FineHand learns hand shapes for better ASL recognition.
problem Difficult ASL recognition due to fast, articulate gestures.
method Combines manual and deep learning for hand shape embeddings, uses RNN for sequential gestures.
result Improved video gesture recognition accuracy on GMU-ASL51 benchmark.
AT-CNNs show improved shape recognition over texture recognition.
problem Understanding adversarial training's impact on CNNs' feature learning.
method Systematic qualitative and quantitative approaches to interpret AT-CNNs.
result Adversarial training reduces texture bias and improves shape 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.
ESPRESSO segments time-series data for better human activity recognition.
problem Segmenting high-dimensional time-series data for applications like HAR.
method ESPRESSO combines entropy and shape analysis for multi-dimensional time-series segmentation.
result ESPRESSO outperforms four state-of-the-art methods across seven datasets.
Paper proposes meshAdv to generate adversarial 3D meshes for visual recognition.
problem Vulnerability of deep neural networks to adversarial examples.
method Differentiable renderer to manipulate shape and texture of 3D meshes.
result 3D meshes effectively attack classifiers and object detectors.
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.
Shape analysis is ubiquitous in problems of pattern and object recognition and has developed considerably in the last decade. The use of shapes is natural in applications where one wants to compare curves independently of their parametrisation. One computationally efficient approach to shape analysis is based on the Sq…
Any subset of the plane can be approximated by a set of square pixels. This transition from a shape to its pixelation is rather brutal since it destroys geometric and topological information about the shape. Using a technique inspired by Morse Theory, we algorithmically produce a PL approximation of the original shape …
In its most general form, the recognition problem in Riemannian geometry asks for the identification of an unknown Riemannian manifold via measurements of metric invariants on the manifold. We introduce a new infinite sequence of invariants, the first term of which is the usual diameter, and illustrate the role of thes…
ES-VAE models skeletal pose trajectories by removing nuisance factors.
problem Handling camera orientation, subject scale, viewpoint, and execution speed in skeletal data.
method ES-VAE uses TSRVF representation on Kendall's shape manifold to isolate shape dynamics.
result ES-VAE outperforms standard VAEs and sequence modeling baselines in gait cycle prediction and action recognition.
Proposes a new layer for efficient 3D shape discrimination.
problem Irregular structure and redundancy in 3D point clouds hinder efficient inter-class discrimination.
method Integrates Blended Convolution and Synthesis layer that projects and synthesizes 3D point clouds, followed by 3D convolution in the unit ball.
result End-to-end architecture achieves compelling results on 3D shape recognition and retrieval.
The paper presents a recognition system for Pashto letters using KNN and ANN.
problem Challenging handwritten character recognition, especially for Pashto letters.
method Designed a database of 4488 images, used zoning feature extractor, KNN, and ANN classifiers.
result Achieved overall classification accuracy of 70.05% using KNN and 72% using ANN.
In some sense, the world is composed of shapes and words, of continuous things and discrete things. The recognition and study of continuous objects in the form of shapes occupies a significant part of the effort of unraveling many geometric questions. Shapes can be rep- resented with great generality by objects called …
Single neurons can perform as well as dense networks in binary and multi-class recognition tasks.
problem Designing efficient neural networks for recognition tasks.
method Investigated the use of single or multiple neurons in neural networks for binary and multi-class recognition tasks.
result Sparse networks can be as efficient as dense networks in both binary and multi-class tasks.
New method uses cluster shapes to improve track finding in particle collisions.
problem Combining timing and additional detector information for efficient track finding.
method Neural networks to analyze cluster shapes for track seeding.
result Cluster shapes reduce fake combinatorial backgrounds while maintaining high track efficiency.
Study develops sign recognition system for DHH users.
problem Accessibility of voice-controlled devices for Deaf and Hard-of-Hearing users.
method Multimodal data (RGB video and skeletal data) for sign language recognition using deep learning.
result Validation on GMUASL51 dataset of 12 users and 13107 samples across 51 signs.
