Solves recognition problem of frontal singularities.
problem Recognition of frontal singularities.
method Specified geometric frontal singularities, provided explicit normal forms, combined results from K. Saji and applied to tangent surfaces of null curves.
result Classification of singularities in tangent surfaces of null curves.
Paper tackles zero-shot activity recognition using video features and text embeddings.
problem Zero-shot activity recognition with videos.
method Auto-encoder model for multimodal joint embedding, 3D convolutional action recognition for visual features, GloVe word embeddings for textual features.
result Improved zero-shot recognition results with top-n accuracy and mean Nearest Neighbor Overlap.
Study pinches volume of CAT(1) spaces, proving sphere theorem and manifold recognition criterion.
problem Volume pinching problems in CAT(1) spaces.
method Characterization of compact geodesically complete CAT(1) spaces, sphere theorem proof, manifold recognition criterion formulation.
result Sphere theorem for compact CAT(1) homology manifolds of small volume, manifold recognition criterion under upper curvature bound.
Shows NP-completeness of non-hyperbolic 3-manifolds.
problem Determining if a cusped 3-manifold is non-hyperbolic.
method NP-completeness proof using satellite knot recognition and irreducible toroidal recognition.
result Shows NP-completeness of non-hyperbolic 3-manifolds.
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…
Sparsity-based representations have recently led to notable results in various visual recognition tasks. In a separate line of research, Riemannian manifolds have been shown useful for dealing with features and models that do not lie in Euclidean spaces. With the aim of building a bridge between the two realms, we addr…
Regina is a software package for studying 3-manifold triangulations and normal surfaces. It includes a graphical user interface and Python bindings, and also supports angle structures, census enumeration, combinatorial recognition of triangulations, and high-level functions such as 3-sphere recognition, unknot recognit…
Designs neural networks on matrix manifolds for improved performance in tasks like human action recognition.
problem Designing neural networks for tasks on non-Euclidean manifolds.
method Develops fully-connected and convolutional layers for SPD manifolds, and MLR on SPSD manifolds.
result Demonstrates improved performance in human action recognition and node classification tasks.
Deep neural networks (DNNs) have been successfully applied to a wide variety of acoustic modeling tasks in recent years. These include the applications of DNNs either in a discriminative feature extraction or in a hybrid acoustic modeling scenario. Despite the rapid progress in this area, a number of challenges remain …
We prove that the homeomorphism problem for 2-manifolds can be decided in logspace. The proof relies on Reingold's logspace solution to the undirected s,t-connectivity problem in graphs.
Recognition of Seifert fibered spaces with boundary is computationally tractable.
problem Recognizing Seifert fibered spaces with boundary.
method Proving the existence of fundamental horizontal surfaces and normal vertical annuli with bounded total weight.
result The decision problem is in NP and the construction problem is in FNP.
We describe theoretical backgrounds for a computer program that recognizes all closed orientable 3-manifolds up to complexity 8. The program can treat also not necessarily closed 3-manifolds of bigger complexities, but here some unrecognizable (by the program) 3-manifolds may occur.
Perceptual manifolds arise when a neural population responds to an ensemble of sensory signals associated with different physical features (e.g., orientation, pose, scale, location, and intensity) of the same perceptual object. Object recognition and discrimination requires classifying the manifolds in a manner that is…
In this paper, we consider the problem of fast and efficient indexing techniques for sequences evolving in non-Euclidean spaces. This problem has several applications in the areas of human activity analysis, where there is a need to perform fast search, and recognition in very high dimensional spaces. The problem is ma…
We introduce a kernel method for manifold alignment (KEMA) and domain adaptation that can match an arbitrary number of data sources without needing corresponding pairs, just few labeled examples in all domains. KEMA has interesting properties: 1) it generalizes other manifold alignment methods, 2) it can align manifold…
It is a major unsolved problem as to whether unknot recognition - that is, testing whether a given closed loop in R^3 can be untangled to form a plain circle - has a polynomial time algorithm. In practice, trivial knots (which can be untangled) are typically easy to identify using fast simplification techniques, wherea…
We prove the existence of a new algorithm for 3-sphere recognition based on Groebner basis methods applied to the variety of $\text{\em SL}(2,\C)$-representation of the fundamental group. An essential input is a recent result of the second author, stating that any integer homology 3-sphere different from the 3-sphere a…
Improved speech recognition using EEG and video.
problem Enhancing continuous speech recognition systems.
method Implemented a CTC-based ASR model using EEG features.
result EEG features improve continuous visual speech recognition.
This is a survey paper on algorithms for solving problems in 3-dimensional topology. In particular, it discusses Haken's approach to the recognition of the unknot, and recent variations.
CSI-Net learns WiFi signals for body characterization and pose recognition.
problem Unified learning of body characteristics and pose recognition.
method Unified Deep Neural Network (DNN) for WiFi signal representation and multi-task learning.
result CSI-Net solves biometrics estimation and person recognition.
Study shows emotion affects speaker recognition and vice versa.
problem Dependencies between emotion and speaker recognition.
method Transfer learning and fine-tuning for emotion classification.
result Fine-tuning improves emotion recognition performance by 30.40% on IEMOCAP, 7.99% on MSP-Podcast, and 8.61% on Crema-D.
With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data. However, to scale the recognition to a large number of classes with few or now training samp…
End-to-end speech recognition using EEG without speech input.
problem Speech recognition without direct speech input.
method Implemented attention model and CTC-based ASR systems for EEG signals; fused EEG with noisy speech features.
result Demonstrated end-to-end speech recognition using EEG signals.
