BestHub
Sign in
Tagged articles
1235 articles
Page 5 of 13
Alibaba Cloud Infrastructure
Alibaba Cloud Infrastructure
Mar 22, 2023 · Artificial Intelligence

CUTLASS Extreme Performance Optimization and Its Application in Alibaba's Recommendation System

At the GTC conference, the talk presents Alibaba Cloud’s heterogeneous computing platform and introduces the Open Deep Learning API (ODLA), then details how CUTLASS‑based operator fusion dramatically accelerates attention and MLP layers in large‑scale recommendation models, achieving multi‑fold performance gains in production.

CUTLASSDeep LearningGPU computing
0 likes · 5 min read
CUTLASS Extreme Performance Optimization and Its Application in Alibaba's Recommendation System
Baidu Geek Talk
Baidu Geek Talk
Mar 16, 2023 · Artificial Intelligence

PaddleDetection v2.6 Release: PP-YOLOE Family Expansion and Advanced Detection Algorithms

PaddleDetection v2.6 expands the PP‑YOLOE family with rotating, small‑object, dense‑object, and ultra‑lightweight edge‑GPU models, upgrades PP‑Human and PP‑Vehicle toolboxes, releases semi‑supervised, few‑shot and distillation learning methods, adds numerous state‑of‑the‑art algorithms, and improves infrastructure with Python 3.10, EMA filtering and AdamW support.

BaiduComputer VisionDeep Learning
0 likes · 14 min read
PaddleDetection v2.6 Release: PP-YOLOE Family Expansion and Advanced Detection Algorithms
政采云技术
政采云技术
Mar 9, 2023 · Artificial Intelligence

Comprehensive Overview of Object Detection: From Traditional Methods to Modern Deep Learning Models

This article provides a comprehensive overview of object detection, describing traditional sliding‑window approaches, deep‑learning based two‑stage and one‑stage models such as R‑CNN, Faster R‑CNN, YOLO series, and discusses current challenges, improvement directions, and future research trends in the field.

Computer VisionDeep LearningR-CNN
0 likes · 29 min read
Comprehensive Overview of Object Detection: From Traditional Methods to Modern Deep Learning Models
Tencent Cloud Developer
Tencent Cloud Developer
Mar 8, 2023 · Artificial Intelligence

Building a Scalable Recommendation System for WeChat Games: Architecture and Implementation

The article describes WeChat Games’ scalable recommendation system, detailing its four‑component architecture—offline ML platform, unified management, online DAG‑based engine, and peripheral services—along with a hybrid algorithm library, feature engineering, real‑time monitoring, and solutions that boost engagement across diverse game recommendation scenarios.

Data ManagementDeep LearningReal-time Processing
0 likes · 28 min read
Building a Scalable Recommendation System for WeChat Games: Architecture and Implementation
DataFunTalk
DataFunTalk
Feb 25, 2023 · Artificial Intelligence

The Evolution of Modern AI: From Deep Learning Foundations to ChatGPT and Future Directions

This article traces the development of artificial intelligence from its early conceptual roots and the 2012 deep‑learning breakthrough through the rise of self‑supervised large language models like BERT and GPT, explains ChatGPT’s architecture and RLHF training, and discusses its commercial impact and future prospects for fields such as life sciences.

AI applicationsChatGPTDeep Learning
0 likes · 19 min read
The Evolution of Modern AI: From Deep Learning Foundations to ChatGPT and Future Directions
DataFunTalk
DataFunTalk
Feb 22, 2023 · Artificial Intelligence

Fundamentals, Frontiers, and Applications of Graph Neural Networks

An in‑depth overview of graph neural networks (GNNs) covering their basic concepts, historical development, core models, recent research frontiers, and diverse applications such as recommendation systems, computer vision, NLP, program analysis, and smart cities, based on the book “Fundamentals, Frontiers and Applications of GNNs.”

AI applicationsDeep LearningGNN Models
0 likes · 12 min read
Fundamentals, Frontiers, and Applications of Graph Neural Networks
Architects Research Society
Architects Research Society
Feb 18, 2023 · Artificial Intelligence

Comparison of Deep Learning Software Frameworks

This article provides an overview of deep learning as a branch of machine learning and presents detailed comparative tables of popular deep‑learning software frameworks, covering creators, initial releases, licenses, platforms, programming languages, supported features such as CUDA, OpenMP, and model‑training capabilities.

Deep Learningartificial intelligencesoftware frameworks
0 likes · 9 min read
Comparison of Deep Learning Software Frameworks
Baidu Geek Talk
Baidu Geek Talk
Feb 15, 2023 · Artificial Intelligence

PaddlePaddle 2.4 Release: New Sparse, Graph, and Audio APIs

PaddlePaddle 2.4 introduces 167 new APIs—including sparse computing (paddle.sparse), graph learning (paddle.geometric), and audio processing (paddle.audio) modules—enabling efficient sparse model training and inference, graph message‑passing, advanced audio feature extraction, plus fresh loss functions, tensor utilities, and expanded vision transforms.

API ReleaseAudio ProcessingDeep Learning
0 likes · 16 min read
PaddlePaddle 2.4 Release: New Sparse, Graph, and Audio APIs
DataFunSummit
DataFunSummit
Feb 14, 2023 · Artificial Intelligence

Deep Learning Hyperparameter Tuning and Training Tips: Insights from Zhihu Experts

This article compiles practical deep learning training and hyperparameter tuning advice from Zhihu contributors, covering model debugging, learning‑rate strategies, optimizer choices, data preprocessing, regularization techniques, initialization methods, common pitfalls, recommended research papers, and ensemble approaches.

Deep LearningRegularizationgradient clipping
0 likes · 13 min read
Deep Learning Hyperparameter Tuning and Training Tips: Insights from Zhihu Experts
Volcano Engine Developer Services
Volcano Engine Developer Services
Feb 14, 2023 · Artificial Intelligence

How Make-An-Audio Turns Text Into Realistic Sound Effects

Make-An-Audio, a collaborative text‑to‑audio model from Zhejiang University, Peking University and Volcano Speech, uses a Distill‑then‑Reprogram strategy to generate high‑quality, controllable sound effects from any modality, showcasing impressive demos and promising future AIGC applications.

AIGCDeep LearningSpeech synthesis
0 likes · 7 min read
How Make-An-Audio Turns Text Into Realistic Sound Effects
DataFunTalk
DataFunTalk
Feb 11, 2023 · Artificial Intelligence

Accelerating Computer Vision Pipelines with CV-CUDA: Reducing Complexity and Performance Bottlenecks

This article explains how moving image preprocessing and post‑processing to GPU with the open‑source CV‑CUDA library dramatically reduces system complexity, eliminates CPU‑GPU bottlenecks, and delivers up to thirty‑fold performance gains for computer‑vision workloads across training and inference stages.

CV-CUDAComputer VisionDeep Learning
0 likes · 16 min read
Accelerating Computer Vision Pipelines with CV-CUDA: Reducing Complexity and Performance Bottlenecks
JD Cloud Developers
JD Cloud Developers
Feb 8, 2023 · Operations

Boosting Log Anomaly Detection with NLP and Deep Learning

This article presents a log anomaly detection approach that leverages NLP techniques such as Part‑of‑Speech tagging and Named Entity Recognition combined with deep neural networks, detailing a six‑step model, experimental validation on three datasets, and superior performance compared with existing DeepLog and LogClass methods.

