XceptionTime improves hand gesture recognition accuracy using novel deep learning.
problem Improving hand gesture recognition from sparse sEMG signals.
method Depthwise separable convolutions, adaptive pooling, non-linear normalization.
result Significantly improved accuracy (5.71% improvement) in hand gesture recognition.
A modified VDCNN model reduces size and latency for mobile platforms.
problem Memory and processing constraints on mobile platforms.
method Temporal Depthwise Separable Convolutions and Global Average Pooling.
result The squeezed model (SVDCNN) is 10x-20x smaller with minimal accuracy loss.
A new method speeds up spectral normalization for neural nets.
problem Efficiently controlling the spectral norm of convolutional layers.
method Depthwise separable convolutions with spectral normalization.
result Significant reduction in computational and memory costs.
Convolution Neural Network (CNN) has gained tremendous success in computer vision tasks with its outstanding ability to capture the local latent features. Recently, there has been an increasing interest in extending convolution operations to the non-Euclidean geometry. Although various types of convolution operations h…
In recent times, the use of separable convolutions in deep convolutional neural network architectures has been explored. Several researchers, most notably (Chollet, 2016) and (Ghosh, 2017) have used separable convolutions in their deep architectures and have demonstrated state of the art or close to state of the art pe…
We present a logarithmic-scale efficient convolutional neural network architecture for edge devices, named WaveletNet. Our model is based on the well-known depthwise convolution, and on two new layers, which we introduce in this work: a wavelet convolution and a depthwise fast wavelet transform. By breaking the symmetr…
Paper proposes DeCEF layers to reduce CNN complexity.
problem Reduces complexity of CNNs without pre-trained models.
method Develops Depthwise Convolutional Eigen-Filter (DeCEF) layers.
result Achieves similar or higher accuracy with 2/3 parameters and 2/3 FLOPs.
New tensor network decompositions improve CNN performance.
problem Limited exploration of tensor network decompositions for CNNs.
method Characterized a new class of CNN modules and experimentally compared various decompositions.
result Some nonlinear decompositions outperform existing ones in terms of accuracy and efficiency.
Improves audio source separation using dilated convolutions and dense connections.
problem Optimizing feature extraction in audio source separation models.
method Adaptive dilated convolutions and dense connections in U-Net architecture.
result Improved performance on MUSDB test dataset.
The paper bridges spectral and spatial graph convolutions, improving model capacity and transferability.
problem Improving graph neural networks by bridging spectral and spatial design.
method Theoretical demonstration and general framework for spectral analysis, new spectral convolutions, and depthwise separable convolutions.
result General framework allows spectral analysis of ConvGNNs, showing their performance and limits, and proposing new spectral convolutions.
We present QuickNet, a fast and accurate network architecture that is both faster and significantly more accurate than other fast deep architectures like SqueezeNet. Furthermore, it uses less parameters than previous networks, making it more memory efficient. We do this by making two major modifications to the referenc…
Residual networks with depthwise hyperparameter scaling transfer optimal hyperparameters across width and depth.
problem The challenge of hyperparameter tuning in deep learning, especially for large models.
method Combining μ μ μ P parameterization with residual networks having a residual branch scale of 1 / e x t d e p t h 1/\sqrt{ ext{depth}} 1/ e x t d e pt h . result Optimal hyperparameters transfer across width and depth in residual networks trained with this parameterization.
A simple CNN architecture outperforms complex ones in P300 detection.
problem Efficiently detecting P300 component from EEG signals.
method Used a simple CNN architecture with a single depthwise separable 1D convolutional layer followed by a fully connected Sigmoid neuron.
result A single depthwise separable 1D convolutional layer with four filters achieved competitive performance.
Real-time drowsiness detection on mobile phones reduces road trauma.
problem Driver drowsiness increases crash risk and road trauma.
method Depthwise separable 3D convolutions combined with early fusion of spatial and temporal information.
result Real-time drowsiness detection on mobile phones reduces road trauma.
New bounds for CNNs show better generalization than previous models.
problem Improving understanding of CNNs' generalization ability.
method Proposed tighter generalization bounds for CNNs by exploiting the sparse and permutation structure of weight matrices and spectral norms of convolution operations.
result Theoretical and experimental results show tighter bounds for CNNs than existing bounds.
Unified tensor factorization for efficient 3D convolutions in spatio-temporal emotion analysis.
problem Training deep 3D convolutions is computationally expensive and requires large datasets.
method Tensor factorization framework for separable higher-order convolutions.
result Improved spatio-temporal emotion estimation on large datasets.
