knotR package creates visually appealing knot diagrams in R
problem Creating aesthetically pleasing knot diagrams
method Develops knotR package for R programming to optimize knot diagrams
result Systematic creation of production-quality knot artwork
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.
169,341 papers · 148 categories
Trend · papers per month
48 results for “visual appearance”
Person re-identification (re-id), an emerging problem in visual surveillance, deals with maintaining entities of individuals whilst they traverse various locations surveilled by a camera network. From a visual perspective re-id is challenging due to significant changes in visual appearance of individuals in cameras wit…
Model learns disentangled object location and appearance representations.
problem Learning disentangled representations of object location and appearance.
method Probabilistic generative model with amortized variational inference.
result Fully disentangled object location and appearance representations.
Embedding Projector visualizes and interprets embeddings interactively.
problem Exploring properties of embeddings in machine learning.
method Interactive visualization and interpretation tool for embeddings.
result Interactive exploration of embedding properties.
Context-aware ZSL improves object recognition by considering object context.
problem Previous ZSL approaches ignore object context, limiting their effectiveness.
method Proposes a new approach that models the conditional likelihood of objects appearing in specific contexts.
result Contextual information significantly improves ZSL performance and is robust to class imbalance.
We consider the problem of naming objects in complex, natural scenes containing widely varying object appearance and subtly different names. Informed by cognitive research, we propose an approach based on sharing context based object hypotheses between visual and lexical spaces. To this end, we present the Visual Seman…
A model separates visual style from digit type on MNIST and facial features from shape on CelebA.
problem Learning compact, independent factors of data.
method Explicitly encoded in a generative model with two latent spaces: spatial transformations and intrinsic appearance.
result The model separates visual style from digit type on MNIST and facial features from shape on CelebA.
Improved vision-language embeddings boost cross-task learning.
problem Creating general vision systems with better cross-task learning.
method Aligning image-word representations for better cross-task transfer.
result Improved inductive transfer from visual recognition to visual question answering.
Spectral Overlap and a Comparison of Parameter-Free, Dimensionality Reduction Quality Metricsstat.ML
The paper evaluates and compares dimensionality reduction quality metrics without tuning.
problem Evaluating the quality of nonlinear dimensionality reduction visualizations is challenging.
method Comparison of dimensionality reduction quality metrics on datasets with known ground truth manifolds.
result A few methods consistently perform well, with one proposed as a benchmark.
A framework visualizes embedding spaces of neural survival analysis models using anchor directions.
problem Visualizing complex embeddings in neural survival analysis models.
method Estimating anchor directions through clustering or user-supplied concepts, revealing relationships with raw inputs and survival times.
result Visualization strategies reveal how anchor directions relate to raw clinical features and survival time distributions.
New model separates object attributes for better perceptual grouping.
problem Perceptual grouping of complex visual scenes.
method Spatial mixture models with learnable priors.
result Outperforms state-of-the-art methods in perceptual grouping.
A similarity metric for icon sets simplifies design selection.
problem Designing optimal icon sets is challenging and requires expert knowledge.
method Proposed a Siamese Neural Network trained on human-rated data.
result The model effectively captures style and visual identity similarities.
Improved student engagement detection using contextual and visual data.
problem Detecting students' behavioral engagement in real-world settings.
method Two-phase approach: contextual logs for active use, appearance information for engagement inference.
result Improved F1-scores from 0.77 to 0.82 with contextual information.
New visual tool detects financial market changes using multiscaling analysis.
problem Detecting relevant changes in financial time series.
method Time-dependent Generalized Hurst Exponents (GHE) and Change-Point Analysis.
result Identifies patterns distinguishing between uniscaling and multiscaling, and provides warning signals.
NSL layer improves convolutional networks' ability to recognize novel appearances.
problem Convolutional networks struggle with recognizing novel appearances not seen in training data.
method NSL layer uses neighborhood similarity to induce appearance invariance.
result NSL layer enhances network's ability to generalize to novel appearances.