DNNDeep LearningNER
0 likes · 13 min read
Boosting Log Anomaly Detection with NLP and Deep Learning
DataFunSummit
DataFunSummit
Feb 6, 2023 · Artificial Intelligence

A Minimalist White‑Box Unsupervised Learning Method Using Sparse Manifold Transform

A recent paper by Prof. Ma Yi and Turing‑Award winner Yann LeCun introduces a simple, interpretable unsupervised learning approach that combines sparse coding, manifold learning, and slow feature analysis, achieving near‑state‑of‑the‑art performance on MNIST, CIFAR‑10, and CIFAR‑100 without data augmentation or extensive hyper‑parameter tuning.

AIDeep LearningUnsupervised Learning
0 likes · 8 min read
A Minimalist White‑Box Unsupervised Learning Method Using Sparse Manifold Transform
DataFunSummit
DataFunSummit
Feb 5, 2023 · Artificial Intelligence

Key Takeaways from the Causal Inference Summit: Motivation, Applications, Challenges, and Links to A/B Testing, Machine Learning, and Deep Learning

After attending the DataFun causal inference summit, this article outlines why causal analysis matters, its typical use cases, practical challenges, its relationship with A/B testing, and how it integrates with machine learning and deep learning to improve decision‑making and model robustness.

A/B testingDeep LearningUplift Modeling
0 likes · 10 min read
Key Takeaways from the Causal Inference Summit: Motivation, Applications, Challenges, and Links to A/B Testing, Machine Learning, and Deep Learning
Alimama Tech
Alimama Tech
Feb 1, 2023 · Artificial Intelligence

CapOnImage: Context-driven Dense Captioning on Images

The paper presents CapOnImage, a novel image‑on‑image captioning task that generates location‑specific decorative text for product images, introduces the 2.1‑million‑image CapOnImage2M dataset, and proposes a mixed‑modality transformer with position‑aware pre‑training and progressive training, achieving superior accuracy and diversity and already deployed in Alibaba’s advertising platforms for measurable business impact.

Context-AwareDatasetDeep Learning
0 likes · 9 min read
CapOnImage: Context-driven Dense Captioning on Images
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Jan 10, 2023 · Artificial Intelligence

AI‑Driven Video Coding: Expert Q&A on Intelligent Compression, Standards, and Future Directions

Experts Wang Shenshe and Chen Jing discuss how deep‑learning‑based video coding is reshaping traditional compression by offering modest quality gains but facing theoretical, hardware, and standardization hurdles, while debating hybrid versus end‑to‑end designs, rate control, 3‑D support, and the balance between human‑centric perception and machine‑oriented efficiency.

AIDeep LearningRate Control
0 likes · 16 min read
AI‑Driven Video Coding: Expert Q&A on Intelligent Compression, Standards, and Future Directions
Tencent Cloud Developer
Tencent Cloud Developer
Jan 9, 2023 · Artificial Intelligence

Search Relevance Architecture and Practices in QQ Browser

The QQ Browser search relevance team describes a unified, billion‑scale architecture that combines a main and vertical subsystem, a pyramid‑shaped ranking pipeline (recall, coarse, fine), a dedicated GPU‑accelerated relevance service, and hybrid semantic‑matching models (dual‑tower, BERT, matrix fusion) evaluated with offline and online metrics to deliver accurate, fresh, and authoritative results for diverse content and long‑tail queries.

Deep LearningEvaluation MetricsSystem Architecture
0 likes · 28 min read
Search Relevance Architecture and Practices in QQ Browser
DataFunTalk
DataFunTalk
Jan 9, 2023 · Artificial Intelligence

Key Techniques for Digital Human Modeling: Facial Portrait Editing, Eyelash Segmentation, and Real‑Time Loose Clothing Animation

This article reviews recent research on digital human creation, covering graph‑based facial portrait editing (fat‑slim adjustment, double‑chin removal, hair removal), a high‑quality eyelash segmentation dataset with the EyelashNet pipeline, and a deep‑learning framework for real‑time animation of loose clothing using virtual skeletons and RBF networks.

Deep Learningdigital humanseyelash segmentation
0 likes · 15 min read
Key Techniques for Digital Human Modeling: Facial Portrait Editing, Eyelash Segmentation, and Real‑Time Loose Clothing Animation
DataFunTalk
DataFunTalk
Jan 8, 2023 · Artificial Intelligence

Adaptive Blend Pyramid Network for Real-Time Local Retouching of Ultra High-Resolution Images

The paper introduces ABPN, an Adaptive Blend Pyramid Network that achieves precise, high‑quality skin retouching and garment wrinkle removal on 4K‑8K photos in real time by combining a context‑aware local retouching layer with a novel adaptive blend pyramid layer, addressing challenges of artifact‑free detail preservation and efficient high‑resolution processing.

Computer VisionDeep Learningadaptive blend pyramid
0 likes · 16 min read
Adaptive Blend Pyramid Network for Real-Time Local Retouching of Ultra High-Resolution Images
Bilibili Tech
Bilibili Tech
Jan 3, 2023 · Artificial Intelligence

Two‑Pass Deep Learning Bitrate Factor Prediction for Constant‑Quality Segment Encoding in Bilibili Narrow‑Band HD Transcoding

Bilibili’s IEEE‑VCIP‑2022‑accepted two‑pass deep‑learning bitrate‑factor predictor achieves 98.8% accuracy with only 1.55 encoding passes, enabling constant‑quality segment encoding that reduces bitrate consumption by over 15% while maintaining visual quality in its narrow‑band HD transcoding pipeline.

AIBitrate OptimizationDeep Learning
0 likes · 6 min read
Two‑Pass Deep Learning Bitrate Factor Prediction for Constant‑Quality Segment Encoding in Bilibili Narrow‑Band HD Transcoding
DataFunTalk
DataFunTalk
Dec 28, 2022 · Artificial Intelligence

A Comprehensive Survey of Graph Neural Networks: Development, Complex Graph Models, Applications, Scalability, and Future Directions

This article provides an extensive overview of graph neural networks, tracing their evolution from early RNN‑based models to modern message‑passing frameworks, discussing complex graph types, diverse real‑world applications, scalability challenges, design spaces, training platforms, and promising research directions.

Deep LearningGNNScalability
0 likes · 49 min read
A Comprehensive Survey of Graph Neural Networks: Development, Complex Graph Models, Applications, Scalability, and Future Directions
DataFunTalk
DataFunTalk
Dec 27, 2022 · Artificial Intelligence

Efficient Training for Very Large‑Scale Face Recognition and the FFC Framework

This article reviews the challenges of ultra‑large‑scale face recognition, presents existing solutions such as metric learning, PFC and VFC, and details the proposed FFC framework with dual loaders, ID groups, probe and gallery networks, plus experimental results showing its cost‑effective performance.