TaLK Convolutions improve sequence modeling efficiency.
problem Efficiently modeling sequences with limited time complexity.
method Adaptive convolution operation that learns kernel size.
result Time complexity reduced to O ( n ) O(n) O ( n ) , making sequence encoding linear. Two-stream model recognizes affect from audio and video.
problem Human affect recognition in real-world settings.
method Two-stream aural-visual analysis model with separate audio and visual processing.
result Model achieves promising results on Aff-Wild2 database.
Multistep traffic forecasting on road networks is a crucial task in successful intelligent transportation system applications. To capture the complex non-stationary temporal dynamics and spatial dependency in multistep traffic-condition prediction, we propose a novel deep learning framework named attention graph convol…
MASnet enhances speech on mobile devices with low latency.
problem Efficiently enhancing speech on mobile devices with low latency.
method MASnet processes linear-scale spectrograms, using ratio masks to enhance noisy frames, and operates in low-latency incremental inference mode.
result MASnet achieves efficient speech enhancement with low latency, reducing FMA/s operations.
Brain computer interfaces (BCI) enable direct communication with a computer, using neural activity as the control signal. This neural signal is generally chosen from a variety of well-studied electroencephalogram (EEG) signals. For a given BCI paradigm, feature extractors and classifiers are tailored to the distinct ch…
We propose a random convolutional neural network to generate a feature space in which we study image classification and retrieval performance. Put briefly we apply random convolutional blocks followed by global average pooling to generate a new feature, and we repeat this k times to produce a k-dimensional feature spac…
TMTF improves time series visualization by separating dynamic regimes.
problem Misleading global transition matrix in time series analysis.
method Temporal chunking, local transition matrices, and image assembly.
result Temporal segmentation reveals distinct transition dynamics.
Researchers enhance EfficientNet models for practical efficiency on Graphcore IPU.
problem Improving practical efficiency of EfficientNet models on high-performance accelerators.
method Group convolutions, proxy-normalized activations, and reduced training resolution.
result Improves practical efficiency for both training and inference on Graphcore IPU.
WaveCRN improves E2E speech enhancement with efficient CNN and SRU.
problem Efficiently modeling speech locality and sequential properties for E2E speech enhancement.
method WaveCRN uses a CNN for speech locality and SRU for temporal sequential modeling, with RFM for noise suppression.
result WaveCRN outperforms state-of-the-art approaches with reduced complexity and inference time.
Convolutional LSTM improves missing data imputation in spatio-temporal data.
problem Missing data in spatio-temporal data affects analysis performance.
method Proposes a convolutional bidirectional-LSTM for spatio-temporal missing data imputation.
result The proposed model outperforms state-of-the-art methods for missing data imputation.
Combines CNN and LSTM for spatio-temporal graph networks.
problem Improving spatio-temporal feature extraction.
method Proposes a new architecture combining CNN and LSTM temporal blocks.
result Empirical comparison shows our model outperforms existing models.
GACAN combines multi-granularity time series for traffic forecasting.
problem High dynamics and complex spatial-temporal dependency of road networks in traffic forecasting.
method Graph Attention-Convolution-Attention Networks (GACAN) with Att-Conv-Att (ACA) block.
result GACAN outperforms state-of-the-art baselines in traffic forecasting.
New WildMix dataset and Spectro-Temporal Transformer model for better monoaural audio source separation.
problem Challenging monoaural audio source separation.
method Introducing WildMix dataset and Spectro-Temporal Transformer model (STT) with Spectro-Temporal Encoder (STE).
result STT outperforms previous baselines on the WildMix dataset.
Enhances SNNs for spatio-temporal feature extraction.
problem Insufficient temporal dependencies in existing SNN synaptic structures.
method Integrates temporal convolution and attention mechanisms into synaptic connections.
result Improves SNN performance on classification tasks.
Deep audio prior uses neural networks to solve audio problems without data.
problem Challenging audio problems like source separation, editing, and synthesis.
method Randomly-initialized neural network with carefully designed audio prior.
result Superior audio results on Universal-150 benchmark dataset.
3D-TGCN learns road graphs from time series similarity for spatio-temporal traffic forecasting.
problem Challenging spatio-temporal prediction in traffic networks due to dependency and dynamics.
method Proposes 3D-TGCN with novel components: spatial information-free road graph and 3D graph convolution.
result 3D-TGCN outperforms state-of-the-art baselines in traffic forecasting.
