DeepPhase uses deep learning to recognize surgical phases in cataract surgery videos.
problem Automating surgical workflow analysis for better standardization and post-surgical assessment.
method Deep learning for instrument detection and phase classification in cataract surgery videos.
result DeepPhase models achieve 99% accuracy in instrument detection and 78% in phase recognition.
New approach uses synthetic labels to train models on scarce annotated data for surgical phase recognition.
problem Learning surgical phase recognition from limited annotated data.
method Teacher/Student approach with a CNN-biLSTM-CRF teacher generating synthetic labels for a CNN-LSTM student.
result Improved surgical phase recognition performance with fewer annotated videos.
Moon phases added to stock market analysis for better pattern recognition.
problem Finding meaningful patterns in stock market data using irregular time sampling.
method Incorporating Moon phases into the Gregorian calendar time sampling methods for stock market analysis.
result Moon phases provide unique, irregular sampling features for stock market pattern recognition.
Enhanced speech emotion recognition using nonlinear recurrence dynamics.
problem Improving speech emotion recognition accuracy.
method Phase space reconstruction, Recurrence Plot, Recurrence Quantification Analysis, statistical functionals, feature fusion, Bidirectional Recurrent Neural Network.
result State-of-the-art performance on IEMOCAP with up to 10.7% improvement in accuracy.
Deep learning and prior maps improve traffic light recognition for autonomous cars.
problem Recognizing traffic lights for autonomous cars in urban environments.
method Combining deep learning-based detection with prior maps for traffic light identification and state recognition.
result The proposed system correctly identified relevant traffic lights along predefined routes.
Paper presents a novel online HAR method using Hierarchical Hidden Markov Models.
problem Challenges in robust online activity recognition in smart environments.
method Two-phase approach: 1) Segmentation and activity reporting using Hierarchical Hidden Markov Models, 2) Correction of labels based on statistical features.
result Proposes a method that can detect and correct interrupted activities, outperforming state-of-the-art methods.
This study analyzes how one-layer transformers learn regular language recognition tasks.
problem Understanding how one-layer transformers solve regular language recognition tasks like even pairs and parity check.
method Theoretical analysis of training dynamics and gradient descent for a one-layer transformer.
result A one-layer transformer can solve even pairs directly but needs CoT for parity check. Training phases show rapid growth in attention layer followed by logarithmic growth in linear layer.
PHASE dataset simulates complex social interactions in physical environments.
problem Lack of datasets for evaluating physically grounded perception of complex social interactions.
method Created PHASE dataset of 2D animations with procedural generation and physics engine.
result SIMPLE model outperforms neural networks in recognizing complex social interactions.
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.
End-to-end framework learns new classes dynamically.
problem Challenges in recognizing unseen classes in real-world settings.
method Dynamic cascade of classifiers that incrementally learn features.
result Outperforms existing methods on real-world datasets.
Improved handwriting recognition for historical documents with minimal labeled data.
problem Challenges in recognizing historical documents, especially lack of text-line annotations.
method Trained a deep CRNN system on 10% labeled data, augmented with crafted multiscale data, and applied model-based normalization.
result Achieved second best result in ICDAR2017 competition on publicly available READ dataset.
GenInSAR uses CNNs to filter InSAR phase and estimate coherence without supervision.
problem Improving accuracy in InSAR phase filtering and coherence estimation.
method Unsupervised CNN-based generative model for joint phase filtering and coherence estimation.
result GenInSAR outperforms five related methods in residue reduction and coherence estimation.
Global stability bounds for matrix frames in phase retrieval problems.
problem Phase retrieval for matrix frames in various applications.
method Computable global stability bounds for the quasi-linear analysis map β, using Whitney stratification of positive semidefinite matrices of low rank.
result Novel conditions for a frame to be generalized phase retrievable.
End-to-end voice conversion without vocoder.
problem Speech conversion without vocoder.
method Transformer network for raw spectrum conversion.
result Transformer model converts real voices efficiently.
Canonical correlation analysis (CCA) has been one of the most popular methods for frequency recognition in steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs). Despite its efficiency, a potential problem is that using pre-constructed sine-cosine waves as the required reference signals in…
CGDL improves open set recognition by learning conditional Gaussian distributions.
problem Handling unknown samples in real-world recognition tasks.
method Conditional Gaussian Distribution Learning (CGDL) with probabilistic ladder architecture.
result CGDL significantly outperforms baseline methods on standard image datasets.
Improved action recognition in live videos with hybrid FR-DL method.
problem High computational costs and lack of temporal information in conventional action recognition.
method Automated selection of representative frames, feature extraction, background subtraction, HOG, deep neural network, LSTM, Softmax-KNN classifier.
result Significant improvement in accuracy and speed compared to state-of-the-art methods.