AIComputer VisionDeep Learning
0 likes · 7 min read
Efficient Training for Very Large‑Scale Face Recognition and the FFC Framework
58 Tech
58 Tech
Dec 22, 2022 · Artificial Intelligence

Implementing a Cloud-Native Istio Gateway for 58.com Deep Learning Inference Platform

This article details the evolution of 58.com’s deep learning inference platform, describing the transition from the original SCF‑based architecture to a cloud‑native Istio gateway (architecture 2.0), and explains design choices, traffic‑management, adaptive rate‑limiting, observability, model pre‑warming, and performance improvements.

AICloud NativeDeep Learning
0 likes · 22 min read
Implementing a Cloud-Native Istio Gateway for 58.com Deep Learning Inference Platform
Alimama Tech
Alimama Tech
Dec 21, 2022 · Artificial Intelligence

Adaptive Parameter Generation Network for Click-Through Rate Prediction

Adaptive Parameter Generation Network (APG) dynamically creates sample‑specific model parameters for click‑through‑rate prediction using low‑rank factorization, parameter sharing, and over‑parameterization, achieving up to 0.2% AUC improvement, 3% CTR lift, and up to 96.6% storage reduction with faster inference.

CTR predictionDeep Learningadaptive parameter generation
0 likes · 14 min read
Adaptive Parameter Generation Network for Click-Through Rate Prediction
DataFunTalk
DataFunTalk
Dec 21, 2022 · Artificial Intelligence

A Comprehensive Overview of Computational Advertising: Architecture, Deep‑Learning Evolution, and Future Directions

This article provides a thorough examination of computational advertising, covering the oCPM pricing model as a superset, classic system architecture, the evolution of core modules such as ad ranking, pacing, bidding, federated learning, calibration, and conversion‑delay handling, and concludes with career advice for algorithm engineers.

CalibrationDeep LearningFederated Learning
0 likes · 29 min read
A Comprehensive Overview of Computational Advertising: Architecture, Deep‑Learning Evolution, and Future Directions
DataFunTalk
DataFunTalk
Dec 17, 2022 · Artificial Intelligence

Multimodal Pre‑training Techniques and Applications – Overview, OPPOVL Dataset, Architecture, and Performance

This article presents a comprehensive overview of multimodal pre‑training, describing its motivation, architecture choices, large‑scale Chinese image‑text dataset construction, training optimizations, performance benchmarks, downstream applications, and a Q&A session that highlights practical deployment considerations.

Computer VisionDeep LearningModel architecture
0 likes · 16 min read
Multimodal Pre‑training Techniques and Applications – Overview, OPPOVL Dataset, Architecture, and Performance
Alimama Tech
Alimama Tech
Dec 14, 2022 · Artificial Intelligence

Contrastive Image Representation Learning with Debiasing for CTR Prediction

The article proposes a three-stage contrastive learning framework—pre‑training, fine‑tuning, and debiasing—to generate unbiased, fine‑grained image embeddings for mobile Taobao CTR prediction, achieving higher accuracy, fairness, and a 4‑5% CTR lift in large‑scale offline and online evaluations.

CTR predictionDeep Learningbias mitigation
0 likes · 14 min read
Contrastive Image Representation Learning with Debiasing for CTR Prediction
vivo Internet Technology
vivo Internet Technology
Dec 7, 2022 · Artificial Intelligence

Mixing Heterogeneous Queues in Vivo's Information Flow and App Store: Challenges, Practices, and RL/Deep Learning Solutions

Vivo tackles the complex problem of mixing heterogeneous content queues—ads, games, and organic items—in its information‑flow and app‑store by evolving from rule‑based weighting to Q‑learning and deep‑learning position models that respect product constraints, preserve ordering, and balance short‑term revenue with long‑term user experience, while planning deeper personalization and on‑device solutions.

AdvertisingApp StoreDeep Learning
0 likes · 14 min read
Mixing Heterogeneous Queues in Vivo's Information Flow and App Store: Challenges, Practices, and RL/Deep Learning Solutions
Alimama Tech
Alimama Tech
Dec 7, 2022 · Artificial Intelligence

Adaptive Domain Interest Network for Multi-domain Recommendation

The Adaptive Domain Interest Network (ADIN) introduces a shared backbone with scenario‑specific subnetworks, domain‑specific batch normalization and SE‑Block attention to capture both commonalities and divergences across recommendation scenarios, and, combined with self‑supervised training, consistently outperforms baselines, delivering a 1.8% revenue lift in Alibaba’s display‑ad platform and now runs in production.

Deep Learningdomain adaptationrecommendation
0 likes · 12 min read
Adaptive Domain Interest Network for Multi-domain Recommendation
DataFunTalk
DataFunTalk
Dec 4, 2022 · Artificial Intelligence

Key Insights on Causal Inference: Motivation, Applications, Challenges, and Links to A/B Testing, ML, and Deep Learning

This article summarizes the motivations behind causal inference, its typical business applications such as intelligent decision‑making and prediction, the practical challenges of validation and data, and its relationship with A/B testing, machine learning, and deep learning, providing a concise overview for newcomers.

AB testingBusiness AnalyticsDeep Learning
0 likes · 10 min read
Key Insights on Causal Inference: Motivation, Applications, Challenges, and Links to A/B Testing, ML, and Deep Learning
Hulu Beijing
Hulu Beijing
Dec 2, 2022 · Artificial Intelligence

How Disney+ Designs a Multi‑Task Video Search Ranking Model

This article explains the architecture of a video search ranking system that combines a deep encoding network, multi‑task expert networks, and a bias‑correction module to jointly optimize relevance, click‑through rate, and watch time for streaming platforms.

Bias CorrectionDeep Learningfeature engineering
0 likes · 15 min read
How Disney+ Designs a Multi‑Task Video Search Ranking Model
DataFunSummit
DataFunSummit
Nov 30, 2022 · Artificial Intelligence

Combining Knowledge Graphs with Personalized News Recommendation Systems

This article presents a comprehensive overview of a personalized news recommendation system that leverages knowledge graphs to improve accuracy, explainability, and user satisfaction, detailing background motivations, graph construction methods, model architecture, experimental results, and practical insights from a Meituan research perspective.

Deep Learningexplainabilitygraph neural networks
0 likes · 23 min read
Combining Knowledge Graphs with Personalized News Recommendation Systems
Architects Research Society
Architects Research Society
Nov 30, 2022 · Artificial Intelligence

A Comprehensive Overview of Machine Learning Tools and Libraries

An extensive survey ranks and compares a wide range of machine learning libraries and frameworks—both deep and shallow learning—detailing their languages, types, GPU acceleration, distributed computing capabilities, and typical academic and industrial applications, based on Google search popularity as of May.

Deep LearningGPU Accelerationdistributed computing
0 likes · 20 min read
A Comprehensive Overview of Machine Learning Tools and Libraries
SQB Blog
SQB Blog
Nov 18, 2022 · Artificial Intelligence

Boosting AI Model Development with Alibaba's EasyModeling Framework

This article introduces the EasyModeling framework built on Alibaba Cloud's PAI platform, detailing its modular design, high reusability, integration with deep‑learning libraries, automated hyper‑parameter tuning, deployment scenarios, and a real‑world case study using RoBERTa for dish‑name standardization, demonstrating significant performance gains.

