Introduces the BAH dataset with 1,427 annotated videos for multimodal recognition of ambivalence/hesitancy in digital behavior change contexts.
hub Mixed citations
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
Mixed citation behavior. Most common role is background (69%).
88
Pith papers citing it
Background
69% of classified citations
abstract
For most deep learning practitioners, sequence modeling is synonymous with recurrent networks. Yet recent results indicate that convolutional architectures can outperform recurrent networks on tasks such as audio synthesis and machine translation. Given a new sequence modeling task or dataset, which architecture should one use? We conduct a systematic evaluation of generic convolutional and recurrent architectures for sequence modeling. The models are evaluated across a broad range of standard tasks that are commonly used to benchmark recurrent networks. Our results indicate that a simple convolutional architecture outperforms canonical recurrent networks such as LSTMs across a diverse range of tasks and datasets, while demonstrating longer effective memory. We conclude that the common association between sequence modeling and recurrent networks should be reconsidered, and convolutional networks should be regarded as a natural starting point for sequence modeling tasks. To assist related work, we have made code available at http://github.com/locuslab/TCN .
hub tools
citation-role summary
background 9
baseline 3
method 1
citation-polarity summary
claims ledger
- abstract For most deep learning practitioners, sequence modeling is synonymous with recurrent networks. Yet recent results indicate that convolutional architectures can outperform recurrent networks on tasks such as audio synthesis and machine translation. Given a new sequence modeling task or dataset, which architecture should one use? We conduct a systematic evaluation of generic convolutional and recurrent architectures for sequence modeling. The models are evaluated across a broad range of standard tasks that are commonly used to benchmark recurrent networks. Our results indicate that a simple conv
co-cited works
representative citing papers
S4 is an efficient state space sequence model that captures long-range dependencies via structured parameterization of the SSM, achieving state-of-the-art results on the Long Range Arena and other benchmarks while being faster than Transformers for generation.
Presents SE-WaveNet with weight-tied dilated convolutions plus wavelet and spectral components that reproduces empirical scaling collapse on financial returns while using L times fewer convolutional parameters.
U-STS-LLM uses a spatio-temporally steered LLM with dynamic attention bias generation to achieve state-of-the-art results on long-horizon traffic forecasting and high-missing-rate imputation while remaining parameter-efficient.
TailedTS supplies 24.69 billion Wikipedia page-view records as a public benchmark for heavy-tailed time series forecasting and periodicity analysis, revealing weaker periodic structure in high-traffic pages.
SIGMA-ASL is a multimodal dataset with 93,545 word-level ASL clips from Kinect RGB-D, mmWave radar, and dual IMUs, plus benchmarking protocols for single- and multi-modal recognition.
BadmintonGRF is a new public multimodal dataset and benchmark that pairs multi-view video with instrumented GRF for markerless load estimation in badminton.
GAFSV-Net encodes online signatures as asymmetric Gramian Angular Field images and processes them with dual-branch ConvNeXt plus cross-attention to outperform sequence-based baselines on DeepSignDB and BiosecurID.
Temporal autocorrelation reintroduces spectral bias in KANs for time series forecasting, which DCT preprocessing can mitigate.
The CNN-derived catalog detects over seven times more solar flares than the GOES catalog and extends the power-law distribution of flare peak fluxes to smaller sizes.
Spacetime SSM forecasters represent optimal Kalman predictors for autoregressive data but remain vulnerable to model-free attacks that exploit local linearity and increase error by over 33% compared to projected gradient descent.
T1 uses one-to-one channel-head binding in a CNN-Transformer hybrid to achieve robust multivariate time-series imputation, cutting average MSE by 46% versus the next-best baseline across 11 datasets even at 70% missingness.
MELT is the first behavioral trace dataset for high-risk memecoin launch detection on Solana, providing 122 features, risk annotations, and ML benchmarks that reduce investment loss when used for selection.
CaTSG is a unified diffusion model for causal time series generation that handles observational, interventional, and counterfactual tasks via backdoor adjustment and abduction-action-prediction.
Sundial uses TimeFlow Loss for native pre-training of Transformers on continuous time series from TimeBench, achieving SOTA point and probabilistic forecasting with millisecond inference.
Controlled experiments attribute cross-subject EEG classification degradation to inter-subject variability in multi-class tasks and shortcut learning in single-class tasks.
This survey and benchmark of deep time series models using the released TSLib library finds that models with specific structures perform well only on distinct analysis tasks.
Time-LLM reprograms frozen LLMs for time series forecasting via text prototypes and Prompt-as-Prefix, outperforming specialized models in standard, few-shot, and zero-shot settings.
First benchmarking of ordinal adaptations of CNN and DL methods for time series shows they outperform nominal TSC techniques on ordinal metrics across 29 selected problems.
PatchTST uses subseries patching and channel-independent Transformers to deliver significantly better long-term multivariate time series forecasting and strong self-supervised transfer performance.
Defines iterated-sums signatures over commutative semirings (tropical case emphasized) for time-series feature extraction and links them to quasisymmetric functions over semirings.
ReactiveGWM introduces a decoupled diffusion architecture for player-NPC interactions that learns game-agnostic response logic for zero-shot strategy transfer across games.
A five-phase co-training framework enables stable JEPA pretraining on EHR trajectories, producing converging latent rollouts and higher multi-task AUROC than baselines on MIMIC-IV ICU data.
MS-FLOW uses a capacity-limited sparse routing mechanism to model only critical inter-variable dependencies in time series data, achieving state-of-the-art accuracy on 12 benchmarks with fewer but more reliable connections.
citing papers explorer
-
Universal Time-Series Representation Learning: A Survey
A survey that proposes a taxonomy for universal time-series representation learning and reviews existing deep learning studies along with experimental setups.