arXiv research

Hybrid model predicts flow and pressure in water systems.

Introduces a novel spatial attention module for convolutional networks.

STCA discovers dynamic functional brain networks using spatial-temporal convolution and attention.

Hybrid model integrates GATv2 and geostatistics for better spatial prediction and uncertainty.

Inspired by the observation that humans are able to process videos efficiently by only paying attention where and when it is needed, we propose an interpretable and easy plug-in spatial-temporal attention mechanism for video action recognition. For spatial attention, we learn a saliency mask to allow the model to focus…

Study compares deep learning models for traffic forecasting, highlighting graph elements' impact.

Flow prediction (e.g., crowd flow, traffic flow) with features of spatial-temporal is increasingly investigated in AI research field. It is very challenging due to the complicated spatial dependencies between different locations and dynamic temporal dependencies among different time intervals. Although measurements of …

Enhanced deep learning model forecasts household leverage series accurately.

A3T-GCN improves traffic forecasting by capturing spatial and temporal dependencies.

The ability to decompose complex multi-object scenes into meaningful abstractions like objects is fundamental to achieve higher-level cognition. Previous approaches for unsupervised object-oriented scene representation learning are either based on spatial-attention or scene-mixture approaches and limited in scalability…

New results on splitting tangles and spatial graphs.

This is a survey article for the forthcoming `A Concise Encyclopedia of Knot Theory.' We focus on the topology of spatial graphs with few vertices and edges, paying particular attention to Brunnian $θ$-graphs.

GACAN combines multi-granularity time series for traffic forecasting.

Tiled Squeeze-and-Excite improves channel attention with local spatial context.

CutMix training technique improves spatial locality in Vision Transformers.

Model traffic congestion events using multi-modal data and attention-based neural networks.

Proposes a non-autoregressive Transformer for time series forecasting.

Diffusion Transformer captures spatial-temporal dependencies in sequential data.

Person Re-Identification (person re-id) is a crucial task as its applications in visual surveillance and human-computer interaction. In this work, we present a novel joint Spatial and Temporal Attention Pooling Network (ASTPN) for video-based person re-identification, which enables the feature extractor to be aware of …

Proposes a transformer model with geostatistical inductive bias for spatio-temporal forecasting.

Long-term prediction of multivariate time series is still an important but challenging problem. The key to solve this problem is to capture the spatial correlations at the same time, the spatio-temporal relationships at different times and the long-term dependence of the temporal relationships between different series.…

EFA extends self-attention to handle mixed data types and dynamic relevance.

Researchers develop a new spatial process model for non-Gaussian data.

Kriformer uses graph transformers to estimate data in sparse sensor areas.

As one of the important functions of the intelligent transportation system (ITS), supply-demand prediction for autonomous vehicles provides a decision basis for its control. In this paper, we present two prediction models (i.e. ARLP model and Advanced ARLP model) based on two system environments that only the current d…

As a crucial component in intelligent transportation systems, traffic flow prediction has recently attracted widespread research interest in the field of artificial intelligence (AI) with the increasing availability of massive traffic mobility data. Its key challenge lies in how to integrate diverse factors (such as te…

EAGLE-Net enhances foundation models by integrating patch-level features for better tissue understanding.

GOAT improves attention mechanisms by learning better priors.

GATGPT uses LLMs with graph attention for spatiotemporal data imputation.

Attention mechanisms and non-local mean operations in general are key ingredients in many state-of-the-art deep learning techniques. In particular, the Transformer model based on multi-head self-attention has recently achieved great success in natural language processing and computer vision. However, the vanilla algori…

In this work we present Discrete Attend Infer Repeat (Discrete-AIR), a Recurrent Auto-Encoder with structured latent distributions containing discrete categorical distributions, continuous attribute distributions, and factorised spatial attention. While inspired by the original AIR model andretaining AIR model's capabi…

A scalable Bayesian linear regression framework for spatial data.

Traffic flow prediction is crucial for urban traffic management and public safety. Its key challenges lie in how to adaptively integrate the various factors that affect the flow changes. In this paper, we propose a unified neural network module to address this problem, called Attentive Crowd Flow Machine~(ACFM), which …

Image clustering is an important but challenging task in machine learning. As in most image processing areas, the latest improvements came from models based on the deep learning approach. However, classical deep learning methods have problems to deal with spatial image transformations like scale and rotation. In this p…

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…

Graph Attention Networks predict power outage durations from natural disasters.

Language models trained on chess board states outperform those on moves, even with causal masking.

MetNet forecasts precipitation up to 8 hours with high spatial and temporal resolution.

Video-based emotion recognition is a challenging task because it requires to distinguish the small deformations of the human face that represent emotions, while being invariant to stronger visual differences due to different identities. State-of-the-art methods normally use complex deep learning models such as recurren…

Next point-of-interest (POI) recommendation aims to offer suggestions on which POI to visit next, given a user's POI visit history. This problem has a wide application in the tourism industry, and it is gaining an increasing interest as more POI check-in data become available. The problem is often modeled as a sequenti…

GraphDINO learns neuronal morphologies from unlabeled data.

Deep learning model predicts traffic flows across entire network for multiple steps ahead.

Improves AI agents' 3D navigation by learning from failures and 3D spatial relationships.

SympFormer accelerates attention blocks using inertial dynamics on density spaces.

Traffic forecasting is of great importance to transportation management and public safety, and very challenging due to the complicated spatial-temporal dependency and essential uncertainty brought about by the road network and traffic conditions. Latest studies mainly focus on modeling the spatial dependency by utilizi…

In this paper, we propose a model for the Environment Sound Classification Task (ESC) that consists of multiple feature channels given as input to a Deep Convolutional Neural Network (CNN) with Attention mechanism. The novelty of the paper lies in using multiple feature channels consisting of Mel-Frequency Cepstral Coe…

Image super-resolution is a challenging task and has attracted increasing attention in research and industrial communities. In this paper, we propose a novel end-to-end Attention-based DenseNet with Residual Deconvolution named as ADRD. In our ADRD, a weighted dense block, in which the current layer receives weighted f…

Vision Transformers show different internal representations compared to CNNs.