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…
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “cross-modal retrieval”
Cross-modal hashing has been receiving increasing interests for its low storage cost and fast query speed in multi-modal data retrievals. However, most existing hashing methods are based on hand-crafted or raw level features of objects, which may not be optimally compatible with the coding process. Besides, these hashi…
T-EMDE bridges the heterogeneity gap between image and text modalities.
problem Finding similarities between image and text modalities with non-related feature spaces.
method Inspired by EMDE, T-EMDE uses sketches for multimodal operations, avoiding self-attention's quadratic complexity.
result T-EMDE achieves state-of-the-art results and reduces model latency.
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…
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.
Supervised cross-modal hashing has gained increasing research interest on large-scale retrieval task owning to its satisfactory performance and efficiency. However, it still has some challenging issues to be further studied: 1) most of them fail to well preserve the semantic correlations in hash codes because of the la…
The heterogeneity-gap between different modalities brings a significant challenge to multimedia information retrieval. Some studies formalize the cross-modal retrieval tasks as a ranking problem and learn a shared multi-modal embedding space to measure the cross-modality similarity. However, previous methods often esta…
Successful multimodal search and retrieval requires the automatic understanding of semantic cross-modal relations, which, however, is still an open research problem. Previous work has suggested the metrics cross-modal mutual information and semantic correlation to model and predict cross-modal semantic relations of ima…
New methods estimate point-wise dependency from neural MI models.
problem Estimating point-wise dependency between different events.
method Developed two methods: Probabilistic Classifier and Density-Ratio Fitting.
result Demonstrated effectiveness in MI estimation, self-supervised representation learning, and cross-modal retrieval.
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.
Finite-size scaling of hetero-associative retrieval in continuous-signal-driven Ising spin systemscond-mat.dis-nn
A bridge between continuous signals and discrete Ising spins for associative memory.
problem Associative memory in continuous-signal-driven Ising spin systems.
method Multilayer Ising framework with PCA whitening and SimHash projection, coupled to pseudo-inverse memory couplings.
result Finite-size scaling of operational storage capacity with , approaching .
Multimodal learning aims to discover the relationship between multiple modalities. It has become an important research topic due to extensive multimodal applications such as cross-modal retrieval. This paper attempts to address the modality heterogeneity problem based on Gaussian process latent variable models (GPLVMs)…
This research shows how to learn shared representations from unpaired data.
problem Learning shared representations from unpaired data.
method Spectral embeddings of random walk matrices from each unimodal representation.
result Shared representations can be learned almost exclusively from unpaired data.
GWCA analyzes cross-graph correlations for movie retrieval.
problem Cross heterogeneous graph comparison in movie retrieval.
method Spectral graph filtering, Wasserstein metric learning, generalized eigenvalue decomposition.
result Surprise consistency in learning processes and closed-form solution.
Feed-forward networks are widely used in cross-modal applications to bridge modalities by mapping distributed vectors of one modality to the other, or to a shared space. The predicted vectors are then used to perform e.g., retrieval or labeling. Thus, the success of the whole system relies on the ability of the mapping…
Modeling the relationship between chemical structure and molecular activity is a key goal in drug development. Many benchmark tasks have been proposed for molecular property prediction, but these tasks are generally aimed at specific, isolated biomedical properties. In this work, we propose a new cross-modal small mole…
Hashing techniques have been applied broadly in retrieval tasks due to their low storage requirements and high speed of processing. Many hashing methods based on a single view have been extensively studied for information retrieval. However, the representation capacity of a single view is insufficient and some discrimi…
Unsupervised methods have proven effective for discriminative tasks in a single-modality scenario. In this paper, we present a multimodal framework for learning sparse representations that can capture semantic correlation between modalities. The framework can model relationships at a higher level by forcing the shared …
MuLan links music audio to natural language tags.
problem Traditional music tagging systems use rigid attributes; MuLan aims to link audio directly to natural language.
method Joint audio-text embedding model trained on 44 million music recordings and text annotations.
result MuLan's embeddings enable zero-shot functionalities and transfer learning.
Paper proposes a new unsupervised method for cross-modality data translation without requiring direct mappings.
problem Tackles the challenge of zero-shot cross-modality data translation with fidelity.
method Mutual Information guided Diffusion cross-modality data translation Model (MIDiffusion) using score-matching and stochastic diffusion.
result Empirically shows advanced performance compared to other generative models.
Study improves cross-modal bike-share and transit demand prediction.
problem Cross-modal ripple effects in urban transportation demand.
method Transfer learning and stacked LSTM models for cross-modal demand prediction.
result Transfer learning models outperform unimodal models in cross-modal demand prediction.
We address the problem of learning fine-grained cross-modal representations. We propose an instance-based deep metric learning approach in joint visual and textual space. The key novelty of this paper is that it shows that using per-image semantic supervision leads to substantial improvement in zero-shot performance ov…
MHVAE: a Human-Inspired Deep Hierarchical Generative Model for Multimodal Representation Learningcs.LG
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.
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.
In this paper, we propose a novel structure for a cross-modal data association, which is inspired by the recent research on the associative learning structure of the brain. We formulate the cross-modal association in Bayesian inference framework realized by a deep neural network with multiple variational auto-encoders …
Survey on LLMs for time series analytics across various domains.
problem Cross-modality gap between LLMs and time series data.
method Taxonomy of approaches, cross-modality strategies, and experiments on multimodal datasets.
result Effective combinations of textual data and cross-modality strategies enhance time series analytics.
