spatiotemporal modeling

Ele.me Technology

Aug 17, 2023 · Artificial Intelligence

BASM: A Bottom‑up Adaptive Spatiotemporal Model for Online Food Ordering Service

BASM is a bottom‑up adaptive spatiotemporal model for online food ordering that uses hierarchical embedding, semantic transformation, and adaptive bias layers to dynamically modulate parameters according to time and location, thereby capturing multiple data distributions and achieving superior offline metrics and online A/B test performance.

CTR predictionRecommendation systemsadaptive parameters

0 likes · 18 min read

BASM: A Bottom‑up Adaptive Spatiotemporal Model for Online Food Ordering Service

Ele.me Technology

Aug 16, 2023 · Artificial Intelligence

Spatiotemporal-Enhanced Network for Click-Through Rate Prediction in Location‑Based Services

The paper introduces StEN, a spatiotemporal-enhanced network for CTR prediction in location-based services, combining static spatiotemporal feature activation, dynamic preference activation, and target attention, achieving state-of-the-art offline results and a 1.6% CTR lift in online tests.

Deep LearningRecommendation systemsclick-through rate

0 likes · 19 min read

Spatiotemporal-Enhanced Network for Click-Through Rate Prediction in Location‑Based Services

DataFunTalk

Dec 17, 2022 · Artificial Intelligence

Efficient Spatiotemporal Self‑Attention Transformer (Patch Shift Transformer) for Video Action Recognition

This article introduces a lightweight spatiotemporal self‑attention transformer, called Patch Shift Transformer, which achieves competitive video action recognition performance on datasets such as Kinetics‑400, Sth‑v1/v2, and Diving48 without increasing computational cost or parameters, and details its design, experiments, and speed advantages.

ECCV 2022patch shiftspatiotemporal modeling

0 likes · 5 min read

Efficient Spatiotemporal Self‑Attention Transformer (Patch Shift Transformer) for Video Action Recognition