Real-time personalization for HAR models learns from new users without prior data.
problem Poor performance of HAR models on new users without labeled data.
method Incremental online domain adaptation using batch normalization.
result Personalized HAR models adapt to new users in real-time.
Proposes a new framework for open set recognition using conditional probabilistic generative models.
problem Unknown samples can mislead traditional deep neural networks during testing.
method Conditional Probabilistic Generative Models (CPGM) that combine generative models with discriminative information.
result Significantly outperforms baselines on multiple benchmark datasets.
The resemblance between the methods used in quantum-many body physics and in machine learning has drawn considerable attention. In particular, tensor networks (TNs) and deep learning architectures bear striking similarities to the extent that TNs can be used for machine learning. Previous results used one-dimensional T…
Study finds PLI functional connectivity feature superior for depression recognition.
problem Effective detection of depression remains a public health challenge.
method Resting state EEG data collected from MDD and normal controls; various feature types and selection methods evaluated.
result PLI functional connectivity feature superior to linear and nonlinear features; highest classification accuracy 82.31%.
We present a feature engineering pipeline for the construction of musical signal characteristics, to be used for the design of a supervised model for musical genre identification. The key idea is to extend the traditional two-step process of extraction and classification with additive stand-alone phases which are no lo…
Machine learning predicts failure in brittle materials with high accuracy.
problem Predicting failure in brittle materials under repetitive loads.
method Phase-field model combined with supervised machine learning.
result Framework predicts failure with acceptable accuracy even in noisy data.
We present here a new model and algorithm which performs an efficient Natural gradient descent for Multilayer Perceptrons. Natural gradient descent was originally proposed from a point of view of information geometry, and it performs the steepest descent updates on manifolds in a Riemannian space. In particular, we ext…
Tackling pattern recognition problems in areas such as computer vision, bioinformatics, speech or text recognition is often done best by taking into account task-specific statistical relations between output variables. In structured prediction, this internal structure is used to predict multiple outputs simultaneously,…
CTM uses conjunctive clauses for image recognition, achieving high accuracy.
problem High computational complexity and lack of interpretability in CNNs.
method Introduces Convolutional Tsetlin Machine (CTM) using conjunctive clauses in propositional logic.
result CTM achieves competitive accuracy on various benchmarks, including MNIST and Fashion-MNIST.
Speech enhancement improved by adapting to unknown speakers without auxiliary signals.
problem Improving speech enhancement accuracy for unknown speakers.
method Adopting multi-task learning for speech enhancement and speaker identification, using multi-head self-attention.
result Achieved state-of-the-art performance and improved subjective quality.
Optical co-processor speeds up neural network training.
problem Expensive training costs for large neural networks.
method Direct feedback alignment, optical error projection.
result Optical co-processor trains neural networks for handwritten digit recognition.
Gen1S learns novel classes with 1-shot data using residual space and generative models.
problem Learning new classes with limited data in a growing dataset.
method Mapping embeddings to a residual space, using generative models to learn multi-modal distribution, and applying it as a structural prior.
result Consistent improvement over state-of-the-art methods in recognizing novel classes.
This paper studies concept drift detectors for financial time series.
problem Improving accuracy on financial time series with concept drifts.
method Three simple concept drift detectors tailored to financial time series.
result Two of the detectors are as effective as state-of-the-art detectors.
This paper introduces a new method for semi-supervised learning on high dimensional nonlinear manifolds, which includes a phase of unsupervised basis learning and a phase of supervised function learning. The learned bases provide a set of anchor points to form a local coordinate system, such that each data point x on…
META-DES.H selects competent classifiers using meta-learning and dynamic weighting.
problem Selecting competent classifiers in dynamic ensemble selection.
method META-DES framework using meta-learning and dynamic weighting.
result Improvements in recognition accuracy on 30 datasets.
Minimal DAMs can recognize patterns in high noise, even with minimal data.
problem Pattern recognition in high noise conditions with limited data.
method Interpolating between DAMs and spin glasses, using minimal dense associative networks and extremizing quenched free-energy.
result Minimal DAMs can correctly recognize patterns even when the signal is very weak and noise is high.
We propose an efficient protocol for decentralized training of deep neural networks from distributed data sources. The proposed protocol allows to handle different phases of model training equally well and to quickly adapt to concept drifts. This leads to a reduction of communication by an order of magnitude compared t…
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.
Theory for soft-margin classifiers on object manifolds.
problem Classifying object manifolds with variability.
method Mean-field theory of soft-margin classifiers applied to object manifolds.
result Prediction of classification errors and their dependence on regularization.
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.
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.
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.
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.
Solves Dirichlet problem for Lagrangian phase equation with critical and supercritical phase.
problem Solving Dirichlet problem for Lagrangian phase equation with critical and supercritical phase.
method Uses interior C2 estimate. result Result is sharp, showing existence of singular solutions in subcritical phase.
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.
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.