CMTF improves financial market forecasting by fusing multiple data types.
problem Lack of effective integration of diverse financial data sources.
method Transformer-based deep learning framework with tensor interpretation and auto-training.
result CMTF outperforms classical and deep learning models in price direction classification.
SBCA optimizes portfolios by fusing price data and text sentiment.
problem Insufficient integration of multi-modal information in traditional portfolio optimization models.
method Cross-modal BERT-driven Actor-Critic framework with gated fusion and constraint embedding.
result SBCA outperforms benchmarks in portfolio value, return, Sharpe ratio, and maximum drawdown.
Improved sentiment analysis with multimodal data.
problem Cross-modal sentiment analysis in social media, customer service, and video blogs.
method Gated mechanism for attention-based learning of cross-modal interactions, with experiments on CMU-MOSI and CMU-MOSEI datasets.
result 1.6% and 1.34% absolute improvement over state-of-the-art.
The Gaussian process latent variable model (GP-LVM) is a popular approach to non-linear probabilistic dimensionality reduction. One design choice for the model is the number of latent variables. We present a spike and slab prior for the GP-LVM and propose an efficient variational inference procedure that gives a lower …
We introduce a deep multitask architecture to integrate multityped representations of multimodal objects. This multitype exposition is less abstract than the multimodal characterization, but more machine-friendly, and thus is more precise to model. For example, an image can be described by multiple visual views, which …
Several tasks in machine learning are evaluated using non-differentiable metrics such as mean average precision or Spearman correlation. However, their non-differentiability prevents from using them as objective functions in a learning framework. Surrogate and relaxation methods exist but tend to be specific to a given…
Cross-modal Recurrent Models for Weight Objective Prediction from Multimodal Time-series Datastat.ML
We analyse multimodal time-series data corresponding to weight, sleep and steps measurements. We focus on predicting whether a user will successfully achieve his/her weight objective. For this, we design several deep long short-term memory (LSTM) architectures, including a novel cross-modal LSTM (X-LSTM), and demonstra…
Unified model learns joint and individual features from brain imaging data.
problem Integrating structural and functional connectivity data for behavioral phenotypes.
method Cross-Modal Joint-Individual Variational Network (CM-JIVNet) with multi-head attention fusion.
result CM-JIVNet outperforms in cross-modal reconstruction and behavioral trait prediction.
Proposes a method to align language and image data.
problem Aligning language and image data for better understanding.
method Uses triplet loss to learn consistent embeddings of language and images.
result Outperforms four baselines across multiple metrics.
GEM learns a manifold for cross-modal data, capturing structure without modality dependence.
problem Modality-specific neural models limit flexibility and custom architecture.
method Casts learning as manifold inference, enforcing coverage, linearity, and isometry.
result GEM learns latent structure across image, shape, audio, and cross-modal domains.
AnomalyDAE detects anomalies in networks by learning cross-modality interactions.
problem Detecting anomalies in attributed networks where structure and attributes interact.
method Dual autoencoder framework with attention mechanism for joint learning of structure and attribute embeddings.
result AnomalyDAE effectively detects anomalies by reconstructing node attributes and structures.
This paper addresses the challenging task of video captioning which aims to generate descriptions for video data. Recently, the attention-based encoder-decoder structures have been widely used in video captioning. In existing literature, the attention weights are often built from the information of an individual modali…
This paper introduces a way to learn cross-modal convolutional neural network (X-CNN) architectures from a base convolutional network (CNN) and the training data to reduce the design cost and enable applying cross-modal networks in sparse data environments. Two approaches for building X-CNNs are presented. The base app…
Determining the extent to which different cognitive modalities (understood here as the set of cognitive processes underlying the elaboration of a stimulus by the brain) rely on overlapping neural representations is a fundamental issue in cognitive neuroscience. In the last decade, the identification of shared activity …
Labeling training datasets has become a key barrier to building medical machine learning models. One strategy is to generate training labels programmatically, for example by applying natural language processing pipelines to text reports associated with imaging studies. We propose cross-modal data programming, which gen…
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.
Improved 3D ECG feature attributions for clinical interpretation.
problem Lack of interpretability in deep learning models for 12-lead ECG analysis.
method Cross-modal mapping of feature attributions from 12-lead ECG models onto CineECG 3D space.
result Mapped feature attributions yield higher Dice scores than standard 12-lead attributions.
Modern medicine requires generalised approaches to the synthesis and integration of multimodal data, often at different biological scales, that can be applied to a variety of evidence structures, such as complex disease analyses and epidemiological models. However, current methods are either slow and expensive, or inef…
Unified multi-view learning framework using OPLS with regularization and deep extensions.
problem Improving multi-view learning for classification and feature extraction.
method Orthonormalized Partial Least Squares (OPLS) with regularization and deep extensions.
result Unified multi-view learning framework with improved performance.
New method identifies shared components from unpaired multimodal mixtures.
problem Identify shared components from unpaired multimodal mixtures.
method Distribution divergence minimization-based loss with sufficient conditions for identifiability.
result Sufficient conditions for shared component identifiability from unaligned multimodal mixtures.
Learning social media data embedding by deep models has attracted extensive research interest as well as boomed a lot of applications, such as link prediction, classification, and cross-modal search. However, for social images which contain both link information and multimodal contents (e.g., text description, and visu…
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…