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.

169,181 papers · 148 categories

Trend · papers per month

1122 · Jun 201919922001200920182026
28 results for shape-based

CNNs trained on ImageNet favor textures over shapes, but can learn shape-based recognition.

problem CNNs trained on ImageNet favor textures over shapes, leading to biased recognition.
method Evaluating CNNs and human observers on images with a texture-shape cue conflict.
result CNNs trained on ImageNet favor textures over shapes, but can learn shape-based recognition.

This paper improves facial expression recognition using CNNs and coherence constraints.

problem Facial expression recognition from static images and video sequences is challenging.
method Investigates the use of Convolutional Neural Networks (CNNs) with coherence constraints in a semi-supervised setting.
result Coherence constraints improve facial expression recognition quality, especially in the presence of occlusions.

Consumer Demand Response (DR) is an important research and industry problem, which seeks to categorize, predict and modify consumer's energy consumption. Unfortunately, traditional clustering methods have resulted in many hundreds of clusters, with a given consumer often associated with several clusters, making it diff…

2017-02-05abs ↗pdf ↗

New model combines shape and feature-based measures for better time series classification.

problem Limited approaches in time series classification lead to poor results for some classes.
method Proposes a new model that automatically decides between shape and feature-based measures.
result Improves classification accuracy statistically significantly on real-world datasets.

Shapelet transform improves time series classification for earthquake, wind, and wave events.

problem Autonomous detection of specific events from large time series datasets in civil engineering.
method Shapelet transform for local similarity in time series subsequences, combined with machine learning.
result Shapelet transform yields a new feature representation for time series signals in civil engineering.

This paper introduces a new shape-based image reconstruction technique applicable to a large class of imaging problems formulated in a variational sense. Given a collection of shape priors (a shape dictionary), we define our problem as choosing the right elements and geometrically composing them through basic set opera…

2013-02-28abs ↗pdf ↗

This paper proposes a new Nystrom-based clustering algorithm for large-scale data.

problem Spectral clustering's high computational complexity for large-scale data.
method Centroid Minimum Sum of Squared Similarities (CMS3) sampling procedure with eigen spectrum shape heuristic.
result Competitive low-rank approximations in test datasets compared to state-of-the-art methods.

The study optimizes cell membranes' shapes based on curvature and proves existence of minimizers.

problem Optimizing cell membranes' shapes with respect to curvature.
method Modeling cell membranes as optimal shapes with L2L^2-deficit of mean curvature to spontaneous curvature, and proving lower semi-continuity and existence of minimizers.
result Smoothly embedded minimizers and diameter bounds are obtained.

Study shows increased precipitation variability in Paris area over years.

problem Evaluating the evolution of precipitation variability over time.
method Shape-based Dynamic Time Warping (IMS-DTW) for clustering rainfall time series.
result Precipitation variability increased in Paris area over years.

Enhanced image recognition models learn from human-like memory and shape biases.

problem Improving robustness of image recognition models against various perturbations.
method Integrating human-like episodic memory and shape bias features into image recognition models.
result Combining human-like features improves robustness against both adversarial and natural perturbations.

This research optimizes fluid-dynamic designs using deep learning and active learning.

problem Expensive and limited empirical design verification for fluid dynamics.
method Applied a deep learning architecture to predict and optimize fluid dynamics performance.
result Reduced the number of required simulation data points from ~8000 to 625.

Combines spatial context priors with data term for better dendritic spine segmentation.

problem Poor segmentation results due to overlapping pixel intensity distributions.
method Combines nonparametric context priors with learned-intensity data term and nonparametric shape priors.
result Significant improvements in dendritic spine segmentation.

Program synthesis struggles with complex spatial relationships in image classification.

problem Challenges in solving Synthetic Visual Reasoning Test problems.
method Quantitative reanalysis of human and machine performance, improved program synthesis classifier, categorization of SVRT problems.
result Program synthesis is constrained by spatial relationships in images, not just shape specification.

Study analyzes neural network models to understand generalization performance.

problem Understanding good generalization in neural networks.
method Analyzed a corpus of models from a public contest, breaking ALPHAHAT into scale and shape metrics.
result Identified a Simpson's paradox in metric performance across different model depths and regularization hyperparameters.

Develops a deep clustering framework for large-scale road traffic prediction.

problem Challenges in modeling diverse traffic patterns and handling high-dimensional time series with low latency.
method Combines deep clustering with CNNs and RNNs to predict road traffic at large-scale networks.
result The DeepCluster framework effectively clusters road segments and improves prediction performance.