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.
A recent Cell paper [Chang and Tsao, 2017] reports an interesting discovery. For the face stimuli generated by a pre-trained active appearance model (AAM), the responses of neurons in the areas of the primate brain that are responsible for face recognition exhibit strong linear relationship with the shape variables and…
Novel volumetric convolution for unit ball improves 3D object recognition.
problem Efficiently convolving functions in a unit ball for deep learning.
method Developed volumetric convolution using Zernike polynomials.
result Improved 3D object recognition through novel convolution.
The paper pinches eigenvalues and curvatures to prove shapes close to spheres.
problem Proving shapes close to spheres under curvature constraints.
method Pinching Heintze-Reilly's inequality via sectional curvature upper bounds, 1st eigenvalue, and mean curvature.
result Closed hypersurfaces are Hausdorff close to geodesic spheres and enclosed balls have constant curvature.
Generative classifiers show surprising human-like performance.
problem Comparing generative and discriminative models for object recognition.
method Built on recent advances in generative modeling to create classifiers and compared them to discriminative models.
result Generative classifiers outperform discriminative models in several key areas, including shape bias and out-of-distribution accuracy.
Proposes Moment Exchange to use moments in image recognition models, improving generalization.
problem Discarding moments in image recognition models reduces stability and training time.
method Moment Exchange: replaces moments of learned features with another image's moments and interpolates labels.
result Improves generalization of recognition models across multiple datasets.
Develops neural networks for reductive Lie groups, enhancing symmetry respect.
problem Symmetry respect in neural networks for reductive Lie groups.
method General equivariant neural network architecture for any reductive Lie Group G.
result Demonstrates generality and performance in top quark decay tagging and shape recognition.
A novel 3D shape registration method using spectral graph embedding and probabilistic matching.
problem Challenges in 3D shape analysis and registration, especially with large variability.
method Combining spectral graph matching with Laplacian embedding for large graphs, using commute-time embedding and PCA.
result A method to register shapes with different samplings and isometric deformations.
The classification of multivariate functional data is an important task in scientific research. Unlike point-wise data, functional data are usually classified by their shapes rather than by their scales. We define an outlyingness matrix by extending directional outlyingness, an effective measure of the shape variation …
Our goal is to provide a novel method of representing 2D shapes, where each shape will be assigned a unique fingerprint - a computable approximation to a conformal map of the given shape to a canonical shape in 2D or 3D space (see page 22 for a few examples). In this paper, we make the first significant step in this pr…
Method tracks finger movements to render shapes on display devices.
problem Designing touchless user interfaces for electronic devices.
method Leap Motion controller tracks finger movements, analyzes trajectories, and uses HMM for gesture recognition.
result Method achieves 92.87% accuracy in rendering shapes on display devices.
A novel clustering method uses torque balance to group objects.
problem Grouping similar objects in various scientific fields.
method Inspired by gravitational interactions, a parameter-free clustering algorithm based on mass and distance.
result The algorithm effectively clusters objects regardless of their shape, size, or density.
In this paper we study geometric aspects of the space of arcs parametrized by unit speed in the L2 metric. Physically this corresponds to the motion of a whip, and it also arises in studying shape recognition. The geodesic equation is the nonlinear, nonlocal wave equation ηtt=∂s(σηs), with $\lvert η_…
VCML learns concepts and metaconcepts from images and questions.
problem Learning concepts and metaconcepts from visual data.
method Bidirectional connection between visual concepts and metaconcepts.
result VCML can generalize from limited data and noisy inputs.
Sophie Germain's mean curvature deserves recognition as a surface shape measure.
problem Identifying the shape of a surface using curvature measurements.
method Characterizing surface shape through principal curvatures and their averages.
result Mean curvature should be named after Sophie Germain.
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.