AI modelingAlibaba CloudAutoML
0 likes · 13 min read
Boosting AI Model Development with Alibaba's EasyModeling Framework
Zuoyebang Tech Team
Zuoyebang Tech Team
Nov 17, 2022 · Artificial Intelligence

Scaling Deep Learning Model Serving: High‑Concurrency, Low‑Latency Solutions

This article examines the challenges of deploying dozens of deep‑learning models at Zuoyebang and compares three serving architectures—Gunicorn + Flask + Transformers, Tornado + PyTorch, and Tornado + Triton—highlighting performance trade‑offs and presenting a final high‑concurrency, low‑latency solution in production.

Deep LearningLow latencyModel Deployment
0 likes · 11 min read
Scaling Deep Learning Model Serving: High‑Concurrency, Low‑Latency Solutions
Tencent Advertising Technology
Tencent Advertising Technology
Nov 17, 2022 · Artificial Intelligence

Scaling Huge Embedding Model Training with Cache-Enabled Distributed Framework (HET): VLDB 2022 Best Paper and Its Industrial Deployment

The award‑winning VLDB 2022 paper introduces HET, a cache‑enabled distributed framework that dramatically reduces communication overhead for sparse trillion‑parameter embedding models, and Tencent Ads has industrialized this technology to train 10 TB‑scale models with up to 7×24‑hour online deep learning.

CacheDeep LearningEmbedding
0 likes · 9 min read
Scaling Huge Embedding Model Training with Cache-Enabled Distributed Framework (HET): VLDB 2022 Best Paper and Its Industrial Deployment
Alimama Tech
Alimama Tech
Nov 16, 2022 · Artificial Intelligence

STARDOM: Semantic-Aware Deep Hierarchical Forecasting Model for Search Traffic Prediction

STARDOM is an end‑to‑end deep hierarchical forecasting model that jointly learns hierarchical constraints, query semantics via pretrained BERT, and a calibration matrix within an encoder‑decoder architecture, using a distilled reconciliation loss and hierarchical sampling to accurately predict large‑scale search traffic and outperform state‑of‑the‑art baselines.

Deep Learninghierarchical modelingsearch advertising
0 likes · 22 min read
STARDOM: Semantic-Aware Deep Hierarchical Forecasting Model for Search Traffic Prediction
DataFunSummit
DataFunSummit
Nov 10, 2022 · Artificial Intelligence

Voice‑Driven Facial Animation for Digital Humans: Techniques and OPPO XiaoBu Assistant Practice

This article introduces digital‑human voice‑driven facial animation technologies, compares motion‑capture, audio‑driven and key‑point methods, details OPPO XiaoBu Assistant's end‑side and cloud‑side Audio2Lip pipelines, explores BlendShape versus Mesh approaches, and discusses current challenges and future research directions.

Deep LearningOPPOaudio-to-facial
0 likes · 15 min read
Voice‑Driven Facial Animation for Digital Humans: Techniques and OPPO XiaoBu Assistant Practice
Shopee Tech Team
Shopee Tech Team
Nov 10, 2022 · Artificial Intelligence

ShopeeVideo OCR: Multi-language Text Recognition System for E-commerce Video

ShopeeVideo OCR is a multi‑language text‑recognition system for Southeast Asian e‑commerce videos that unifies detection, Transformer‑based recognition, layout analysis, and large‑scale synthetic data generation to handle Indonesian, Filipino, English, Vietnamese, Thai and Chinese scripts, delivering industry‑leading accuracy and winning thirteen ICDAR first‑place awards.

Computer VisionDeep LearningMulti-language OCR
0 likes · 15 min read
ShopeeVideo OCR: Multi-language Text Recognition System for E-commerce Video
Ctrip Technology
Ctrip Technology
Nov 10, 2022 · Artificial Intelligence

Improving Search Intent Recognition and Term Weighting with Deep Learning and Model Distillation at Ctrip

This article describes how Ctrip's R&D team applied deep‑learning models, BERT‑based embeddings, knowledge distillation, and term‑weighting techniques to enhance e‑commerce search intent recognition and term importance estimation, achieving high accuracy while meeting sub‑10 ms latency requirements.

BERTDeep LearningSearch
0 likes · 12 min read
Improving Search Intent Recognition and Term Weighting with Deep Learning and Model Distillation at Ctrip
Bilibili Tech
Bilibili Tech
Nov 8, 2022 · Artificial Intelligence

Real-Time Super-Resolution Algorithm for League of Legends S12 Live Streaming

A lightweight real‑time super‑resolution network was created for the 2022 League of Legends S12 World Championship, using pixel‑unshuffle/shuffle, structural re‑parameterization, and a multi‑loss (L1, perceptual, Sobel‑based texture, GAN) training pipeline that upscales 1080p streams to 4K at 75 fps on a V100 GPU, delivering clearer textures and reduced noise while remaining computationally efficient.

Deep LearningLoss Functionsgame streaming
0 likes · 10 min read
Real-Time Super-Resolution Algorithm for League of Legends S12 Live Streaming
JD Cloud Developers
JD Cloud Developers
Nov 7, 2022 · Artificial Intelligence

Detecting Time‑Series Anomalies Without Thresholds Using LSTM and Unsupervised Fusion

This article presents a threshold‑free anomaly detection framework for streaming time series that combines an LSTM‑based baseline module with an unsupervised detection module, detailing the architecture, training process, data preprocessing, and experimental results that demonstrate superior accuracy and F1 scores.

Deep LearningLSTMTime Series
0 likes · 15 min read
Detecting Time‑Series Anomalies Without Thresholds Using LSTM and Unsupervised Fusion
Model Perspective
Model Perspective
Nov 5, 2022 · Artificial Intelligence

Explore the Most Popular Machine Learning Algorithms and How They Work

This comprehensive guide walks you through the most popular machine learning algorithms, explaining how they are classified by learning style and problem type, and highlighting key examples from supervised, unsupervised, deep learning, ensemble, and many other algorithm families.

Deep LearningUnsupervised Learningsupervised learning
0 likes · 11 min read
Explore the Most Popular Machine Learning Algorithms and How They Work
Baidu Geek Talk
Baidu Geek Talk
Oct 31, 2022 · Artificial Intelligence

PaddleBox: A GPU‑Based Ultra‑Large‑Scale Sparse DNN Training Framework

PaddleBox is Baidu’s GPU‑based ultra‑large‑scale sparse DNN training framework that combines a three‑tier hierarchical parameter server (SSD, DRAM, HBM) with pipelined scheduling and multi‑machine multi‑GPU communication, delivering 5–40× cost‑performance gains over traditional CPU solutions and powering Baidu’s advertising services.

Deep LearningGPUPaddleBox
0 likes · 15 min read
PaddleBox: A GPU‑Based Ultra‑Large‑Scale Sparse DNN Training Framework
Alimama Tech
Alimama Tech
Oct 26, 2022 · Artificial Intelligence

GPU Utilization Analysis and Optimization for Alibaba's Intelligent Creative Video Service

The paper analyzes why Alibaba Mama’s intelligent creative video service suffers low GPU utilization—due to Python GIL blocking, lack of kernel fusion, and serialized CUDA streams—and details service‑level changes (separate CPU/GPU processes, shared‑memory queues, priority scheduling) and operator‑level kernel‑fusion techniques (channels‑last layouts, custom pooling, TensorRT conversion) that raise utilization from ~30 % to near 100 % and boost throughput by 75 %.