Machine learning predicts graph layouts and metrics.
problem Selecting a good graph layout method is subjective and computationally expensive.
method Uses graph kernels to compute topological similarity and estimate layout aesthetics.
result Estimation is faster and more accurate than actual layout calculations.
Capsule networks detect and diagnose adversarial images better than CNNs.
problem Detecting and diagnosing adversarial images in neural networks.
method Class-conditional capsule reconstruction and reconstructive attack.
result Capsule networks outperform CNNs in detecting and diagnosing adversarial images.
Evolutionary methods improve understanding of LLMs and their relationships.
problem Improving understanding of LLMs and their relationships.
method Relating weights to genotypes and output text to phenotypes using evolutionary methods.
result Estimated evolutionary trees reliably recover the topology of the ground-truth training tree.
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.
A framework learns image embeddings robust to transformations for better recognition.
problem Learning robust image embeddings resistant to transformations like viewpoint, scale, and illumination.
method Discriminate-and-Rectify Encoders using orbit sets, deep parametrizations, and a novel orbit-based loss.
result Learned embeddings are robust to geometric transformations and improve one-shot classification.
Paper proposes redundancy-free features for zero-shot object recognition.
problem Redundant visual features degrade zero-shot object recognition.
method Project original features into a new, statistically independent space.
result RFF-GZSL achieves competitive results on benchmark datasets.
Unified tensor model disentangles object appearance factors.
problem Representing hierarchical intrinsic and extrinsic causal factors of object appearance.
method Compositional hierarchical tensor factorization.
result Interpretable object representation robust to occlusion and reduced training data requirements.
Deep learning identifies plant stresses accurately and quantitatively.
problem Manual inspection of plant stresses is subjective and time-consuming.
method Developed an explainable deep learning model using gradient-weighted class activation mapping.
result Model accurately identifies and quantifies diverse foliar stresses in soybeans and other species.
Automates hair color digitization using imaging and deep learning.
problem Challenges in capturing and rendering realistic hair colors.
method Combines imaging, path-tracing, and self-supervised machine learning.
result Accurately captures and renders hair color with synthetic images.
Reassesses calibration metrics in machine learning models.
problem Inconsistent reporting of calibration metrics in recent literature.
method Calibration-based decomposition of Bregman divergences, visualization of calibration and generalization error.
result New visualization technique for detecting trade-offs between calibration and generalization.
We review and illustrate how the volatility smile translates into a probability distribution, the market-implied probability distribution representing believes priced in. The effects of changes in the smile are examined. Special attention is given to the effects of slope, which might appear at first counter-intuitive. …
New models disentangle body pose and appearance for flexible human body analysis.
problem Interpretable latent space for human body analysis.
method Conditional-DGPose and Semi-DGPose models for disentangled pose and appearance.
result Models enable independent manipulation of pose and appearance.
Light pillars over rippled water appear parallel due to projection geometry.
problem Light pillars over rippled water appear parallel.
method Developing a geometric optics model
result The phenomenon is explained using the specular reflection rule, projection geometry, and physics of surface slopes.
Virtual reality brings non-Euclidean geometry to life.
problem Understanding non-Euclidean geometry is challenging.
method Interactive visualizations in virtual reality.
result Users can experience non-Euclidean geometry firsthand.
AI models struggle to generate diverse natural chemical structures.
problem Generating diverse chemical structures for drug discovery.
method Quantified internal chemical diversity; challenge with two models.
result AI models fail to reproduce natural chemical diversity.
A new method precisely recovers latent vectors from GAN-generated images.
problem No out-of-the-box method to reverse GAN mappings.
method Gradient-based stochastic clipping technique.
result Precise recovery of latent vectors 100% of the time for GAN-generated images.
Tile2Vec learns spatially meaningful representations without labels.
problem Lack of unsupervised methods for geospatial data.
method Unsupervised representation learning using the distributional hypothesis.
result Tile2Vec improves performance in spatial classification tasks.
