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.

169,051 papers · 148 categories

Trend · papers per month

87175262349 · Jun 202019922001200920182026
48 results for content representation

New model learns content and transformation separately from data.

problem Learning disentangled representations from data without explicit labels.
method Group-based variational autoencoders, assuming content and transformation groups.
result Model learns generalizable content representations from unseen data.

Unsupervised learning of speech representations using WaveNet autoencoders.

problem Extract meaningful latent representations of speech signals.
method Applying autoencoding neural networks to speech waveforms, using a high capacity WaveNet decoder, and comparing three variants of latent representations.
result Comparable performance with top entries in the ZeroSpeech 2017 unsupervised acoustic unit discovery task.

This work improves disentanglement by preventing style variables from encoding content-related features.

problem Disentanglement of content and style in data representations using Variational Autoencoders.
method Adversarial training with mutual information minimization to prevent content information leakage in style representations.
result The method efficiently separates content and style related attributes and generalizes to unseen data.

Proposes a VAE variant for ordinal content factors.

problem Isolating ordinal-valued content factors in deep latent variable models.
method Introduces a partially ordered set (poset) structure and a conditional Gaussian spacing prior model.
result Significant improvements in content-style separation over previous non-ordinal approaches.

A method for disentangling text representations without supervision.

problem Challenges in learning disentangled representations of natural language.
method Information-theoretic guidance to induce independent style and content embeddings.
result High quality disentangled representations in terms of content and style preservation.

Unified method for disentangling classes and content improves AI representation learning.

problem Current methods struggle with disentangling class and content variations.
method LORD: Latent Optimization for Representation Disentanglement with asymmetric noise regularization.
result LORD achieves superior disentanglement performance compared to existing methods.

A new method for image translation using disentangled style and content preservation.

problem Difficulty in maintaining original content during reverse diffusion in diffusion-based image translation.
method Disentangled style and content representation using intermediate keys from ViT model, CLIP loss, semantic divergence loss, and resampling strategy.
result Outperforms state-of-the-art models in text-guided and image-guided translation tasks.

Applying traditional collaborative filtering to digital publishing is challenging because user data is very sparse due to the high volume of documents relative to the number of users. Content based approaches, on the other hand, is attractive because textual content is often very informative. In this paper we describe …

2015-01-18abs ↗pdf ↗

The study analyzes how data augmentation helps isolate content from style in self-supervised learning.

problem Understanding how data augmentation affects the separation of content and style in self-supervised learning.
method Formulated a latent variable model with content and style components, studied identifiability of latent representation, and introduced a dataset to test the theory.
result Sufficient conditions for identifying the invariant content partition in self-supervised learning.

RALM extends exposure for long-tail contents in real-time recommender systems.

problem Lack of timely exposure for long-tail contents in recommender systems.
method Real-time attention-based look-alike model (RALM) with seeds-to-user similarity prediction and user representation learning.
result RALM outperforms traditional look-alike models in effectiveness and real-time performance.

Content based image retrieval, a technique which uses visual contents of image to search images from large scale image databases according to users' interests. This paper provides a comprehensive survey on recent technology used in the area of content based face image retrieval. Nowadays digital devices and photo shari…

2014-02-20abs ↗pdf ↗

Study shows label noise impacts neural representations' information content, revealing double descent behavior.

problem Impact of label noise on neural network hidden representations.
method Information Imbalance proxy of conditional mutual information to compare hidden representations.
result Representations learned with noisy labels are more informative than those with clean labels in the underparameterized regime, and equally informative in the overparameterized regime.

Study predicts email triage actions using content-based approach.

problem Predicting user triage actions on incoming emails.
method Formulated as a recommendation problem, uses content-based approach with additional similarity features.
result Proposed framework achieves better performance than state-of-the-art deep recommendation methods.

Detects anomalous behavior in social media users by analyzing content and connections.

problem Identifying disruptive patterns in user behavior on social media platforms.
method Joint representation learning of content and connection to detect anomalous behavior.
result Observed densely connected users engaging in local politics and exhibiting troll-like behavior.

DAM with MRL improves relational reasoning in MANNs.

problem Limited performance of associative memory networks on complex relational reasoning tasks.
method Distributed Associative Memory architecture with Memory Refreshing Loss.
result Enhanced relation reasoning performance of MANNs on long temporal sequence data.