Develops a fast non-invasive tool for diagnosing pediatric sleep apnea.
problem Diagnosing pediatric obstructive sleep apnea using an overnight sleep study is often impractical.
method Combines persistent homology, geometric shape analysis, and convolutional neural networks to classify facial images.
result Facial features associated with obstructive sleep apnea can be recognized for diagnosis.
Improved 3D scene understanding from partial point sets using multiview fusion.
problem Challenging task of 3D scene semantic understanding from partial point clouds.
method Multiview representation of 360° point clouds and fusion with original data.
result Overall increase of 31.9% and 4.3% in segmentation accuracy for partial and complete scenes.
The paper classifies vehicle shapes and colors using deep neural networks.
problem Vehicle reidentification and classification challenges.
method Used deeper neural networks for classification accuracy.
result Good classification accuracy on make/model and color.
Proposes GIC for graph convolution, improving graph classification.
problem Graphs lack local convolution kernels like images.
method GIC framework using edge-induced and vertex-induced Gaussian mixtures.
result GIC achieves state-of-the-art results on graph classification.
Deep learning automates bacterial image classification.
problem Manual bacterial classification is time-consuming and error-prone.
method ResNet-50 pre-trained CNN architecture with transfer learning.
result Average classification accuracy of 99.2%.
We present an extension of sparse PCA, or sparse dictionary learning, where the sparsity patterns of all dictionary elements are structured and constrained to belong to a prespecified set of shapes. This \emph{structured sparse PCA} is based on a structured regularization recently introduced by [1]. While classical spa…
Topological data analysis (TDA) has emerged as one of the most promising techniques to reconstruct the unknown shapes of high-dimensional spaces from observed data samples. TDA, thus, yields key shape descriptors in the form of persistent topological features that can be used for any supervised or unsupervised learning…
Proposes neural similarity for CNNs to enhance flexibility and performance.
problem Limited flexibility of inner product-based convolution in CNNs.
method Introduces neural similarity as a learnable parametric similarity measure, and proposes NSL for adaptive learning from data.
result Dynamic neural similarity improves flexibility and performance in visual recognition and few-shot learning.
We describe an algorithm that associates to each positive real number r and each finite collection Cr of planar pixels of size r a planar piecewise linear set Sr with the following additional property: if Cr is the collection of pixels of size r that touch a given compact semialgebraic set S, then the …
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.
Facebook's ResNeXt WSL models show exceptional robustness against image corruptions and adversarial attacks.
problem Image recognition model robustness against corruptions and adversarial attacks.
method Training with 1B images from Instagram and fine-tuning on ImageNet.
result ResNeXt WSL models achieve state-of-the-art results on ImageNet-C, ImageNet-P, and ImageNet-A.
In this article, we will formulate a mathematical framework that allows us to treat character animations as points on infinite dimensional Hilbert manifolds. Constructing geodesic paths between animations on those manifolds allows us to derive a distance function to measure similarities of different motions. This appro…
Topological data analysis offers a rich source of valuable information to study vision problems. Yet, so far we lack a theoretically sound connection to popular kernel-based learning techniques, such as kernel SVMs or kernel PCA. In this work, we establish such a connection by designing a multi-scale kernel for persist…
This paper surveys measures of classification complexity.
problem Estimating the difficulty of separating data points into classes.
method Analysis of descriptors from training datasets.
result Characterization of classification problem complexity.
Algorithm finds essential surfaces in 3D shapes.
problem Detecting closed essential surfaces in 3D shapes.
method Triangulation, ideal triangulation, enumeration, optimisation, normal surface theory.
result Algorithm tests for essential surfaces in 3D shapes.
Study uses LSTM models to detect Wyckoff patterns in currency trading.
problem Understanding market dynamics and identifying trading opportunities.
method Dissecting Wyckoff Phases, using CNNs for spatial data and LSTM for temporal data.
result Deep learning models enhance pattern recognition in financial markets.