Deep LearningGPU OptimizationPython
0 likes · 20 min read
GPU Utilization Analysis and Optimization for Alibaba's Intelligent Creative Video Service
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Oct 18, 2022 · Artificial Intelligence

Practical Implementation of Vision Transformer (ViT) for Image Classification in PyTorch

This article walks readers through building, training, and evaluating a Vision Transformer (ViT) model for a five‑class flower classification task, providing detailed code snippets, model architecture explanations, training script adjustments, and experimental results that highlight the importance of pre‑trained weights.

Deep LearningImage ClassificationPyTorch
0 likes · 13 min read
Practical Implementation of Vision Transformer (ViT) for Image Classification in PyTorch
Bilibili Tech
Bilibili Tech
Oct 18, 2022 · Artificial Intelligence

Real-Time Super-Resolution Algorithm for League of Legends S12 Live Streaming

A real‑time super‑resolution network specially designed for the League of Legends S12 live broadcast upscales 1080p streams to 4K at 75 fps by compressing parameters, employing pixel‑unshuffle/shuffle, structural re‑parameterization, and a multi‑loss (L1, perceptual, Sobel, GAN) training pipeline, delivering markedly sharper textures and lower latency for live game streaming.

Deep LearningLoss Functionsgame streaming
0 likes · 12 min read
Real-Time Super-Resolution Algorithm for League of Legends S12 Live Streaming
Ctrip Technology
Ctrip Technology
Oct 13, 2022 · Artificial Intelligence

Chinese New Word Discovery: From Traditional Unsupervised Methods to CNN‑Based Deep Learning

The article examines the challenge of out‑of‑vocabulary terms in Chinese e‑commerce NLP, reviews classic unsupervised metrics such as frequency, cohesion and neighbor entropy, and proposes a lightweight fully‑convolutional network inspired by image‑segmentation techniques to automatically detect new words.

CNNDeep LearningNLP
0 likes · 10 min read
Chinese New Word Discovery: From Traditional Unsupervised Methods to CNN‑Based Deep Learning
DataFunTalk
DataFunTalk
Oct 13, 2022 · Artificial Intelligence

Multimodal Attribute-Level Sentiment Analysis for Social Media: Background, Tasks, and Recent Advances

This article reviews the rapid development of multimodal attribute-level sentiment analysis on social media, outlining its background, defining four core sub‑tasks, summarizing representative recent models—including unified multimodal transformers, coarse‑to‑fine image‑target matching, and vision‑language pre‑training—and discussing experimental results and future research directions.

Deep LearningNLPaspect based sentiment
0 likes · 21 min read
Multimodal Attribute-Level Sentiment Analysis for Social Media: Background, Tasks, and Recent Advances
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Oct 12, 2022 · Artificial Intelligence

Unlock Vision AI: How EasyCV Streamlines Datasets and Model Training

This article introduces EasyCV, an open‑source all‑in‑one visual algorithm platform that abstracts diverse data sources, provides SOTA self‑supervised models, and offers ready‑to‑download datasets for image classification, object detection, segmentation, and pose estimation, complete with configuration examples.

Computer VisionDatasetsDeep Learning
0 likes · 9 min read
Unlock Vision AI: How EasyCV Streamlines Datasets and Model Training
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Oct 11, 2022 · Artificial Intelligence

GANomaly: Theory and Source Code Analysis

This article explains the GANomaly model for semi‑supervised anomaly detection, detailing its generator‑encoder‑discriminator architecture, loss functions, testing phase scoring, and provides annotated PyTorch source code to help readers implement and understand the approach.

Deep LearningEncoder-DecoderGAN
0 likes · 15 min read
GANomaly: Theory and Source Code Analysis
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Oct 8, 2022 · Artificial Intelligence

Wasserstein GAN (WGAN): Theory and Hands‑On Implementation

This article explains why traditional GANs suffer from training instability, introduces the Wasserstein (Earth‑Mover) distance as a smoother alternative, derives the WGAN objective, discusses Lipschitz constraints, and provides practical PyTorch code modifications to convert a vanilla GAN into a stable WGAN.

Deep LearningGANPyTorch
0 likes · 21 min read
Wasserstein GAN (WGAN): Theory and Hands‑On Implementation
AntTech
AntTech
Sep 27, 2022 · Artificial Intelligence

Ant Group’s Research Institute Publishes Four NeurIPS 2022 Papers on Advanced Computer Vision and AI

Ant Group’s Ant Technology Research Institute had four papers from its Visual Intelligence Lab accepted at NeurIPS 2022, covering rank diminishing in deep networks, geometry‑aware 3D image synthesis, dynamic discriminators for GANs, and uncertainty‑aware hierarchical refinement for incremental classification, highlighting the institute’s cutting‑edge AI research.

AI researchComputer VisionDeep Learning
0 likes · 8 min read
Ant Group’s Research Institute Publishes Four NeurIPS 2022 Papers on Advanced Computer Vision and AI
DataFunTalk
DataFunTalk
Sep 25, 2022 · Artificial Intelligence

Personalized News Recommendation System Based on Knowledge Graphs

This talk presents a personalized news recommendation system that leverages knowledge graphs to enhance recommendation accuracy, explainability, and user interest modeling, detailing background, graph construction methods, multi‑task deep learning architecture, experimental results, and future research directions.

Deep LearningGraph ConstructionKnowledge Graph
0 likes · 22 min read
Personalized News Recommendation System Based on Knowledge Graphs
Zhengtong Technical Team
Zhengtong Technical Team
Sep 22, 2022 · Artificial Intelligence

How YOLOv5 Powers Real‑Time City Management Video Analysis

This article explains the background, workflow, and technical details of using the YOLOv5 one‑stage object detection algorithm to enable fast, accurate video analytics for urban management, covering data augmentation, backbone design, FPN‑PAN neck, and prediction output processing.

AIComputer VisionDeep Learning
0 likes · 8 min read
How YOLOv5 Powers Real‑Time City Management Video Analysis
HomeTech
HomeTech
Sep 20, 2022 · Artificial Intelligence

Deep Learning for Image Classification: Classic Networks, Attention Mechanisms, and Their Application to Fine‑Grained Classification and Automotive Series Recognition

This article reviews the evolution of deep‑learning image‑classification networks, surveys attention mechanisms for fine‑grained tasks, describes the CVPR 2022 FGVC9 competition solution using RegNetY and random attention cropping, and discusses its deployment in automotive series recognition along with future challenges.

CVPRComputer VisionDeep Learning
0 likes · 19 min read
Deep Learning for Image Classification: Classic Networks, Attention Mechanisms, and Their Application to Fine‑Grained Classification and Automotive Series Recognition
Java Architect Essentials
Java Architect Essentials
Sep 18, 2022 · Industry Insights

Why AI Porn Detection Still Struggles: Key Challenges and the Need for Human Moderators

AI-powered porn detection leverages deep neural networks to classify images, but faces serious hurdles such as visual similarity with benign content, subjective standards of obscenity, and vulnerabilities stemming from training data, making human moderators indispensable for reliable content safety.