A new framework converts EEG signals between subjects and tasks.

problem Noise and variability in EEG data hinder generalizable signal extraction.
method Contrastive Split-Latent Permutation Autoencoder (CSLP-AE) framework.
result The CSLP-AE framework enables zero-shot conversion between unseen subjects.

Study reveals differences in medical image models' hidden representation refinement.

problem Understanding how intrinsic dimensionality changes in neural network hidden representations across different domains.
method Analysis of 11 natural and medical image datasets using 6 network architectures.
result Medical image models refine hidden representations earlier, suggesting differences in feature abstraction.

Builds a novel educational recommender for lifelong learners.

problem Challenges in creating scalable and transparent models for lifelong learning.
method Integrative approach combining content novelty, background knowledge, and learner engagement.
result TrueLearn achieves promising performance while retaining a human interpretable learner model.

A movie multilayer network model captures narration from script, subtitles, and content.

problem Discovering content and stories in movies using network models.
method Developed a multilayer network model using visual and textual semantic cues.
result Demonstrated the effectiveness of the model on the Star Wars saga.

DEMUD-VIS detects novel image content and explains it visually.

problem Detecting and explaining novel image content in large datasets.
method Uses CNN for feature extraction, reconstruction error for novelty detection, and up-convolutional networks for image reconstruction.
result Demonstrates visual explanations of novel image content on diverse datasets.

Paper proposes LAHA to improve XMTC by integrating document content and label correlation.

problem Challenges in tagging documents with most relevant labels from a large label set.
method Hybrid attention deep neural network model (LAHA) that combines multi-label self-attention and adaptive fusion strategies.
result LAHA outperforms state-of-the-art methods, especially on tail labels.

System converts 3D lung nodule images into embeddings for retrieval.

problem Retrieving similar 3D lung nodule images for radiologist decision support.
method 3D deep learning, semantic representation, transfer learning, similarity score.
result System can measure similarity between nodule annotations and CBIR results.

The paper proposes a model to learn motion perception in V1 using vector and matrix representations.

problem Motion perception in primary visual cortex (V1).
method Coupling vector representations of local contents and matrix representations of local pixel displacements.
result The model can learn Gabor-like filter pairs and infer local motions.

In information retrieval, a fundamental goal is to transform a document into concepts that are representative of its content. The term "representative" is in itself challenging to define, and various tasks require different granularities of concepts. In this paper, we aim to model concepts that are sparse over the voca…

2012-04-11abs ↗pdf ↗

Paper generates personalized fonts from a few characters.

problem Creating personalized fonts from a limited set of characters.
method Designs a network framework to extract and recombine character content and style using various neural networks.
result Generated characters are structurally similar to real characters.

ST-STORM separates semantic and appearance features for robust representation learning.

problem Traditional SSL methods fail to capture appearance cues in critical applications.
method Hybrid SSL framework with two latent streams, Content and Style, disentangled through gating mechanisms.
result The Style branch effectively isolates complex appearance phenomena without degrading semantic performance.

Automated detection of new, interesting, unusual, or anomalous images within large data sets has great value for applications from surveillance (e.g., airport security) to science (observations that don't fit a given theory can lead to new discoveries). Many image data analysis systems are turning to convolutional neur…

2018-06-21abs ↗pdf ↗

Study shows online learning algorithms incentivize low-quality content, proposing new algorithms to improve quality.

problem Online learning algorithms in content recommender systems incentivize producers to create low-quality content.
method Analyzed the game between producers and content quality, designed new learning algorithms to incentivize high effort and quality.
result New algorithms incentivize producers to invest high effort and achieve high user welfare, improving content quality.

Online voting is an emerging feature in social networks, in which users can express their attitudes toward various issues and show their unique interest. Online voting imposes new challenges on recommendation, because the propagation of votings heavily depends on the structure of social networks as well as the content …

2017-12-03abs ↗pdf ↗

This research predicts the popularity of new video contents using a hybrid machine learning approach.

problem Predicting the popularity of new video contents before they are published.
method Hybrid machine learning approach combining XGBoosting and deep neural nets, using metadata and categorical embedding techniques.
result Achieved better performance than standalone methods, validated on a dataset from a top streaming service.

Many businesses are using recommender systems for marketing outreach. Recommendation algorithms can be either based on content or driven by collaborative filtering. We study different ways to incorporate content information directly into the matrix factorization approach of collaborative filtering. These content-booste…

2012-10-20abs ↗pdf ↗