multiple data modalities.
method Mixture-of-experts variational autoencoder (MMVAE).
result MMVAE satisfies four criteria for multi-modal learning.
COBRA reduces modality gap in cross-modal tasks.
problem Joint embedding spaces fail to sufficiently reduce modality gap in multi-modal tasks.
method COBRA trains image and text modalities in a joint fashion using Contrastive Predictive Coding and Noise Contrastive Estimation.
result COBRA significantly reduces the modality gap and generates robust joint-embedding space.
Proposes a novel network for CTR prediction by learning modality-specific and modality-invariant representations.
problem Learning good representation of items from multimodal features in E-commerce is challenging due to redundant information across modalities.
method Introduces a Multimodal Adversarial Representation Network (MARN) that calculates modality-specific weights and learns modality-invariant representations.
result Consistently achieves remarkable improvements over state-of-the-art methods in CTR prediction.
Combining complementary information from multiple modalities is intuitively appealing for improving the performance of learning-based approaches. However, it is challenging to fully leverage different modalities due to practical challenges such as varying levels of noise and conflicts between modalities. Existing metho…
We investigate deep generative models that can exchange multiple modalities bi-directionally, e.g., generating images from corresponding texts and vice versa. Recently, some studies handle multiple modalities on deep generative models, such as variational autoencoders (VAEs). However, these models typically assume that…
Improves video search by balancing text and visual modalities.
problem Modality imbalance in video search models, focusing mainly on text matching.
method Proposes MBVR with MS samples and DM to balance modalities.
result Empirically shows significant improvement in modality balance and search effectiveness.
Multimodal sentiment analysis is a core research area that studies speaker sentiment expressed from the language, visual, and acoustic modalities. The central challenge in multimodal learning involves inferring joint representations that can process and relate information from these modalities. However, existing work l…
MoCA uses a novel autoencoder to analyze multi-modal health data.
problem Challenges in analyzing continuous multi-modal health data from wearable devices.
method Proposes MoCA, a self-supervised learning framework combining transformer and masked autoencoder methods.
result Demonstrates strong performance boosts across reconstruction and classification tasks.
We explore training an automatic modality tagger. Modality is the attitude that a speaker might have toward an event or state. One of the main hurdles for training a linguistic tagger is gathering training data. This is particularly problematic for training a tagger for modality because modality triggers are sparse for…
Obtaining common representations from different modalities is important in that they are interchangeable with each other in a classification problem. For example, we can train a classifier on image features in the common representations and apply it to the testing of the text features in the representations. Existing m…
Framework for handling long-tailed multi-modal data.
problem Class imbalance and long-tailed distributions in multi-modal data.
method Multi-expert architecture with modality-specific networks and dynamic fusion weights.
result Framework outperforms existing methods in long-tailed, class-imbalanced scenarios.
Paper tackles cross-modal anomalies in multi-source data.
problem Detect anomalies in multi-modal data where patterns are inconsistent across different sources.
method Proposes a deep structured anomaly detection framework.
result Demonstrates effectiveness on real-world datasets.
TAP transfers knowledge from unlabeled data to improve cross-modal learning.
problem Improving supervised learning performance using unlabeled data from a different modality.
method Probabilistic approach for missing information estimation, kernel regression, cross-attention module, TAP neural network.
result TAP significantly improves generalization across different domains and neural network architectures.
Study improves product categorization on Amazon using multi-modal fusion.
problem Multi-label product categorization in e-commerce.
method Late fusion of image, description, and title modalities using modified CNN and ResNet-50 models.
result Tri-modal late fusion model achieved an F1 score of 88.2%, significantly better than single modal models. We propose a novel method, Modality-based Redundancy Reduction Fusion (MRRF), for understanding and modulating the relative contribution of each modality in multimodal inference tasks. This is achieved by obtaining an (M+1)-way tensor to consider the high-order relationships between M modalities and the output laye…
DNN-based cross-modal retrieval has become a research hotspot, by which users can search results across various modalities like image and text. However, existing methods mainly focus on the pairwise correlation and reconstruction error of labeled data. They ignore the semantically similar and dissimilar constraints bet…
This work improves multi-modal generative models by using permutation-invariant neural networks.
problem Improving multi-modal generative models with tighter variational objectives.
method Developed more flexible aggregation schemes based on permutation-invariant neural networks.
result Our variational objective and flexible aggregation models can better approximate the true joint distribution.
A framework for uncertainty-aware multimodal learning using conformal Shapley intervals.
problem Uncertainty and modality level importance in multimodal learning.
method Introduces conformal Shapley intervals to quantify modality level importance and uncertainty.
result Demonstrates meaningful uncertainty quantification and strong predictive performance.
This paper studies the nonparametric modal regression problem systematically from a statistical learning view. Originally motivated by pursuing a theoretical understanding of the maximum correntropy criterion based regression (MCCR), our study reveals that MCCR with a tending-to-zero scale parameter is essentially moda…
Symile learns joint representations across multiple modalities, outperforming pairwise CLIP.
problem Pairwise contrastive learning fails to capture joint information between multiple modalities.
method Symile uses a flexible, architecture-agnostic objective to learn modality-specific representations by deriving a lower bound on total correlation.
result Symile outperforms pairwise CLIP on cross-modal classification and retrieval across various datasets.
A method uses autoencoders to align multi-modal neuron data.
problem Inconsistent cell type definitions across different data modalities.
method Coupled training of autoencoders for cross-modal alignment.
result Representations learned by coupled autoencoders can identify single-modality sampled cell types.
ROME improves density estimation for multi-modal, non-normal data.
problem Robust multi-modal density estimation in non-normal, highly correlated distributions.
method ROME uses clustering to segment multi-modal data into uni-modal clusters, then combines KDE estimates for each cluster.
result ROME outperforms state-of-the-art methods and is more robust to various distributions.
ESE-FN improves elderly activity recognition accuracy.
problem Recognizing individual actions and human-object interactions in elderly activities.
method Exploits multi-modal features from RGB videos and skeleton sequences using ESE attentions and a new Multi-modal Loss.
result ESE-FN achieves best accuracy on ETRI-Activity3D dataset.
We investigate deep generative models that can exchange multiple modalities bi-directionally, e.g., generating images from corresponding texts and vice versa. A major approach to achieve this objective is to train a model that integrates all the information of different modalities into a joint representation and then t…
New model learns from missing modalities and class labels.
problem Conflict between learning joint representations and modalities in multi-modal data.
method Introduces a novel conditional multi-modal discriminative model using an informative prior distribution and a likelihood-free objective function.
result Our model achieves state-of-the-art results in downstream classification, acoustic inversion, and image and annotation generation.
Proposes a parametric modal regression method using the implicit function theorem.
problem Finding conditional modes for multi-modal conditional distributions.
method Uses the implicit function theorem to develop an objective function for learning a joint function over inputs and targets.
result Empirically demonstrates scalability and effectiveness in learning multi-valued functions and high-dimensional inputs.