AI moderationContent SafetyDeep Learning
0 likes · 3 min read
Why AI Porn Detection Still Struggles: Key Challenges and the Need for Human Moderators
Programmer DD
Programmer DD
Sep 13, 2022 · Artificial Intelligence

Why AI Porn Detection Still Struggles: Key Challenges Explained

AI-based porn detection uses deep neural networks to classify images, but faces tough hurdles such as visual similarity with benign content, subjective standards for nudity, and vulnerabilities from training‑data dependence, meaning human moderators remain essential for reliable safety.

AI moderationComputer VisionContent Safety
0 likes · 3 min read
Why AI Porn Detection Still Struggles: Key Challenges Explained
DataFunTalk
DataFunTalk
Sep 13, 2022 · Artificial Intelligence

Intelligent Question Answering in QQ Browser Search: Background, Key Technologies, and Frontier Research

This article presents an in‑depth overview of intelligent question answering in QQ Browser search, covering its background, the core KBQA and DeepQA technologies, system architecture, challenges, recent advances such as end‑to‑end, knowledge‑guided and multimodal QA, and practical Q&A for deployment.

AIDeep LearningKnowledge Graph
0 likes · 22 min read
Intelligent Question Answering in QQ Browser Search: Background, Key Technologies, and Frontier Research
Huolala Tech
Huolala Tech
Sep 10, 2022 · Artificial Intelligence

How AI Transforms Freight Safety: Real‑Time Risk Detection and Intervention

This article explains how AI technologies enable end‑to‑end freight safety monitoring, from pre‑trip and in‑trip risk identification to targeted interventions and governance, addressing challenges such as long‑tail data, small‑sample learning, fine‑grained classification, and multi‑level filtering.

AIDeep LearningLogistics
0 likes · 12 min read
How AI Transforms Freight Safety: Real‑Time Risk Detection and Intervention
DataFunSummit
DataFunSummit
Sep 9, 2022 · Artificial Intelligence

Wuliang: Tencent's Deep Learning Framework for Real‑Time Large‑Scale Recommendation

The presentation by Tencent expert Yuan Yi details the Wuliang deep learning system for recommendation, covering its background, technical challenges such as massive data and real‑time requirements, the parameter‑server based solutions for training and inference, model compression techniques, and continuous online deployment strategies.

Deep LearningLarge-Scale TrainingParameter Server
0 likes · 14 min read
Wuliang: Tencent's Deep Learning Framework for Real‑Time Large‑Scale Recommendation
Bilibili Tech
Bilibili Tech
Sep 9, 2022 · Artificial Intelligence

Visual Lossless Deep Learning Pre‑processing for Video Transcoding Using DCT‑Based Low‑Rank Loss and a Lightweight Model

A visual‑lossless deep‑learning pre‑processor that employs a DCT‑based low‑rank loss and an ultra‑lightweight CPU‑friendly model achieves up to 20% bitrate reduction for 1080p videos while preserving high‑frequency details, enabling real‑time transcoding and bandwidth savings for popular content on Bilibili.

AIDCTDeep Learning
0 likes · 11 min read
Visual Lossless Deep Learning Pre‑processing for Video Transcoding Using DCT‑Based Low‑Rank Loss and a Lightweight Model
DataFunSummit
DataFunSummit
Sep 4, 2022 · Artificial Intelligence

Sparse Features in Machine Learning: Challenges, NVIDIA Ampere Structured Sparsity, Knowledge Distillation, and GAN Model Compression

This talk explores the challenges and opportunities of leveraging sparsity in machine learning models, covering fine‑grained and coarse‑grained sparsity, NVIDIA Ampere’s 2:4 structured sparsity, knowledge‑distillation techniques for converting unstructured to structured sparsity, and model compression strategies for generative adversarial networks.

Deep LearningGANGPU Acceleration
0 likes · 14 min read
Sparse Features in Machine Learning: Challenges, NVIDIA Ampere Structured Sparsity, Knowledge Distillation, and GAN Model Compression
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Sep 1, 2022 · Artificial Intelligence

How Uni‑Fold + Alibaba PAI Boost Protein Structure Prediction to 6.6k Amino Acids

DeepMind’s AlphaFold inspired Uni‑Fold, now accelerated with Alibaba Cloud’s PAI platform, can predict protein structures up to 6.6k amino acids—covering 99.992% of known sequences—delivering ten‑minute inference for SARS‑CoV‑2 spike trimers and setting new performance benchmarks for AI‑driven structural biology.

AI accelerationAlibaba PAIDeep Learning
0 likes · 7 min read
How Uni‑Fold + Alibaba PAI Boost Protein Structure Prediction to 6.6k Amino Acids
ByteDance Terminal Technology
ByteDance Terminal Technology
Sep 1, 2022 · Artificial Intelligence

Hybrid Computer Vision and Deep Learning for Automated UI Background Color Extraction and Assertion

This article presents a hybrid pipeline combining traditional computer vision techniques and deep learning models to automatically extract and verify text background colors in UI automation screenshots, effectively addressing challenges like limited training data and complex borders to significantly reduce manual inspection costs while achieving high accuracy and robustness in production environments.

Automated TestingComputer VisionDeep Learning
0 likes · 10 min read
Hybrid Computer Vision and Deep Learning for Automated UI Background Color Extraction and Assertion
iQIYI Technical Product Team
iQIYI Technical Product Team
Aug 26, 2022 · Industry Insights

How iQ Dubbing Cuts Film Dubbing Time by Over 3× Using Deep‑Learning AI

iQ Dubbing, iQIYI’s AI‑driven dubbing platform, leverages deep‑learning models to automate voice‑over, international voice extraction, and sound‑effect creation, reducing dubbing turnaround from months to under a week and boosting efficiency more than threefold, as recognized by the 2022 ChinaMM Innovation Product award.

AI dubbingDeep Learningindustry insight
0 likes · 4 min read
How iQ Dubbing Cuts Film Dubbing Time by Over 3× Using Deep‑Learning AI
DataFunSummit
DataFunSummit
Aug 23, 2022 · Artificial Intelligence

Graph Deep Learning for Content Risk Control and APT Detection

This article presents a comprehensive overview of Tencent AI Lab's graph‑based approaches for detecting misinformation and advanced persistent threats, detailing the challenges of modeling news content and social context, the design of the Post‑User Interaction Network (PSIN), experimental results on large multi‑topic datasets, and a novel graph‑pretraining pipeline for APT detection.

APT detectionDeep LearningSocial Network Analysis
0 likes · 12 min read
Graph Deep Learning for Content Risk Control and APT Detection
Tencent Cloud Developer
Tencent Cloud Developer
Aug 23, 2022 · Artificial Intelligence

Brain-Computer Interface Competition Showcases AI-Powered Mind-Controlled Technology

The Tencent Cloud‑backed “Tencent Cloud Cup” BCI competition, part of the World Robot Contest, drew over 250 teams from 26 provinces and three countries to tackle brain‑computer tasks like spelling and emotion detection, demonstrating typing, wheelchair and robotic arm applications, with the winning Chinese university team typing 81 characters in 285 seconds and results set for 5G deployment and publication in Brain Science Advances.

