BestHub
Sign in
Tagged articles
4 articles
Page 1 of 1
AI Frontier Lectures
AI Frontier Lectures
Apr 13, 2025 · Artificial Intelligence

How HINT’s Hierarchical Multi‑Head Attention Boosts Image Restoration Quality

The paper introduces HINT, a Transformer‑based image restoration model that employs Hierarchical Multi‑Head Attention (HMHA) and a Query‑Key Cache Updating (QKCU) module to eliminate attention redundancy, achieving superior PSNR/SSIM scores across low‑light enhancement, dehazing, desnowing, denoising, and deraining tasks while maintaining low model complexity.

Computer VisionHierarchical AttentionImage Restoration
0 likes · 10 min read
How HINT’s Hierarchical Multi‑Head Attention Boosts Image Restoration Quality
Tencent Cloud Developer
Tencent Cloud Developer
Dec 4, 2020 · Artificial Intelligence

Building User Interest Tags in WeChat's Recommendation System

The paper presents a WeChat recommendation system that estimates user interest tags via multi‑class classification, using hierarchical intra‑ and inter‑domain attention and dense feature‑crossing to capture diverse preferences, aggregates click‑tag preferences rather than treating all tags equally, and demonstrates superior offline and online performance over baselines such as YouTube‑DNN, AFM, NFM, DCN, and AUTOINT.

AB testingHierarchical Attentionfeature crossing
0 likes · 8 min read
Building User Interest Tags in WeChat's Recommendation System
Alibaba Cloud Developer
Alibaba Cloud Developer
May 7, 2020 · Artificial Intelligence

How Hierarchical Attention Boosts Dynamic Heterogeneous Graph Embedding

This article introduces DyHAN, a hierarchical attention‑based dynamic heterogeneous graph embedding method that captures temporal, node‑level, and edge‑level information, demonstrates superior offline and online performance on Alibaba’s ICBU recommendation system, and discusses dataset construction, model architecture, and future challenges.

DyHANHierarchical Attentiondynamic heterogeneous graph
0 likes · 10 min read
How Hierarchical Attention Boosts Dynamic Heterogeneous Graph Embedding