Predicts whether an image is an abstraction of text or vice versa.
problem Understanding semantic cross-modal relations between images and text.
method Introduces a new metric (ABS) and a deep learning autoencoder approach to predict it.
result Demonstrates feasibility of predicting the relative abstractness level of image-text pairs.
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…
A new hashing method handles complex multi-level labels.
problem Handling complex multi-level labels in cross-modal data retrieval.
method Derives a semantic ranking list from feature and label information, integrates semantic ranking into deep cross-modal hashing.
result RDCMH outperforms other methods in cross-modal retrieval applications.
Efficient Discrete Supervised Hashing improves cross-modal retrieval by preserving semantic correlations and reducing quantization error.
problem Challenges in preserving semantic correlations and reducing quantization error in cross-modal hashing for large-scale retrieval.
method Collective matrix factorization on heterogenous features and semantic embedding with class labels to learn hash codes efficiently.
result EDSH produces superior performance in both accuracy and scalability over existing methods.
Adaptive cross-modal few-shot learning improves performance in image classification.
problem Few-shot classification with limited data.
method Adaptive combination of visual and semantic features.
result Model outperforms uni-modality and modality-alignment methods.
TCT learns multimodal sequence representations by translating from related sequences.
problem Challenges in learning semantic representations from multimodalities.
method Transformer based Cross-modal Translator (TCT) combined with Multimodal Transformer Network (MTN).
result Proposed method achieves new state-of-the-art performance on video-grounded dialogue.
CLAREL improves zero-shot learning by using per-image semantic supervision and metric rescaling.
problem Fine-grained cross-modal representation learning for zero-shot classification.
method Instance-based deep metric learning in joint visual and textual space, using per-image semantic supervision and metric rescaling.
result CLAREL consistently outperforms existing approaches on fine-grained zero-shot learning datasets.
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.
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…
Paper proposes a harmonized approach to multimodal learning using GPLVMs.
problem Modality heterogeneity in multimodal data.
method Develops a novel learning scheme called Harmonization to jointly learn latent model parameters from different modalities.
result Experimental results show superior performance in cross-modal retrieval tasks.
New method transfers between different modalities using latent spaces.
problem Cross-modal domain transfer between pretrained generative models.
method Learning a shared latent space between two generative models.
result Variational autoencoder best bridges latent spaces of different models.
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.
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 …
We address the problem of image translation between domains or modalities for which no direct paired data is available (i.e. zero-pair translation). We propose mix and match networks, based on multiple encoders and decoders aligned in such a way that other encoder-decoder pairs can be composed at test time to perform u…
A novel cross-modal auto-encoder associates different data types efficiently.
problem Cross-modal data association in heterogeneous datasets.
method Bayesian inference framework with variational auto-encoders and associators.
result Successfully associates visual and auditory data with minimal paired data.
Unified framework for generating meteorological time series from text.
problem Lack of large-scale, physically grounded multimodal datasets and architectures ignoring spectral-temporal structure.
method Introduce MeteoCap-3B dataset and MTransformer model.
result State-of-the-art generation quality, accurate cross-modal alignment, strong semantic controllability.
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.
New unsupervised learning framework for sound recognition.
problem Learning sound recognition without explicit labels.
method Combines self-supervised and clustering objectives with active learning.
result Achieves state-of-the-art unsupervised audio representation with reduced labels.
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.
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.
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.
Multimodal sensory data resembles the form of information perceived by humans for learning, and are easy to obtain in large quantities. Compared to unimodal data, synchronization of concepts between modalities in such data provides supervision for disentangling the underlying explanatory factors of each modality. Previ…
Efficient video captioning model captures cross-modal interactions.
problem Capturing frame-level cross-modal interactions in video captioning.
method Proposes High-Order Cross-Modal Attention (HOCA) and Low-Rank HOCA.
result Low-Rank HOCA achieves state-of-the-art performance.
FlexCMH learns effective hashing codes from weakly-paired data.
problem Cross-modal hashing assumes perfect correspondence between samples, which is unrealistic.
method FlexCMH uses clustering-based matching to find potential correspondence and jointly optimizes it with hashing functions.
result FlexCMH achieves significantly better results than state-of-the-art methods.
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.
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…
Service robots learn new tasks more efficiently with ISI, improving query performance and reducing training time.
problem Incremental learning of semantic concepts in multi-relational embeddings for service robots.
method Incremental Semantic Initialization (ISI) that allows new semantic concepts to be initialized in relation to previously learned embeddings.
result ISI improves immediate query performance by 41.4% and reduces the number of epochs to approach model convergence by 78.2%.
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.
Cross-modal data programming speeds medical machine learning.
problem Labeling medical datasets is time-consuming and requires expert knowledge.
method Generates training labels by writing rules over auxiliary modalities, estimating accuracies and correlations.
result Matches or exceeds hand-labeling with statistical significance, faster and more flexible.
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.
PIMA autoencoders discover shared features in multimodal scientific data.
problem Discovering shared information in high-throughput scientific datasets.
method Physics-informed multimodal autoencoders (PIMA) with Gaussian mixture prior and product of experts formulation.
result Accurate cross-modal inference between images and mechanical stress-strain response in lattice metamaterials.
Paper tackles zero-shot learning for semantic image interpretation.
problem Extracting structured semantic descriptions from images requires complete training sets, which are often unavailable.
method Uses Logic Tensor Networks to leverage logical constraints and similarities among relationships in the training set.
result Background knowledge can alleviate the incompleteness of training sets, improving zero-shot learning performance.
Computational modeling of human multimodal language is an emerging research area in natural language processing spanning the language, visual and acoustic modalities. Comprehending multimodal language requires modeling not only the interactions within each modality (intra-modal interactions) but more importantly the in…
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.
New test assesses shared brain activity across different cognitive modalities.
problem Determining if different cognitive modalities use overlapping neural representations.
method Formulated a statistical hypothesis testing approach using permutation testing.
result New test (CMPT) has greater statistical power than cross-modal decoding while maintaining low Type I errors.
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.
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…
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 …
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.
EmbraceNet improves robustness in multimodal classification.
problem Robust multimodal classification with partial data loss.
method Deep learning architecture for multimodal fusion.
result EmbraceNet outperforms other models in partial data scenarios.
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.
Study reduces redundant information in multi-modal datasets.
problem Redundant information increases data size and costs.
method Multimodal framework using entropy, mutual info, Lasso, SHAP, PCA, topic modeling.
result Significant feature space can be pruned with minimal loss in performance.
Deep learning model improves medical diagnosis and reduces patient time.
problem Ineffective and slow methods for synthesizing multimodal medical data.
method Cross-modal deep learning architecture with co-attention mechanism.
result Model outperforms previous methods by 2.35% and is 53% more efficient.
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…
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…