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.
Meta Fusion integrates various multimodal data fusion strategies into a unified framework.
We present a baseline approach for cross-modal knowledge fusion. Different basic fusion methods are evaluated on existing embedding approaches to show the potential of joining knowledge about certain concepts across modalities in a fused concept representation.
A new Fusion method combines multiple distributions efficiently.
Adaptive data fusion boosts efficiency in multi-task optimization.
A new memory-based fusion layer improves multi-modal deep learning performance.
In recent years, multi-modal fusion has attracted a lot of research interest, both in academia, and in industry. Multimodal fusion entails the combination of information from a set of different types of sensors. Exploiting complementary information from different sensors, we show that target detection and classificatio…
Fusion of transformer networks using optimal transport for improved 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…
LMGPs enable efficient, accurate data fusion across multiple data sources.
Bayesian fusion improves radar target recognition for UAVs.
Novel fusion network combines polarization and radiomics features for liver cancer classification.
Algorithms that fuse multiple input sources benefit from both complementary and shared information. Shared information may provide robustness against faulty or noisy inputs, which is indispensable for safety-critical applications like self-driving cars. We investigate learning fusion algorithms that are robust against …
This paper reviews deep learning for multi-modality medical image segmentation.
Paper proposes a new method for Bayesian linear regression using spike-and-slab priors.
For most problems in science and engineering we can obtain data sets that describe the observed system from various perspectives and record the behavior of its individual components. Heterogeneous data sets can be collectively mined by data fusion. Fusion can focus on a specific target relation and exploit directly ass…
Multimodal fusion is considered a key step in multimodal tasks such as sentiment analysis, emotion detection, question answering, and others. Most of the recent work on multimodal fusion does not guarantee the fidelity of the multimodal representation with respect to the unimodal representations. In this paper, we prop…
A new combinatorial approach groups regression coefficients for improved accuracy.
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…
A machine learning approach to record fusion with high accuracy.
Paper introduces topological eigenvalue theorems for tensor analysis in multi-modal data.
A novel one-class classifier fusion method for robust anomaly detection.
We present convolutional neural network (CNN) based approaches for unsupervised multimodal subspace clustering. The proposed framework consists of three main stages - multimodal encoder, self-expressive layer, and multimodal decoder. The encoder takes multimodal data as input and fuses them to a latent space representa…
LDF combines neural networks with probabilistic models for data fusion.
In the past few years, a lot of attention has been devoted to multimedia indexing by fusing multimodal informations. Two kinds of fusion schemes are generally considered: The early fusion and the late fusion. We focus on late classifier fusion, where one combines the scores of each modality at the decision level. To ta…
New method learns fusion rules from few images using granular ball priors.
Paper fine-tunes LLMs for financial tasks using data fusion.
Ensemble methods have been widely used for improving the results of the best single classificationmodel. A large body of works have achieved better performance mainly by applying one specific ensemble method. However, very few works have explored complex fusion schemes using het-erogeneous ensembles with new aggregatio…
Sensor fusion has wide applications in many domains including health care and autonomous systems. While the advent of deep learning has enabled promising multi-modal fusion of high-level features and end-to-end sensor fusion solutions, existing deep learning based sensor fusion techniques including deep gating architec…
Fusion framework improves time series classification across different datasets.
Late fusion of clinical notes and physiological data improves ICU mortality prediction.
Proposes Fusion Recurrent Neural Network for sequence data.
We describe a methodology for modeling the performance of decision-level data fusion between different sensor configurations, implemented as part of the JIEDDO Analytic Decision Engine (JADE). We first discuss a Bayesian network formulation of classical probabilistic data fusion, which allows elementary fusion structur…
New fusion blocks improve equivariant neural networks for molecular dynamics.
Proposes clustering and pruning to simplify causal data fusion models.
We propose a generalized class of multimodal fusion operators for the task of visual question answering (VQA). We identify generalizations of existing multimodal fusion operators based on the Hadamard product, and show that specific non-trivial instantiations of this generalized fusion operator exhibit superior perform…
A new method for feature fusion in U-Net decoders using difference-based gating.
New insights into knot fusion numbers via cabling.
Paper detects gradual changes in cluster structure using MC fusion.
We introduce semisimple 2-categories, fusion 2-categories, and spherical fusion 2-categories. For each spherical fusion 2-category, we construct a state-sum invariant of oriented singular piecewise-linear 4-manifolds.
This paper proposes a novel framework for fusing multi-temporal, multispectral satellite images and OpenStreetMap (OSM) data for the classification of local climate zones (LCZs). Feature stacking is the most commonly-used method of data fusion but does not consider the heterogeneity of multimodal optical images and OSM…
Inspired by brain's modality fusion, this paper detects active speakers from audio and video.
Proposes a fusion method for many treatment groups in ITRs.
The sharp and recent increase in the availability of data captured by different sensors combined with their considerably heterogeneous natures poses a serious challenge for the effective and efficient processing of remotely sensed data. Such an increase in remote sensing and ancillary datasets, however, opens up the po…
In this paper we propose a fusion approach to continuous emotion recognition that combines visual and auditory modalities in their representation spaces to predict the arousal and valence levels. The proposed approach employs a pre-trained convolution neural network and transfer learning to extract features from video …
Study knots that divide ribbon knotted surfaces, computing their half ribbon genus and fusion number.
Proposes LVGP for multi-source data fusion in science and engineering.
Proposes a new method for subgroup analysis using optimal trees with parameter fusion.
We address the task of simultaneous feature fusion and modeling of discrete ordinal outputs. We propose a novel Gaussian process(GP) auto-encoder modeling approach. In particular, we introduce GP encoders to project multiple observed features onto a latent space, while GP decoders are responsible for reconstructing the…