Tagged articles

41 articles

Page 1 of 1

Feb 5, 2026 · Artificial Intelligence

Scanning 100 Million Hubble Images in 3 Days: ESA’s AnomalyMatch Finds Over 1,000 Rare Objects

ESA’s ESAC team introduced AnomalyMatch, a semi‑supervised active‑learning framework that, with fewer than ten labeled anomalies, processed roughly 100 million Hubble cutouts in just 2–3 days, uncovering 1,339 distinct anomalous astrophysical objects such as merging galaxies, gravitational lenses, and jellyfish galaxies.

AnomalyMatchEfficientNetHubble Legacy Archive

0 likes · 16 min read

Scanning 100 Million Hubble Images in 3 Days: ESA’s AnomalyMatch Finds Over 1,000 Rare Objects

JD Tech

Dec 30, 2025 · Artificial Intelligence

How a Semi‑Supervised Unified Framework Boosts E‑commerce Query Intent Classification

The paper introduces a semi‑supervised, extensible unified framework (SSUF) that integrates knowledge, label, and structural enhancements to overcome data sparsity, label bias, and fragmented sub‑tasks in e‑commerce query intent prediction, achieving superior offline and online performance.

BERTGCNSemi-supervised Learning

0 likes · 14 min read

How a Semi‑Supervised Unified Framework Boosts E‑commerce Query Intent Classification

AntTech

Jul 11, 2024 · Information Security

Enhancing Fraud Transaction Detection via Unlabeled Suspicious Records (GIANTESS Framework)

The paper presents GIANTESS, a novel semi‑supervised fraud detection framework that leverages online‑identified suspicious transactions to augment the feature space, generating pseudo‑labels for out‑of‑distribution samples and employing a hybrid loss to improve detection of covert fraudulent activities, achieving notable recall gains on real‑world datasets.

GIANTESSSemi-supervised Learningmachine learning

0 likes · 6 min read

Enhancing Fraud Transaction Detection via Unlabeled Suspicious Records (GIANTESS Framework)

Meituan Technology Team

Jun 13, 2024 · Artificial Intelligence

Overview of Meituan's Selected CVPR 2024 Papers and Online Sharing Event

Meituan's tech team highlights seven CVPR 2024 papers—spanning OCR pre‑training, long‑tail semi‑supervised learning, visual AIGC, audio‑visual segmentation and synthetic‑data detection—provides detailed abstracts and experimental results, and announces an online author‑talk session on June 27.

Audio-Visual SegmentationCVPR 2024Computer Vision

0 likes · 18 min read

Overview of Meituan's Selected CVPR 2024 Papers and Online Sharing Event

NetEase Smart Enterprise Tech+

Mar 12, 2024 · Artificial Intelligence

How Advanced Video AI Transforms Content Moderation and Retrieval

This article explores how modern video AI techniques—ranging from transformer‑based classification to semi‑supervised retrieval and token‑halting acceleration—enable efficient, accurate detection of prohibited content and fast, scalable video search in the era of short‑form media.

AI moderationSemi-supervised LearningTransformer

0 likes · 18 min read

How Advanced Video AI Transforms Content Moderation and Retrieval

HomeTech

Jul 7, 2023 · Artificial Intelligence

Multi-Modal Video Understanding and AIGC Video Generation at Autohome

This article presents a comprehensive multi-modal video understanding system for AIGC video generation, detailing technical architecture, GCN-based semi-supervised learning, and practical applications across automotive content scenarios.

AIGCBERTNeXtVLAD

0 likes · 8 min read

Multi-Modal Video Understanding and AIGC Video Generation at Autohome

Baidu Tech Salon

Apr 7, 2023 · Artificial Intelligence

Ambiguity-Resistant Semi-supervised Learning (ARSL) for Single-stage Object Detection

ARSL, an ambiguity‑resistant semi‑supervised learning framework for single‑stage object detection, introduces Joint‑Confidence Estimation and Task‑Separation Assignment to resolve selection and assignment ambiguities in pseudo‑labels, thereby markedly improving pseudo‑label quality and achieving state‑of‑the‑art AP gains on COCO benchmarks.

