BestHub
Sign in
Tagged articles
121 articles
Page 1 of 2
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Mar 11, 2026 · Artificial Intelligence

Random Parameter Pruning Boosts Transferable Targeted Attacks Across Model Architectures

The RaPA method introduces random parameter pruning during adversarial generation, creating diverse model variants that markedly increase the success rate of targeted transfer attacks across CNN and Transformer architectures, even against defended models and with higher computational budgets, as demonstrated on ImageNet‑compatible benchmarks.

CNNTransformeradversarial attacks
0 likes · 14 min read
Random Parameter Pruning Boosts Transferable Targeted Attacks Across Model Architectures
HyperAI Super Neural
HyperAI Super Neural
Dec 4, 2025 · Artificial Intelligence

CNNs Help Top Universities Find 7 Rare Quasar Lenses in 810k Spectra

A multinational team of researchers from Stanford, Peking University, UCL and UC Berkeley built a data‑driven pipeline using convolutional neural networks to scan DESI DR1 spectra, expanding the known quasar‑lens sample from a handful to seven high‑quality candidates and demonstrating the power of AI for rare‑object astronomy.

CNNDESIGravitational Lensing
0 likes · 16 min read
CNNs Help Top Universities Find 7 Rare Quasar Lenses in 810k Spectra
HyperAI Super Neural
HyperAI Super Neural
Sep 17, 2025 · Artificial Intelligence

How a CNN‑Transfer Learning Model Boosts Mumbai Monsoon Forecast Accuracy by 400% Using 36 Stations

A collaborative study between IIT Bombay and the University of Maryland creates a hyperlocal monsoon forecast model that downscales GFS data to city‑scale using 36 weather stations, event‑synchronization clustering, and transfer‑learned CNNs, achieving 60‑400% higher accuracy for extreme rainfall predictions several days in advance.

CNNEvent SynchronizationHyperlocal Prediction
0 likes · 12 min read
How a CNN‑Transfer Learning Model Boosts Mumbai Monsoon Forecast Accuracy by 400% Using 36 Stations
AIWalker
AIWalker
Aug 18, 2025 · Artificial Intelligence

UniConvNet: Expanding Effective Receptive Field for a SOTA CNN Vision Backbone (ICCV 2025)

UniConvNet introduces a three‑layer receptive‑field aggregator that combines small kernels to enlarge the effective receptive field while preserving its Gaussian distribution, achieving state‑of‑the‑art results on ImageNet‑1K, COCO2017 and ADE20K with only 30M parameters and 5.1G FLOPs.

CNNComputer VisionEffective Receptive Field
0 likes · 6 min read
UniConvNet: Expanding Effective Receptive Field for a SOTA CNN Vision Backbone (ICCV 2025)
Qborfy AI
Qborfy AI
Jul 1, 2025 · Artificial Intelligence

Why CNNs Outperform Fully Connected Networks: A Deep Dive into Architecture and Applications

This article explains the fundamentals of convolutional neural networks (CNNs), detailing their definition, advantages over fully connected networks, architectural components such as input, hidden, and output layers, key operations like convolution, pooling, and activation, and showcases practical applications and notable insights.

Artificial IntelligenceCNNComputer Vision
0 likes · 5 min read
Why CNNs Outperform Fully Connected Networks: A Deep Dive into Architecture and Applications
Python Programming Learning Circle
Python Programming Learning Circle
May 6, 2025 · Artificial Intelligence

Automatic Math Equation Grading with Python: Data Generation, CNN Training, Image Segmentation, and Result Feedback

This tutorial explains how to build a Python-based automatic grading system for handwritten math equations by generating synthetic character images, training a convolutional neural network, segmenting input images using projection techniques, evaluating expressions with eval, and overlaying correctness indicators on the original image.

CNNImage ProcessingMath Grading
0 likes · 28 min read
Automatic Math Equation Grading with Python: Data Generation, CNN Training, Image Segmentation, and Result Feedback
Python Programming Learning Circle
Python Programming Learning Circle
Apr 15, 2025 · Artificial Intelligence

Automatic Math Expression Grading with Python, CNN and Image Processing

This tutorial explains how to generate synthetic digit fonts, build a convolutional neural network to recognize handwritten arithmetic expressions, segment images using projection methods, evaluate the results with Python's eval function, and overlay feedback symbols on the original image, providing a complete end‑to‑end solution.

