How Diffusion Models and Transformers Power the Next Generation of AI Video Generation

AI video generation now turns textual prompts into high‑quality clips using diffusion models and transformer‑based architectures; this article explains the underlying mathematics, training objectives, spatio‑temporal encoding, breakthroughs like consistent motion and physical realism, and discusses the technology’s opportunities and inherent risks.

AI video generationDiffusion ModelsSpatio-temporal modeling

0 likes · 11 min read

How Diffusion Models and Transformers Power the Next Generation of AI Video Generation

Amap Tech

Sep 24, 2020 · Artificial Intelligence

Hybrid Spatio‑Temporal Graph Convolutional Network for Precise Traffic Prediction

At the 2020 Yunqi Conference, Amap’s senior algorithm expert presented the Hybrid Spatio‑Temporal Graph Convolutional Network, which leverages massive real‑time navigation data to estimate future traffic flow, transform it into travel‑time features, and outperform prior models, enabling proactive congestion avoidance and dynamic traffic‑scheduling for millions of users.

HSTGCNSmart MobilitySpatio-temporal modeling

0 likes · 11 min read

Hybrid Spatio‑Temporal Graph Convolutional Network for Precise Traffic Prediction

Amap Tech

Jun 24, 2020 · Artificial Intelligence

Hybrid Spatio-Temporal Graph Convolutional Network (H‑STGCN) for Traffic Forecasting

The Hybrid Spatio‑Temporal Graph Convolutional Network (H‑STGCN) integrates planned traffic flow from navigation data via a domain transformer and a compound adjacency matrix, enabling graph‑based spatio‑temporal modeling that consistently outperforms baselines in real‑world traffic forecasting and reduces severe ETA errors.

Deep LearningH‑STGCNSpatio-temporal modeling

0 likes · 17 min read

Hybrid Spatio-Temporal Graph Convolutional Network (H‑STGCN) for Traffic Forecasting

Alibaba Cloud Developer

Aug 14, 2018 · Artificial Intelligence

How AI Predicts Short-Term Rainfall from Radar Images: A Competition Walkthrough

This article reviews the CIKM AnalytiCup 2017 competition, detailing how a team used radar image sequences, SIFT‑based motion tracking, and a custom convolutional neural network to forecast 1‑2‑hour precipitation totals, highlighting data preprocessing, feature extraction, model architecture, and training strategies.

CNNSIFTSpatio-temporal modeling

0 likes · 10 min read

How AI Predicts Short-Term Rainfall from Radar Images: A Competition Walkthrough