ARSLComputer VisionSemi-supervised Learning

0 likes · 8 min read

Ambiguity-Resistant Semi-supervised Learning (ARSL) for Single-stage Object Detection

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

DataFunSummit

Dec 23, 2022 · Artificial Intelligence

Data‑Centric AI Practices for Content Moderation at NetEase Yidun

The article presents NetEase Yidun’s data‑centric AI approach to content moderation, covering the background of Data‑Centric AI, the specific business and data challenges of content safety, comprehensive data pipelines—including collection, labeling, augmentation, selection, cleaning, iteration and testing—and the role of self‑, semi‑ and weak‑supervised learning in enhancing algorithm performance.

Algorithm InnovationData ManagementData‑Centric AI

0 likes · 19 min read

Data‑Centric AI Practices for Content Moderation at NetEase Yidun

AntTech

Dec 19, 2022 · Artificial Intelligence

TransVCL: Attention‑Enhanced Video Copy Localization Network with Flexible Supervision

TransVCL introduces an end‑to‑end attention‑enhanced video copy localization network that leverages a custom Transformer, correlation‑Softmax similarity matrix, and temporal alignment module, combined with a semi‑supervised learning framework, achieving state‑of‑the‑art performance on VCSL and VCDB benchmarks.

AISemi-supervised LearningTransformer

0 likes · 13 min read

TransVCL: Attention‑Enhanced Video Copy Localization Network with Flexible Supervision

NetEase Smart Enterprise Tech+

Dec 8, 2022 · Artificial Intelligence

How NetEase Optimizes AI for Digital Content Risk Control and Cost Efficiency

At QCon 2022, NetEase’s AI experts detailed their end‑to‑end approach for digital content risk control, covering data acquisition, semi‑supervised training, dynamic inference, cost‑effective deployment, and future directions, highlighting how AI can boost efficiency while managing escalating operational expenses.

AICost OptimizationSemi-supervised Learning

0 likes · 26 min read

How NetEase Optimizes AI for Digital Content Risk Control and Cost Efficiency

AntTech

Nov 6, 2022 · Artificial Intelligence

Advanced Rule Learning, Constraint‑Adaptive Frameworks, and Semi‑Supervised Data Augmentation for Fraud Detection and Imbalanced Ranking

This article surveys recent Ant Group research on explainable fraud detection, including constraint‑adaptive rule‑set learning (CRSL), meta‑path guided rule generation (MetaRule), biased sampling for imbalanced ranking, and a semi‑supervised data‑augmentation framework (SDAT) for tabular data, highlighting their motivations, methodologies, deployments, and experimental results.

Semi-supervised Learningconstraint adaptivedata augmentation

0 likes · 18 min read

Advanced Rule Learning, Constraint‑Adaptive Frameworks, and Semi‑Supervised Data Augmentation for Fraud Detection and Imbalanced Ranking

DataFunTalk

Oct 30, 2022 · Artificial Intelligence

SPACE and Proton: Semi‑Supervised Knowledge Injection and Probing‑Tuning for Pretrained Conversational AI Models

This article reviews Alibaba DAMO‑ConvAI’s work on large‑scale conversational AI, comparing pretrained language and dialogue models, introducing the SPACE semi‑supervised knowledge‑injection framework and the Proton probing‑tuning method for extracting and applying model knowledge to downstream tasks.

Pretrained Dialogue ModelProbing TuningSemi-supervised Learning

0 likes · 21 min read

SPACE and Proton: Semi‑Supervised Knowledge Injection and Probing‑Tuning for Pretrained Conversational AI Models

58 Tech

Sep 29, 2022 · Artificial Intelligence

End-to-End Speech Recognition Optimization and Deployment at 58.com

58.com’s AI Lab presents a comprehensive overview of its end‑to‑end speech recognition system, detailing data collection, semi‑supervised training, Efficient Conformer architecture, model compression, and deployment strategies that together achieve high accuracy across diverse acoustic conditions and large‑scale production workloads.

