metric learning

HelloTech

Jun 21, 2023 · Artificial Intelligence

Overview of Haro Intelligent Customer Service: Algorithms, Challenges, and AI Solutions

Haro’s intelligent customer service combines a smart FAQ recommender and a conversational chatbot that leverages matching‑based intent recognition, large‑scale domain pre‑training, metric‑learning for new intents, and fine‑tuned generative LLMs, achieving 82 % top‑1 accuracy while reducing human workload and outlining future API‑orchestrated, multimodal AI enhancements.

NLPaicustomer service

0 likes · 10 min read

Overview of Haro Intelligent Customer Service: Algorithms, Challenges, and AI Solutions

DataFunSummit

Jan 10, 2022 · Artificial Intelligence

Understanding Vector Retrieval: Principles, Applications, and High‑Performance Algorithms

This article explains how deep learning transforms raw physical‑world data into dense vectors, defines the significance of vector retrieval, surveys common use cases such as image, video, and text search, discusses challenges in representation learning, and reviews high‑performance approximate nearest‑neighbor algorithms and practical deployments.

AI applicationsDeep LearningVector Retrieval

0 likes · 21 min read

Understanding Vector Retrieval: Principles, Applications, and High‑Performance Algorithms

Amap Tech

Nov 4, 2021 · Artificial Intelligence

POI Signboard Image Retrieval: Technical Solution, Model Design, and Future Directions

To efficiently filter unchanged POI signboards, the authors propose a multimodal image‑retrieval system that combines enhanced global and local visual features with BERT‑encoded OCR text, using metric learning and alignment techniques to achieve over 95 % accuracy while handling occlusion, viewpoint variation, and subtle text changes.

Deep Learningcomputer visionimage retrieval

0 likes · 17 min read

POI Signboard Image Retrieval: Technical Solution, Model Design, and Future Directions

Kuaishou Tech

Apr 6, 2021 · Artificial Intelligence

Frequency-Aware Feature Learning with Single-Center Loss for Face Forgery Detection

Researchers from USTC and Kuaishou propose a frequency‑aware feature learning framework that combines a data‑driven adaptive frequency module with a novel single‑center loss, achieving state‑of‑the‑art performance on deepfake detection while addressing class‑distribution challenges.

AI securityDeepfake Detectioncomputer vision

0 likes · 7 min read

Frequency-Aware Feature Learning with Single-Center Loss for Face Forgery Detection