AI competitionDeep LearningHuman-Computer Interaction
0 likes · 8 min read
Brain-Computer Interface Competition Showcases AI-Powered Mind-Controlled Technology
DaTaobao Tech
DaTaobao Tech
Aug 19, 2022 · Artificial Intelligence

SepLUT: Separable Lookup Tables for Real-time Image Enhancement

SepLUT, a new separable lookup‑table framework, splits color enhancement into a 1‑D LUT for independent adjustments and a 3‑D LUT for correlated changes, predicted by a lightweight CNN, enabling quantizable, real‑time ISP performance with state‑of‑the‑art results on the FiveK benchmark.

Computer VisionDeep LearningReal-Time
0 likes · 12 min read
SepLUT: Separable Lookup Tables for Real-time Image Enhancement
Hulu Beijing
Hulu Beijing
Aug 19, 2022 · Artificial Intelligence

Disney’s M5 Model: Multi‑Modal, Multi‑Interest, Multi‑Scenario Boost for Streaming Recommendations

Disney’s Content Discovery team introduces M5, a multi‑modal, multi‑interest, multi‑scenario recall model that enhances VOD and live streaming recommendations by leveraging rich metadata, user behavior, and contextual features, outperforming baseline methods with significant hit‑ratio gains across Hulu and Disney+.

Deep LearningM5 modelRecommendation Systems
0 likes · 22 min read
Disney’s M5 Model: Multi‑Modal, Multi‑Interest, Multi‑Scenario Boost for Streaming Recommendations
FunTester
FunTester
Aug 18, 2022 · Artificial Intelligence

How AI Can Automate UI Testing: Building Image‑Based Anomaly Detection

This article examines the evolution of mobile UI testing toward AI‑driven approaches, outlines the challenges of large‑scale apps, and details a practical workflow for constructing image‑based anomaly datasets, training a ResNet‑18 model, and iterating on detection performance.

AI testingComputer VisionDeep Learning
0 likes · 13 min read
How AI Can Automate UI Testing: Building Image‑Based Anomaly Detection
Model Perspective
Model Perspective
Aug 15, 2022 · Artificial Intelligence

Understanding Recurrent Neural Networks: From Vanilla RNN to LSTM with Keras

This article introduces recurrent neural networks (RNNs) and their ability to handle sequential data, explains the limitations of vanilla RNNs, presents the LSTM architecture with its gates, and provides complete Keras code for data loading, model building, and training both vanilla RNN and LSTM models.

Deep LearningKerasLSTM
0 likes · 5 min read
Understanding Recurrent Neural Networks: From Vanilla RNN to LSTM with Keras
JD Cloud Developers
JD Cloud Developers
Aug 15, 2022 · Artificial Intelligence

How FCA Doubles BERT’s Inference Speed with Less Than 1% Accuracy Loss

This article explains how the Fine‑ and Coarse‑Granularity Hybrid Self‑Attention (FCA) mechanism reduces BERT’s computational cost by over 50% while keeping accuracy loss under 1%, detailing the method, experimental results, and its significance for efficient large‑scale language models.

BERTDeep LearningFCA
0 likes · 8 min read
How FCA Doubles BERT’s Inference Speed with Less Than 1% Accuracy Loss
Model Perspective
Model Perspective
Aug 6, 2022 · Artificial Intelligence

Understanding Activation Functions in Artificial Neural Networks

This article introduces artificial neural networks, explains the role of artificial neurons and their weighted connections, and provides an overview of common activation functions—including linear, nonlinear ramp, threshold/step, and sigmoid forms—highlighting their characteristics and typical saturation values.

Deep Learningactivation functionartificial neural network
0 likes · 2 min read
Understanding Activation Functions in Artificial Neural Networks
Model Perspective
Model Perspective
Aug 3, 2022 · Artificial Intelligence

Explore the Most Popular Machine Learning Algorithms: A Comprehensive Guide

This article provides a thorough overview of the most widely used machine learning algorithms, classifying them by learning style and problem type, and highlighting popular methods such as supervised, unsupervised, semi‑supervised, regression, instance‑based, regularization, decision‑tree, Bayesian, clustering, association rule, neural network, deep learning, dimensionality‑reduction, and ensemble techniques.

AlgorithmsDeep LearningUnsupervised Learning
0 likes · 10 min read
Explore the Most Popular Machine Learning Algorithms: A Comprehensive Guide
Huawei Cloud Developer Alliance
Huawei Cloud Developer Alliance
Aug 3, 2022 · Artificial Intelligence

Unlock AI-Powered Makeup Transfer: Copy Any Look to Your Photo in Three Steps

This article introduces an AI-powered makeup transfer technique that copies makeup from any reference image onto a user's photo, explains its advantages over traditional sticker-based apps, outlines a three‑step workflow, and provides sample Python code runnable on Huawei Cloud ModelArts.

AI makeup transferDeep LearningHuawei Cloud
0 likes · 4 min read
Unlock AI-Powered Makeup Transfer: Copy Any Look to Your Photo in Three Steps
Zuoyebang Tech Team
Zuoyebang Tech Team
Jul 29, 2022 · Artificial Intelligence

Boosting Chinese‑English Code‑Switching Speech Recognition with Language ID and LM Enhancements

This report details a series of experiments on Chinese‑English mixed‑language speech recognition, introducing language‑identification loss and language‑model integration to improve acoustic modeling, reduce mixed error rates, and achieve significant gains over a baseline end‑to‑end ASR system.

Code-SwitchingDeep Learninglanguage identification
0 likes · 16 min read
Boosting Chinese‑English Code‑Switching Speech Recognition with Language ID and LM Enhancements
GuanYuan Data Tech Team
GuanYuan Data Tech Team
Jul 28, 2022 · Artificial Intelligence

Unlocking Reinforcement Learning: Core Concepts, Algorithms, and Real‑World Applications

This article introduces reinforcement learning by defining agents, environments, rewards, and policies, explains key concepts such as Markov Decision Processes and Bellman equations, and surveys major algorithms—including dynamic programming, Monte‑Carlo, TD learning, policy gradients, Q‑learning, DQN, and evolution strategies—while highlighting practical challenges and notable case studies like AlphaGo Zero.

Deep LearningEvolution StrategiesMDP
0 likes · 27 min read
Unlocking Reinforcement Learning: Core Concepts, Algorithms, and Real‑World Applications
ITPUB
ITPUB
Jul 21, 2022 · Artificial Intelligence

From Blur to Brilliance: How AI‑Powered Image Quality Assessment Transformed 58.com’s Recruitment Images

This article reviews image quality assessment fundamentals, modern CNN‑based IQA models, and their deployment at 58.com to automatically score, filter, and rank millions of recruitment photos, achieving a drop in low‑quality images from 9% to zero while boosting overall accuracy to 94.7%.

Business ApplicationCNNComputer Vision
0 likes · 19 min read
From Blur to Brilliance: How AI‑Powered Image Quality Assessment Transformed 58.com’s Recruitment Images
JD Tech
JD Tech
Jul 21, 2022 · Artificial Intelligence

Improving JD Retail Recommendation Advertising Ranking with Variational Feature Learning, User Interest Network Optimization, and Global Collaborative Modeling

This article presents JD's comprehensive technical solution for boosting recommendation ad ranking by addressing cold‑start, shallow user interest extraction, and insufficient global data through a variational feature learning framework, enhanced user‑interest networks, and full‑domain collaborative modeling, achieving over 1% AUC gain and notable revenue growth.