CNNImageProcessingMachineLearning
0 likes · 27 min read
Automatic Math Expression Grading with Python, CNN and Image Processing
AIWalker
AIWalker
Mar 11, 2025 · Artificial Intelligence

MobileMamba: Lightweight Multi‑Receptive‑Field Backbone Beats Existing Mamba Models

MobileMamba introduces a three‑stage, lightweight backbone with a multi‑receptive‑field feature‑interaction module that combines wavelet‑enhanced Mamba, multi‑kernel depthwise convolutions, and redundant‑mapping reduction, delivering up to 83.6% ImageNet Top‑1 accuracy while running 21× faster than LocalVim and 3.3× faster than EfficientVMamba.

CNNMambaMobileMamba
0 likes · 10 min read
MobileMamba: Lightweight Multi‑Receptive‑Field Backbone Beats Existing Mamba Models
Python Programming Learning Circle
Python Programming Learning Circle
Jan 3, 2025 · Artificial Intelligence

Visualizing Convolutional Neural Network Features with 40 Lines of Python Code

This article demonstrates how to visualize convolutional features of a VGG‑16 network using only about 40 lines of Python code, explains the underlying concepts, walks through generating patterns by maximizing filter activations, and provides a complete implementation with hooks, loss functions, and multi‑scale optimization.

CNNDeep LearningFeature Visualization
0 likes · 15 min read
Visualizing Convolutional Neural Network Features with 40 Lines of Python Code
Python Programming Learning Circle
Python Programming Learning Circle
Sep 4, 2024 · Artificial Intelligence

Building an Automatic Math Grading System with Python: Data Generation, CNN Training, Image Segmentation, and Result Feedback

This tutorial explains how to create an automatic math‑grading tool in Python by generating synthetic digit images, training a small CNN on the data, segmenting handwritten equations with projection techniques, recognizing characters, evaluating the expressions, and overlaying the results back onto the original image.

CNNImage ProcessingOCR
0 likes · 30 min read
Building an Automatic Math Grading System with Python: Data Generation, CNN Training, Image Segmentation, and Result Feedback
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Jul 7, 2024 · Artificial Intelligence

Daily and Sports Activities Dataset: Description, Preprocessing Pipeline, and CNN Classification Results

This article introduces the Daily_and_Sports_Activities sensor dataset, details its structure and characteristics, provides a Python preprocessing pipeline with sliding‑window segmentation and Z‑score normalization, and reports CNN training results achieving 87.93% accuracy on activity classification.

CNNUCIdata preprocessing
0 likes · 9 min read
Daily and Sports Activities Dataset: Description, Preprocessing Pipeline, and CNN Classification Results
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Jun 30, 2024 · Artificial Intelligence

Spatial Attention Mechanism and Its PyTorch Implementation

This article explains the principle of spatial attention in convolutional neural networks, details the underlying algorithmic steps, and provides a complete PyTorch implementation including the attention module, full network architecture, and practical considerations for integrating spatial attention into deep learning models.

CNNDeep LearningNeural Network
0 likes · 10 min read
Spatial Attention Mechanism and Its PyTorch Implementation
DaTaobao Tech
DaTaobao Tech
May 17, 2024 · Artificial Intelligence

Understanding Convolutional Neural Networks: Theory, Architecture, and Practical Techniques

The article explains CNN fundamentals—convolution, pooling, and fully‑connected layers—illustrates their implementation for American Sign Language letter recognition, details parameter calculations, demonstrates data augmentation and transfer learning techniques, and highlights how these methods boost image‑classification accuracy to around 92%.