AIDeploymentEfficient Conformer

0 likes · 19 min read

End-to-End Speech Recognition Optimization and Deployment at 58.com

HomeTech

Sep 8, 2022 · Artificial Intelligence

Concept Tag Mining for Recommendation Systems: Methods, Challenges, and Solutions

This article presents a comprehensive overview of concept tag mining for recommendation systems, describing unsupervised pattern‑matching, semi‑supervised AutoPhase, and supervised NER approaches, analyzing their advantages and drawbacks, and offering practical solutions to tag duplication and quality issues.

NERNLPSemi-supervised Learning

0 likes · 11 min read

Concept Tag Mining for Recommendation Systems: Methods, Challenges, and Solutions

Code DAO

May 19, 2022 · Artificial Intelligence

Semi‑Supervised Training Methods for Transformers

This article explains an end‑to‑end semi‑supervised training pipeline for Transformer‑based NLP models, detailing the unsupervised language‑model pre‑training, supervised fine‑tuning, and the internal architecture of embeddings, encoder layers, and downstream tasks such as text classification and NER.

BERTFine-tuningMasked Language Model

0 likes · 9 min read

Semi‑Supervised Training Methods for Transformers

Code DAO

Apr 22, 2022 · Artificial Intelligence

Review: Semi‑Supervised Learning with Ladder Networks and Virtual Adversarial Training (VAT)

This article reviews Ladder Networks and the Γ‑Model for semi‑supervised learning, explains how they minimize supervised and unsupervised costs, presents experimental results on MNIST, CIFAR‑10 and SVHN, and details the Virtual Adversarial Training method with TensorFlow code.

CIFAR-10Ladder NetworksMNIST

0 likes · 9 min read

Review: Semi‑Supervised Learning with Ladder Networks and Virtual Adversarial Training (VAT)

DataFunSummit

Apr 17, 2022 · Artificial Intelligence

Precise Marketing Algorithms and Practices at Hello Mobility

This article presents Hello Mobility’s precise marketing system, covering its business background, value, framework, algorithmic capabilities such as Pu‑Learning LookAlike modeling, TSA semi‑supervised learning, and Graph Embedding, as well as identified pain points, project impact, and future directions for scaling and automation.

AISemi-supervised Learninggraph embedding

0 likes · 12 min read

Precise Marketing Algorithms and Practices at Hello Mobility

Baobao Algorithm Notes

Mar 15, 2022 · Artificial Intelligence

Boost Model Performance with Only 5 Lines of Pseudo‑Label Code

This article explains how semi‑supervised pseudo‑label learning can dramatically improve model accuracy by using a tiny five‑line code snippet that generates pseudo‑labels for unlabeled data, retrains a second model, and avoids data leakage with a proper validation set.

AISemi-supervised Learningdata labeling

0 likes · 4 min read

Boost Model Performance with Only 5 Lines of Pseudo‑Label Code

Beike Product & Technology

Jan 7, 2022 · Artificial Intelligence

Beike Real Estate NLP Team Wins First Place in CCIR Cup 2021 Intelligent Human‑Computer Interaction Track

The Beike Real Estate NLP team secured first place in the CCIR Cup 2021 Intelligent Human‑Computer Interaction track by applying semi‑supervised and transfer learning techniques to small‑sample intent recognition and slot filling, and also presented the large‑scale Mandarin dialect speech benchmark KeSpeech at NeurIPS 2021.

AI competitionBERTNLP

0 likes · 5 min read

Beike Real Estate NLP Team Wins First Place in CCIR Cup 2021 Intelligent Human‑Computer Interaction Track

NetEase Smart Enterprise Tech+

Sep 2, 2021 · Artificial Intelligence

How AI Detects Video Deepfakes: Techniques, Challenges, and Real-World Solutions

This article explores the rapid rise of AI‑generated video deepfakes, examines the four main manipulation techniques, discusses the inherent security risks, and presents NetEase Yidun’s comprehensive detection framework—including face‑detection‑based classification, semi‑supervised learning, feature fusion, and model distillation—to combat content‑security threats.