Positive Quaternion Kaehler Manifolds are Riemannian manifolds with holonomy contained in Sp(n)Sp(1) and with positive scalar curvature. Conjecturally, they are symmetric spaces. We prove this conjecture in dimension 20 under additional assumptions and we provide recognition theorems for quaternionic projective spaces …
GDMaps reduces high-dimensional data to lower dimensions for better classification.
problem High-dimensional data classification and representation.
method Grassmannian Diffusion Maps technique for nonlinear dimensionality reduction.
result GDMaps effectively identifies intrinsic subspace structures in high-dimensional data.
New proof for sphere recognition algorithm.
problem Sphere recognition algorithm proof.
method New proof of a lemma in Abigail Thompson's algorithm.
result New proof of a lemma in Abigail Thompson's proof of the Recognition Algorithm for 3-spheres.
Continuous speech recognition from brain activity without vocalization.
problem Recognizing silent speech from EEG signals.
method Implemented a CTC ASR model using EEG signals.
result Demonstrated feasibility of EEG for continuous silent speech recognition.
VoxCeleb 2019 challenge assesses speaker recognition in uncontrolled settings.
problem Evaluate speaker recognition technology in unconstrained data.
method Public dataset, challenge, and workshop at Interspeech 2019.
result Baseline results and discussions provided.
Deep learning is the mainstream technique for many machine learning tasks, including image recognition, machine translation, speech recognition, and so on. It has outperformed conventional methods in various fields and achieved great successes. Unfortunately, the understanding on how it works remains unclear. It has th…
Paper proposes Roweisposes for 3D action recognition using generalized eigenvalue problem.
problem Need for basic methods in 3D action recognition.
method Roweisposes uses Roweis discriminant analysis for generalized subspace learning.
result Roweisposes is effective for 3D action recognition.
Paper introduces a new distance measure for Gaussian Mixture Models.
problem Developing a new distance measure for Gaussian Mixture Models.
method Embedding K-component Gaussian Mixture Models into the manifold of symmetric positive definite matrices and calculating a lower bound for the Fisher-Rao metric.
result Demonstrated effectiveness through experiments on standard datasets.
Survey of open set recognition techniques and their limitations.
problem Recognition tasks with unknown classes during testing.
method Comprehensive review of techniques, datasets, and evaluation criteria.
result Highlighting the limitations and future directions in open set recognition.
This survey article describes the algorithmic approaches successfully used over the time to construct hyperbolic structures on 3-dimensional topological "objects" of various types, and to classify several classes of such objects using such structures.
A new deep neural network improves short-speech recognition.
problem Improving speaker recognition for short-duration speech segments.
method Proposes UtterIdNet, a novel deep neural network architecture.
result Consistent and stable performance for short segments, especially sub-second durations.
Paper explores EEG-based speech recognition using transformers, showing faster training and better performance for smaller vocabularies.
problem Continuous speech recognition using EEG features.
method Transformer-based ASR model compared to RNN-based models.
result Transformer models perform better for smaller vocabularies but RNN models outperform them for larger vocabularies.
Proposes a neural network for recognizing 3D skeleton-based interactions.
problem Recognizing two-person interactions from 3D skeleton sequences.
method Uses Gaussian distributions and Riemannian geometry of SPD matrices and matrix groups.
result Achieves competitive results on three benchmarks for 3D human activity understanding.
EmbraceNet fusion model for multi-sensor activity recognition.
problem Human activity recognition using multiple sensors is challenging.
method Independent processing of each sensor, feature fusion with EmbraceNet, post-processing, and additional processes.
result Improved performance in SHL recognition challenge.
Paper improves EEG-based speech recognition using CTC and beam search.
problem Improving continuous speech recognition from EEG signals.
method Implemented CTC-based ASR system, initialized weights, used external language model, studied articulatory feature prediction.
result Enhanced performance of EEG-based speech recognition systems.
We compute persistent homology using an intrinsic metric derived from density.
problem Estimating topological features from high-dimensional data.
method Density-based metric learning for persistent homology.
result Persistent homology converges to intrinsic manifold metric.
TransFall uses transfer learning to improve activity recognition from mobile sensors.
problem Performance degradation due to platform and user movement differences.
method Two-tier data transformation, label estimation, and model generation layers.
result TransFall enhances activity recognition accuracy for new scenarios.
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.
Neural network framework for language recognition considers sequence information and improves accuracy.
problem Challenging task of automatic language identification in noisy conditions.
method Proposes a neural network framework with bidirectional LSTM and attention modeling for relevance weighting.
result Significant improvements over conventional methods in noisy conditions and multi-speaker speech.
New dataset for UAV gesture recognition in outdoor settings.
problem Lack of public outdoor UAV gesture recognition datasets.
method Recorded 13 gestures in an outdoor setting, created 119 HD video clips, annotated with body joints and gesture classes.
result Baseline gesture recognition performance of 91.9% using P-CNN.
Study uses HMM for real-time activity recognition from sensor data.
problem Real-time activity recognition from streaming sensor data.
method Online hierarchical hidden Markov model.
result Improved activity recognition accuracy compared to existing methods.
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.
Paper shows EEG can improve ASR in noisy speech.
problem ASR performance drops in noisy conditions.
method Used EEG to train ASR models and improve performance.
result ASR accuracy improved with EEG features and distillation.
Fawkes protects images from unauthorized facial recognition models.
problem Unauthorized training of facial recognition models poses privacy risks.
method Fawkes adds imperceptible pixel-level changes (cloaks) to images before release.
result Fawkes can protect images from misidentification by 95% and 80% even when clean images are leaked.
Paper shows continuous speech recognition with EEG features, no speech input.
problem Continuous speech recognition with limited vocabulary and noisy/no speech input.
method Connectionist temporal classification (CTC) model, EEG features, new deep learning architecture.
result Continuous speech recognition achieved on limited vocabulary with noisy/no speech input.