CNNdata augmentationimage recognition
0 likes · 19 min read
Understanding Convolutional Neural Networks: Theory, Architecture, and Practical Techniques
Python Programming Learning Circle
Python Programming Learning Circle
Apr 18, 2024 · Artificial Intelligence

Implementing an Automatic Math Expression Grading System with Python and Convolutional Neural Networks

This tutorial walks through building a self‑trained OCR pipeline that generates synthetic digit images, trains a CNN model, segments handwritten math expressions, predicts each character, evaluates the arithmetic result, and overlays checkmarks, crosses or answers onto the original image.

CNNImage ProcessingOCR
0 likes · 28 min read
Implementing an Automatic Math Expression Grading System with Python and Convolutional Neural Networks
AI Algorithm Path
AI Algorithm Path
Apr 5, 2024 · Artificial Intelligence

Master CNN, RNN, GAN, and Transformer Architectures in One Guide

This article provides a friendly, step‑by‑step overview of five core deep‑learning architectures—CNN, RNN, GAN, Transformers, and encoder‑decoder—explaining their structures, key components, and typical use cases in image and natural‑language processing.

CNNDeep LearningEncoder-Decoder
0 likes · 12 min read
Master CNN, RNN, GAN, and Transformer Architectures in One Guide
Test Development Learning Exchange
Test Development Learning Exchange
Mar 27, 2024 · Artificial Intelligence

Introduction to PyTorch and Example CNN Training on CIFAR-10

This article introduces PyTorch as a leading open‑source deep‑learning framework, outlines its key components such as dynamic computation graphs, tensors, autograd, modules, optimizers, data loading, distributed training and TorchScript, and provides a complete Python example that defines a simple CNN and trains it on the CIFAR‑10 dataset.

CNNDeep LearningPyTorch
0 likes · 8 min read
Introduction to PyTorch and Example CNN Training on CIFAR-10
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Sep 16, 2023 · Artificial Intelligence

Understanding DeepSort: A Classic Multi-Object Tracking Algorithm

This article introduces the fundamentals of object tracking in computer vision, explains classic algorithms such as SORT and its deep learning extension DeepSort, describes their underlying mechanisms including Kalman filtering, Hungarian assignment, feature extraction via CNNs, and provides references and code resources for further study.

CNNComputer VisionDeepSort
0 likes · 10 min read
Understanding DeepSort: A Classic Multi-Object Tracking Algorithm
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Jul 31, 2023 · Artificial Intelligence

Overview of Deep Neural Network Architectures

This article provides a comprehensive overview of deep neural network families, introducing twelve major architectures—including Feedforward, CNN, RNN, LSTM, DBN, GAN, Autoencoder, Residual, Capsule, Transformer, Attention, and Deep Reinforcement Learning—explaining their principles, structures, training methods, and offering Python/TensorFlow/PyTorch code examples.

CNNDeep LearningGAN
0 likes · 29 min read
Overview of Deep Neural Network Architectures
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Jul 23, 2023 · Artificial Intelligence

Ten Deep Learning Based Image Dehazing Algorithms: Principles, Implementations, and Comparisons

This article reviews ten state‑of‑the‑art single‑image dehazing methods—including DehazeNet, MSCNN, AOD‑Net, NLD, SSLD, EPDN, DAD, PSD, MSBDN and GFN—detailing their underlying atmospheric scattering models, network architectures, training pipelines, advantages, drawbacks, and providing links to papers, code repositories and illustrative results.

AICNNImage Processing
0 likes · 28 min read
Ten Deep Learning Based Image Dehazing Algorithms: Principles, Implementations, and Comparisons
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Jul 22, 2023 · Artificial Intelligence

Building an Image Classification Model with Transformers and TensorFlow: Theory, Code, and Practice

This article explains how to leverage computer‑vision techniques and deep‑learning frameworks such as Transformers and TensorFlow to build a complete image‑classification pipeline, covering the underlying RGB and CNN principles, model architecture, data preparation, training, and inference with runnable Python code.