DRCN learns shared representation for supervised and unsupervised tasks.
problem Unsupervised domain adaptation in visual object recognition.
method Deep Reconstruction-Classification Network (DRCN) that jointly learns shared encoding representation for supervised classification and unsupervised reconstruction.
result DRCN achieves significant improvement in cross-domain object recognition tasks (up to ~8% in accuracy).
Generative model creates realistic images with 3D understanding.
problem Lack of 3D understanding in existing image generation models.
method Disentangled 3D representation using shape, viewpoint, and texture.
result Generates more realistic images and enables 3D operations.
New method improves RL/IL agents' adaptability to unseen environments.
problem Current RL/IL techniques struggle with generalizing to unseen environments.
method Zero-shot compositional policy learning with multi-modal fusion and attention mechanism.
result Language grounding enhances generalization across varied environments.
BERT captures linguistic features in separate semantic and syntactic subspaces.
problem Understanding how transformer models like BERT represent linguistic features internally.
method Qualitative and quantitative investigations of BERT's internal representations.
result Evidence of a fine-grained geometric representation of word senses and syntactic representations.
regvis.net offers a visual survey of regulatory visualization.
problem Lack of a comprehensive resource for regulatory visualization.
method Collection and manual tagging of 80+ publications, creation of a searchable webpage.
result First publication set tailored for regulatory visualization.
Algorithm transfers visual concepts to answer out-of-vocabulary questions.
problem Leveraging off-the-shelf visual and linguistic data for out-of-vocabulary answers in visual question answering.
method Unsupervised task discovery for learning task conditional visual classifier, then transferring to visual question answering models.
result Algorithm generalizes to out-of-vocabulary answers successfully.
A new model tracks multiple people from cluttered scenes.
problem Tracking multiple people in cluttered scenes.
method Variational Bayesian framework with VEM algorithm.
result Competitive results compared to state-of-the-art models.
Adaptive convolution improves GANs performance on image generation.
problem GANs struggle with generating images of objects with diverse appearances.
method Proposes adaptive convolution to learn upsampling based on local context.
result Adaptive convolution models improve GANs performance on CIFAR-10 and STL-10 datasets.
Aesthetic-based clothing recommendation improves user satisfaction.
problem Lack of aesthetic features in existing clothing recommendation methods.
method Introduce aesthetic features extracted by a neural network and incorporate them into a personalized tensor factorization model.
result Our approach significantly outperforms state-of-the-art recommendation methods.
Net2Vis automates CNN visualization for publications.
problem Lack of consistent visual representations in deep learning papers.
method Proposes a visual grammar and automated system for generating publication-ready CNN visualizations.
result Reduces time and ambiguity in generating network visualizations.
This paper explains deep learning for pedestrians using CNNs.
problem Training deep neural networks with gradient descent.
method Backpropagation in Convolutional Neural Networks (CNNs).
result Conceptual clarity in vectorized backpropagation.
Proposes a spectral method to assess and combine multiple data visualizations.
problem Evaluating and combining the strengths of different data visualization algorithms.
method Spectral method for assessing and combining multiple visualizations.
result Proposes a visualization eigenscore to quantify relative performance and a consensus visualization.
Study reveals RL game's embedding space is stratified, not a manifold.
problem Understanding the structure of RL game embeddings.
method Adapted Robinson's volume growth transform for RL setting.
result Token embedding space is stratified, not a manifold.
AV-CPL uses continuous pseudo-labels for AVSR combining labeled and unlabeled data.
problem Improving AVSR performance with labeled and unlabeled data.
method Semi-supervised method using continuous pseudo-labels generated by the same AVSR model.
result Significant improvements in VSR performance on LRS3 dataset.
This report synthesizes research advances in integrating machine learning with visual analytics.
problem Underexplored combination of machine learning and data visualization in visual analytics.
method Synthesizing research advances to highlight the progress and challenges.
result Opportunities and challenges identified for future research in machine learning and visual analytics.
Visualizes futures markets using particle physics tools.
problem Understanding high-velocity data in futures markets.
method Uses ROOT, an open-source data-analysis tool, to reconstruct and visualize message-based data.
result Allows stakeholders to gain a better understanding of markets and monitor effectively.