AI securityComputer VisionSemi-supervised Learning

0 likes · 12 min read

How AI Detects Video Deepfakes: Techniques, Challenges, and Real-World Solutions

Meituan Technology Team

Aug 19, 2021 · Artificial Intelligence

Few-Shot Learning Methods and Applications in Meituan NLP

Meituan’s NLP team leverages few‑shot learning—using data‑augmentation, semi‑supervised, ensemble/self‑training, and domain‑adaptation techniques—to cut annotation costs, achieving 1–2 percentage‑point accuracy gains on internal benchmarks and deploying high‑performing models for tasks such as topic classification, fake‑review detection, and sentiment analysis, while planning broader platform and model extensions.

Few‑Shot LearningNLPSemi-supervised Learning

0 likes · 29 min read

Few-Shot Learning Methods and Applications in Meituan NLP

DataFunTalk

Aug 13, 2021 · Artificial Intelligence

Predictions for Speech Recognition Technology Over the Next Decade: Research and Application Directions

The article, authored by a former Stanford PhD now at Zoom, forecasts that by 2030 speech recognition will rely heavily on semi‑supervised learning, on‑device models, richer representations, and personalization, while applications such as transcription services and voice assistants will evolve modestly.

AIFuture TrendsSemi-supervised Learning

0 likes · 7 min read

Predictions for Speech Recognition Technology Over the Next Decade: Research and Application Directions

DataFunTalk

May 9, 2021 · Artificial Intelligence

Few-Shot Learning, Data Augmentation, and Multi‑Task Learning for Safety Modeling in Ride‑Hailing Platforms

This article presents Didi's exploration of few‑shot learning, data‑augmentation, semi‑supervised self‑training and multi‑task learning techniques to address the scarcity of labeled samples in safety and governance scenarios, demonstrating practical solutions and performance gains across various risk‑detection tasks.

AIFew‑Shot LearningSemi-supervised Learning

0 likes · 15 min read

Few-Shot Learning, Data Augmentation, and Multi‑Task Learning for Safety Modeling in Ride‑Hailing Platforms

Didi Tech

Apr 20, 2021 · Artificial Intelligence

Few-Shot Learning, Data Augmentation, and Semi‑Supervised Methods for Improving Safety and Governance Models at Didi

To overcome scarce labeled data for safety and governance, Didi combines few‑shot learning with systematic data augmentation, self‑training semi‑supervised labeling, and multi‑task neural architectures, cutting labeling costs and reducing log‑loss by over 20% while boosting ROC‑AUC and PR‑AUC across harassment detection, expense‑complaint, and route‑intercept use cases.

AI SafetyDidiFew‑Shot Learning

0 likes · 15 min read

Few-Shot Learning, Data Augmentation, and Semi‑Supervised Methods for Improving Safety and Governance Models at Didi

Youku Technology

Apr 8, 2021 · Artificial Intelligence

Champion Solution of Media AI Alibaba Entertainment Video Object Segmentation Challenge

The Youku AI team won the Media AI Alibaba Entertainment Video Object Segmentation Challenge by enhancing the STM model with a spatial‑constrained memory reader, ASPP‑HRNet refinement, ResNeSt‑101 backbone, and a multi‑stage training pipeline, while also devising an unsupervised framework that combines DetectoRS detection, HRNet mask refinement, STM‑based association, and key‑frame optimization to achieve 95.5% test score on a large, richly annotated video dataset.

Computer VisionDeep LearningSemi-supervised Learning

0 likes · 13 min read

Champion Solution of Media AI Alibaba Entertainment Video Object Segmentation Challenge

JD Cloud Developers

Jan 11, 2021 · Artificial Intelligence

Top Tech News: R2DBC for Java, 4600‑km Quantum Network, AI Papers & More

This weekly roundup highlights MariaDB’s new R2DBC connector for Java, China’s 4600‑km quantum communication network, JD’s 16 AAAI‑2021 papers, Intel’s RealSense ID facial recognition, JupyterLab 3.0 release, JD’s Smart Community 2.0, the OpenViDial multimodal dialogue dataset, and the FixMatch semi‑supervised learning breakthrough.

