novel deep learning research works with PaddlePaddle

[ECCV'2020] STTN: Learning Joint Spatial-Temporal Transformations for Video Inpainting

Formation Flight in Dense Environments

STEP: Spatio-Temporal Progressive Learning for Video Action Detection. CVPR'19 (Oral)

State-of-the-art model for person re-identification in Multi-camera Multi-Target Tracking. Benchmarked on Market-1501 and DukeMTMTC-reID datasets.

A curated collection of research papers, models, and resources tracing the evolution from specialized models to unified world models.

FedSTIL: Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edges. (TCSVT'23)

[EMNLP 2024] A Video Chat Agent with Temporal Prior

A high-level Python framework to evaluate the skill of geospatial datasets by comparing candidates to benchmark maps producing agreement maps and metrics.

[ICASSP 2025 Oral] ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Images

[ICASSP 2025 Oral] ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Images

A Python framework to evaluate geospatial datasets by comparing candidate and benchmark maps to compute agreement maps and statistics.

MATLAB implementation of ST-Matching Algorithm for map matching

A framework for designing and evaluating Spatio-Temporal networks.

R package | Data Class and Tools for Handling Spatial-Temporal Data

A unified Spatial Temporal Net Trainer for different baselines in Spatial Temporal Forecasting problems.

Paper: Task-Adaptive Meta-Learning Framework for Advancing Spatial Generalizability.

Pytorch version of ST-ResNet

A Human Action Recognition (HAR) model combining 3D CNN and LSTM networks to accurately recognize actions in videos using spatial-temporal feature extraction. Trained on UCF-50 and outperforming existing architectures.

PredRNN implementation using Tensorflow.

Forecasting traffic speed using sensor data from San Diego highways and a Spatial-Temporal Graph Attention Network.

🔍 Accelerate research using a Multi Agent System for efficient context engineering with DeepAgent and LangChain's library.

The LC2019 team winning entry for the EVA 2019 data competition

Official PyTorch implementation of Lite-STGNN

A Python implementation of sti-dbscan: an algorithm based on st-dbscan (which is based on dbscan) that clusters spatial-temporal interval data

🔍 Explore AI-generated research projects, showcasing code and insights created entirely by LLM tools like Claude Code.

PurgeLite: Lightweight Graph Neural Networks with Dynamic Purging for Traffic Forecasting

Robust vision based lane detection with spatial temporal deep learning

Some guides using postgis to load and processing environment-related data

🎨 Compute WCAG contrast efficiently using ESDT methods on GPU and CPU with Futhark for accurate web accessibility research and development.