CTR predictionDeep Learninge‑commerce
0 likes · 21 min read
Improving JD Retail Recommendation Advertising Ranking with Variational Feature Learning, User Interest Network Optimization, and Global Collaborative Modeling
Huawei Cloud Developer Alliance
Huawei Cloud Developer Alliance
Jul 20, 2022 · Artificial Intelligence

AI Boosts Ship‑Sea Target Detection: Lessons from the First Innovation Competition

The inaugural Ship‑Sea Data Intelligent Application Innovation Competition, co‑hosted by Taihu Laboratory, Huawei and Wuxi authorities, showcased cutting‑edge AI techniques—such as multi‑scale training, TTA, knowledge distillation, and model pruning—to improve surface and underwater target detection for vessels, nets, buoys, and marine life, while offering transparent rankings, research funding, and a platform for advancing maritime AI.

AIDeep LearningMaritime
0 likes · 7 min read
AI Boosts Ship‑Sea Target Detection: Lessons from the First Innovation Competition
NetEase Smart Enterprise Tech+
NetEase Smart Enterprise Tech+
Jul 19, 2022 · Artificial Intelligence

How NER Dominated NLPCC 2022: Techniques Behind the Winning Model

This article reviews the recent NLPCC 2022 NER competition, explains the evolution of named entity recognition, details the five major modeling paradigms, and describes the winning team’s relation‑classification approach, data‑augmentation strategy, experimental results, and its practical deployment in NetEase Cloud Commerce services.

Deep LearningNLPRelation Classification
0 likes · 13 min read
How NER Dominated NLPCC 2022: Techniques Behind the Winning Model
JD Tech
JD Tech
Jul 18, 2022 · Artificial Intelligence

AI-Powered Visual Defect Detection for Mobile App UI Testing: Methodology, Data Construction, Model Training, and Evaluation

This article presents an end‑to‑end AI‑driven visual testing solution for mobile applications, detailing the business pain points, data set construction, CNN‑based model design, training procedures, performance evaluation with ROC and confusion matrices, and future directions for improving defect detection accuracy.

Computer VisionDeep LearningImage Classification
0 likes · 14 min read
AI-Powered Visual Defect Detection for Mobile App UI Testing: Methodology, Data Construction, Model Training, and Evaluation
DaTaobao Tech
DaTaobao Tech
Jul 13, 2022 · Artificial Intelligence

MNN 2.0: A Unified Edge‑Cloud Deep Learning Framework Overview

MNN 2.0 transforms Alibaba’s lightweight deep‑learning engine into a unified edge‑cloud framework, delivering ultra‑small binaries, broad model‑format support, and aggressive CPU/GPU/DSP/NPU optimizations—including SIMD, Winograd, quantization, and sparse computation—while providing Python‑style APIs for preprocessing, inference, and on‑device training.

Deep LearningEdge ComputingMNN
0 likes · 18 min read
MNN 2.0: A Unified Edge‑Cloud Deep Learning Framework Overview
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Jul 12, 2022 · Artificial Intelligence

How Whale Enables Efficient Giant Model Training on Heterogeneous GPUs

The article introduces Whale, an open‑source distributed training framework that unifies multiple parallelism strategies, uses hardware‑aware load balancing to accelerate giant models like BERT‑Large and the trillion‑parameter M6 on heterogeneous GPU clusters, and details its architecture, planning, and real‑world performance gains.

Deep LearningParallelismhardware-aware scheduling
0 likes · 11 min read
How Whale Enables Efficient Giant Model Training on Heterogeneous GPUs
DataFunTalk
DataFunTalk
Jul 9, 2022 · Artificial Intelligence

User Behavior Sequence Based Transaction Anti‑Fraud Detection

This presentation explains how leveraging user behavior sequences with supervised and unsupervised deep learning models, including end‑to‑end and two‑stage architectures, improves transaction fraud detection by identifying distinct patterns of account takeover and stolen‑card activities and outlines the engineering deployment pipeline.

Deep LearningEmbeddingfraud detection
0 likes · 12 min read
User Behavior Sequence Based Transaction Anti‑Fraud Detection
Meituan Technology Team
Meituan Technology Team
Jul 6, 2022 · Artificial Intelligence

Engineering Practices for Large-Scale Deep Learning Models in Meituan Takeaway Advertising

The article details Meituan's engineering journey from small DNNs to hundred‑gigabyte deep learning models for food‑delivery ads, analyzing online latency and offline efficiency challenges and presenting distributed storage, CPU/GPU acceleration, OpenVINO, TensorRT, CodeGen, and data‑pipeline optimizations that dramatically improve throughput, memory usage, and sample‑building speed.

CPU accelerationDeep LearningGPU Acceleration
0 likes · 45 min read
Engineering Practices for Large-Scale Deep Learning Models in Meituan Takeaway Advertising
Alimama Tech
Alimama Tech
Jul 6, 2022 · Artificial Intelligence

How Mixed‑Curvature Graph Embeddings Boost E‑commerce Ad Retrieval

This article presents AMCAD, an adaptive mixed‑curvature graph embedding system that models heterogeneous e‑commerce search ad graphs in non‑Euclidean spaces, detailing its sample construction, three‑stage model architecture, offline and online experiments, and demonstrating significant performance gains over Euclidean baselines.

Deep Learningadvertisement retrievale‑commerce
0 likes · 13 min read
How Mixed‑Curvature Graph Embeddings Boost E‑commerce Ad Retrieval
Bilibili Tech
Bilibili Tech
Jul 1, 2022 · Artificial Intelligence

Quality‑Controlled Scene‑Adaptive Video Transcoding System at Bilibili

Bilibili’s quality‑controlled scene‑adaptive transcoding system automatically splits videos into shot‑level segments, predicts optimal encoding parameters with a deep‑learning model, applies two‑pass VMAF‑targeted encoding and ROI‑aware bitrate allocation, achieving stable visual quality, 99% accuracy, and roughly 15% bitrate reduction.

Deep LearningROI encodingVMAF
0 likes · 25 min read
Quality‑Controlled Scene‑Adaptive Video Transcoding System at Bilibili
360 Quality & Efficiency
360 Quality & Efficiency
Jul 1, 2022 · Artificial Intelligence

Building an End-to-End Image Search System with Milvus and VGG

This article presents a complete image‑search solution that extracts visual features with the VGG16 model, stores them in the Milvus vector database, and provides a set of web APIs for training, querying, counting, searching, and deleting image vectors, all deployed via Docker containers.

AIDeep LearningMilvus
0 likes · 7 min read
Building an End-to-End Image Search System with Milvus and VGG
AntTech
AntTech
Jun 24, 2022 · Artificial Intelligence

Hierarchical Residual Network for Multi‑Granularity Classification (HRN) – CVPR 2022 Paper Overview

This article presents a CVPR 2022 paper by Zhejiang University and Ant Group that introduces a label‑relation‑tree‑based Hierarchical Residual Network (HRN) for improving multi‑granularity image classification, detailing its motivation, architecture, composite loss design, extensive experiments on fine‑grained datasets, and practical impact on content‑security applications.

CVPR2022Computer VisionDeep Learning
0 likes · 12 min read
Hierarchical Residual Network for Multi‑Granularity Classification (HRN) – CVPR 2022 Paper Overview