STCN combines TCNs with stochastic latent variables for sequence modeling.
problem Performance gap between TCNs and stochastic RNNs, especially with multiple layers of random variables.
method Proposes a hierarchy of stochastic latent variables in a modular architecture.
result Achieves state-of-the-art log-likelihoods across various tasks.
Recent studies have demonstrated the power of recurrent neural networks for machine translation, image captioning and speech recognition. For the task of capturing temporal structure in video, however, there still remain numerous open research questions. Current research suggests using a simple temporal feature pooling…
Enhances speech emotion recognition by adapting to varying time scales.
problem Robust emotion recognition from speech audio with temporal variations.
method Introduces multi-time-scale (MTS) convolutional layers to CNNs.
result MTS layers improve generalization, especially on smaller datasets.
Efficiently learns 3D convolutions with less data.
problem High parameter and data costs in 3D convolutions.
method Temporal factorization of 3D kernels.
result Significantly reduces training data requirement and parameter count.
A new CNN approach for time series forecasting outperforms traditional RNNs.
problem Time series forecasting using conventional RNNs.
method Temporally folded convolutional neural networks (TFC's) for sequence forecasting.
result TFC's outperform conventional RNNs on sequential MNIST and JSB chorals datasets.
Convolutional neural networks outperform other architectures in streaming time series classification.
problem Efficient deep learning models for real-time data streams.
method Asynchronous dual-pipeline deep learning framework for real-time predictions.
result Convolutional architectures achieve higher accuracy and efficiency in streaming time series classification.
This paper tackles spatio-temporal information preservation in machine learning.
problem Conventional machine learning assumes orthogonal data attributes, disrupting spatio-temporal information.
method Shift-invariant k-means, convolutional dictionary learning, and spatio-temporal hypercomplex encoding schemes are proposed.
result Gabor feature extraction outperforms convolutional dictionary learning in spatio-temporal information preservation.
Novel ECG classification for AF using spectro-temporal Kalman filtering and deep CNN.
problem Atrial fibrillation (AF) detection in ECG signals.
method Spectro-temporal representation using Kalman filter and deep convolutional neural networks.
result Proposed method achieves an overall F1 score of 80.2% on the PhysioNet/Computing in Cardiology (CinC) 2017 dataset.
New approach uses graphs for sign language recognition.
problem Challenges in recognizing sign language for deaf individuals.
method Spatial-Temporal Graph Convolutional Network.
result Improved sign language recognition using human skeletal movements.
Timely accurate traffic forecast is crucial for urban traffic control and guidance. Due to the high nonlinearity and complexity of traffic flow, traditional methods cannot satisfy the requirements of mid-and-long term prediction tasks and often neglect spatial and temporal dependencies. In this paper, we propose a nove…
A new neural network learns from acoustic scenes by suppressing irrelevant patterns.
problem Acoustic scenes are rich and redundant, making classification challenging.
method Spatio-temporal attention pooling layer coupled with a convolutional recurrent neural network.
result The method outperforms a strong convolutional neural network baseline and sets new state-of-the-art performance.
Develops a hybrid deep learning model for stock price prediction.
problem Predicting daily stock prices in the stock market.
method Representation learning with Stock2Vec embedding and temporal convolutional layers.
result Achieves better performance on stock price prediction than benchmarks.
A new method for separating mixed signals in space and time.
problem Nonlinear and nonstationary spatio-temporal data challenges.
method Identifiable autoregressive variational autoencoder.
result The method outperforms existing techniques in blind source separation and spatio-temporal prediction.
Paper proposes a new LSTM model for spatio-temporal learning.
problem Challenging video tasks require learning long-term spatio-temporal correlations.
method Introduces a higher-order convolutional LSTM model with tensor train decomposition.
result Model achieves state-of-the-art performance with significantly fewer parameters.
New model predicts ICU patients' stay duration efficiently.
problem Efficient ICU bed allocation under resource constraints.
method Temporal Pointwise Convolution (TPC) model combining temporal and pointwise convolutions.
result Significant performance improvements over LSTM and Transformer models.
A3T-GCN improves traffic forecasting by capturing spatial and temporal dependencies.
problem Accurate real-time traffic forecasting in complex road networks.
method Attention Temporal Graph Convolutional Network (A3T-GCN) integrating recurrent units and graph convolutional network.
result Improved prediction accuracy through attention mechanism and global temporal information.