JupyterLabQuantum CommunicationR2DBC

0 likes · 8 min read

Top Tech News: R2DBC for Java, 4600‑km Quantum Network, AI Papers & More

JD Tech Talk

Dec 3, 2020 · Artificial Intelligence

Graph Algorithms and Graph Neural Networks for Fraud Detection

The article explains how building account relationship graphs and applying both traditional graph algorithms and modern graph neural networks—through community detection, anomaly detection, semi‑supervised and unsupervised learning, and dynamic graph techniques—can effectively identify and dismantle fraud groups in online services.

AISemi-supervised Learningdynamic graphs

0 likes · 11 min read

Graph Algorithms and Graph Neural Networks for Fraud Detection

Didi Tech

Nov 5, 2020 · Artificial Intelligence

Self-Learning Platform for Speech Recognition Model Optimization at DiDi

DiDi’s self‑learning ASR platform lets non‑technical users upload business data, automatically train, test and deploy models with semi‑supervised learning, hot‑word updates and LSTM rescoring, creating a closed‑loop pipeline that boosted vehicle voice‑interaction accuracy from around 80 % to over 95 % within months.

AILanguage ModelSemi-supervised Learning

0 likes · 14 min read

Self-Learning Platform for Speech Recognition Model Optimization at DiDi

DataFunTalk

Jun 28, 2020 · Artificial Intelligence

Applying UDA Semi‑Supervised Learning to Financial Text Classification: Experiments and Insights

This article investigates the practical performance of Google’s 2019 Unsupervised Data Augmentation (UDA) framework on real‑world financial text classification tasks, detailing experiments with limited labeled data, domain‑out‑of‑distribution samples, noisy labels, and comparisons between BERT and lightweight TextCNN models.

BERTSemi-supervised LearningTextCNN

0 likes · 21 min read

Applying UDA Semi‑Supervised Learning to Financial Text Classification: Experiments and Insights

Alibaba Cloud Developer

Dec 3, 2019 · Artificial Intelligence

How Alibaba Detects ‘Disgusting’ Images on Taobao with AI

This article describes Alibaba's AI system for automatically filtering nauseating product images on Taobao, covering challenges such as cold‑start, class imbalance, and diverse visual features, and detailing solutions like semi‑supervised learning, active learning, OHEM‑cascade, attention mechanisms, and the resulting business impact.

Attention MechanismE-commerce AIImage Classification

0 likes · 15 min read

How Alibaba Detects ‘Disgusting’ Images on Taobao with AI

DataFunTalk

Nov 27, 2019 · Artificial Intelligence

Front‑Fusion Based Recognition Pipeline for High‑Precision Map Static Obstacle Detection

This article presents a comprehensive front‑fusion recognition pipeline for high‑definition map static obstacle detection, detailing depth‑aware mapping, precise multi‑sensor calibration, point‑cloud registration, and semi‑supervised learning techniques that improve detection accuracy over traditional image‑only methods.

AIHD mapSemi-supervised Learning

0 likes · 11 min read

Front‑Fusion Based Recognition Pipeline for High‑Precision Map Static Obstacle Detection

Huawei Cloud Developer Alliance

Nov 22, 2019 · Artificial Intelligence

How Front Fusion Improves High-Precision Map Obstacle Detection

This article explains how integrating depth data from LiDAR and stereo cameras with image‑based perception through front‑fusion algorithms reduces semantic errors, enhances static obstacle mapping, and enables semi‑supervised spatial annotation for high‑precision maps used in autonomous driving.

LiDARSemi-supervised LearningSensor Fusion

0 likes · 11 min read

How Front Fusion Improves High-Precision Map Obstacle Detection

iQIYI Technical Product Team

Oct 31, 2019 · Artificial Intelligence

UIR Loss: Leveraging Unlabeled Data to Enhance Face Recognition

iQIYI introduces a semi‑supervised Unknown Identity Rejection (UIR) loss that uses massive unlabeled face images to push unknown samples away from known class centers, improving open‑set face‑recognition accuracy, feature sparsity, and out‑of‑library rejection rates across multiple benchmarks and products.

Semi-supervised LearningUIR lossface recognition

0 likes · 9 min read

UIR Loss: Leveraging Unlabeled Data to Enhance Face Recognition

Alibaba Cloud Developer

Sep 24, 2019 · Artificial Intelligence

How Semi‑Supervised Deep Learning Detects Road Closures in Real‑Time

Gaode’s engineering team presents a semi‑supervised deep‑learning framework that models road networks, extracts traffic, routing, deviation and heatmap features, and combines LSTM with ResNet to accurately identify dynamic road‑closure events, enabling both offline and real‑time detection with high confidence and business‑aligned validation.

Big DataLSTMResNetSemi-supervised Learning

0 likes · 12 min read

How Semi‑Supervised Deep Learning Detects Road Closures in Real‑Time

Amap Tech

Sep 4, 2019 · Artificial Intelligence

Semi-supervised Deep Learning Solution for Detecting Road Closure Events

Gaode’s semi‑supervised deep‑learning framework combines LSTM and ResNet to analyze 28‑day sequences of 39‑dimensional traffic and planning features, automatically discovering and verifying road‑closure events through a three‑layer pipeline, boosting detection confidence and top‑N accuracy by about ten percent and improving user routing.

LSTMResNetSemi-supervised LearningTraffic analysis

0 likes · 11 min read

Semi-supervised Deep Learning Solution for Detecting Road Closure Events

DataFunTalk

Mar 27, 2019 · Artificial Intelligence

Understanding Graph Convolutional Networks through Heat Diffusion and Laplacian Operators

The article explains how the heat diffusion equation and the Laplacian operator on graphs provide a physical intuition for Graph Convolutional Networks, showing the equivalence between continuous‑space Fourier analysis and discrete‑space message passing, and linking these concepts to semi‑supervised learning and GraphSAGE implementations.

GCNLaplacianSemi-supervised Learning

0 likes · 19 min read

Understanding Graph Convolutional Networks through Heat Diffusion and Laplacian Operators

360 Quality & Efficiency

Oct 26, 2018 · Artificial Intelligence

Machine Learning Methods: Discriminative and Generative Models, Semi‑Supervised Learning, and GAN‑Based Classification

This article explains the distinction between discriminative and generative models, outlines the challenges of limited labeled data, introduces semi‑supervised learning principles, and describes GAN‑based semi‑supervised classification algorithms with illustrative diagrams.

GANGenerative ModelsSemi-supervised Learning

0 likes · 3 min read

Machine Learning Methods: Discriminative and Generative Models, Semi‑Supervised Learning, and GAN‑Based Classification

Alibaba Cloud Developer

May 7, 2018 · Artificial Intelligence

How Active PU Learning Boosts Cash‑Out Fraud Detection by 3×

This article presents an Active PU Learning framework that combines active learning with two‑step PU semi‑supervised learning to improve cash‑out fraud detection, reducing labeling costs, enhancing model performance, and achieving a three‑fold increase in identified fraudulent transactions compared to traditional unsupervised methods.

AIRisk DetectionSemi-supervised Learning

0 likes · 15 min read

How Active PU Learning Boosts Cash‑Out Fraud Detection by 3×

AntTech

Apr 24, 2018 · Artificial Intelligence

Anomaly Detection with Partially Observed Anomalies: A Two‑Stage Semi‑Supervised Approach

This article summarizes a two‑stage method for anomaly detection when only a few labeled anomalies and many unlabeled instances are available, detailing problem formulation, isolation‑forest‑based scoring, clustering of anomalies, weighted multiclass modeling, experimental validation, and real‑world URL attack applications.

Pu-LearningSemi-supervised Learninganomaly detection

0 likes · 10 min read

Anomaly Detection with Partially Observed Anomalies: A Two‑Stage Semi‑Supervised Approach

AntTech

Apr 16, 2018 · Artificial Intelligence

Active PU Learning for Cash‑Out Fraud Detection in Alipay’s AlphaRisk Engine

This article presents an Active PU Learning framework that combines active learning with two‑step positive‑unlabeled learning to improve cash‑out fraud detection in Alipay’s fifth‑generation risk engine, AlphaRisk, achieving three‑fold identification gains over unsupervised methods while reducing labeling costs.

Semi-supervised Learningactive learningfraud detection

0 likes · 14 min read

Active PU Learning for Cash‑Out Fraud Detection in Alipay’s AlphaRisk Engine