CNNImage ClassificationPython
0 likes · 15 min read
Building an Image Classification Model with Transformers and TensorFlow: Theory, Code, and Practice
DaTaobao Tech
DaTaobao Tech
Jun 30, 2023 · Operations

How Perception‑Aware Congestion Control Boosts Real‑Time Video QoE by Up to 32%

The paper introduces PACC, a perception‑aware congestion‑control algorithm that leverages a CNN‑based video‑quality sensor to adjust bitrate based on user‑perceived delay and quality trends, achieving 6.8%‑32.4% QoE improvements over existing model‑based, hybrid, and RL‑based schemes in diverse network conditions.

CNNPACCQoE
0 likes · 16 min read
How Perception‑Aware Congestion Control Boosts Real‑Time Video QoE by Up to 32%
DataFunSummit
DataFunSummit
Jun 23, 2023 · Artificial Intelligence

Frontiers of Video Action Recognition: Concepts, Algorithms, and Applications

This article introduces video action recognition, covering its basic definition, downstream tasks, major algorithmic families—including CNN‑based, Vision‑Transformer, self‑supervised, and multimodal approaches—and discusses practical deployment scenarios and open challenges in the field.

CNNmultimodal modelsself-supervised learning
0 likes · 16 min read
Frontiers of Video Action Recognition: Concepts, Algorithms, and Applications
Model Perspective
Model Perspective
Jan 12, 2023 · Artificial Intelligence

Neural Networks Explained: Architecture, Training, and Reinforcement Basics

This article introduces neural networks, covering their layered structure, common types like CNNs and RNNs, key components such as activation functions, loss, learning rate, backpropagation, dropout, batch normalization, and extends to reinforcement learning concepts including MDPs, policies, value functions, and Q‑learning.

CNNNeural NetworksRNN
0 likes · 6 min read
Neural Networks Explained: Architecture, Training, and Reinforcement Basics
ELab Team
ELab Team
Nov 25, 2022 · Artificial Intelligence

How to Build a Real‑Time Virtual Avatar with CNN and face‑api.js

This tutorial explains how to create a simple virtual avatar system by combining convolutional neural networks, the face‑api.js library, and WebRTC, covering CNN fundamentals, face detection, landmark extraction, model selection, and rendering techniques with code examples.

CNNFace DetectionJavaScript
0 likes · 13 min read
How to Build a Real‑Time Virtual Avatar with CNN and face‑api.js
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
Model Perspective
Model Perspective
Aug 10, 2022 · Artificial Intelligence

Master CNN Basics: Build, Train, and Evaluate a Convolutional Neural Network

This article introduces the fundamentals of convolutional neural networks (CNN), explains key layers such as convolution, pooling, and fully connected layers, and provides a step‑by‑step Python implementation using Keras to load data, construct, compile, train, and evaluate a CNN model on the digits dataset.

CNNKerasPython
0 likes · 5 min read
Master CNN Basics: Build, Train, and Evaluate a Convolutional Neural Network
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
Python Programming Learning Circle
Python Programming Learning Circle
Jul 21, 2022 · Artificial Intelligence

Building an Automatic Math Problem Grading System with Python and Convolutional Neural Networks

This tutorial explains how to generate synthetic digit images, train a CNN model to recognize handwritten numbers and operators, segment scanned math worksheets using projection techniques, evaluate each expression with Python's eval, and overlay the results on the original image to provide automatic grading feedback.

CNNOCRPython
0 likes · 26 min read
Building an Automatic Math Problem Grading System with Python and Convolutional Neural Networks
58 Tech
58 Tech
Jul 14, 2022 · Artificial Intelligence

Image Quality Assessment Techniques and Their Application in 58.com Recruitment Image Filtering

This article reviews image quality assessment (IQA) methods—including full‑reference, reduced‑reference, and no‑reference approaches—covers typical datasets and evaluation metrics, describes CNN‑based models such as WaDIQaM, DBCNN and hyperIQA, and details a customized IQA solution deployed at 58.com to filter and rank recruitment images, achieving a reduction of bad‑image rate from 9% to 0%.

CNNComputer VisionIQA
0 likes · 17 min read
Image Quality Assessment Techniques and Their Application in 58.com Recruitment Image Filtering
Code DAO
Code DAO
May 31, 2022 · Artificial Intelligence

How Deep Convolutional Networks Boost Image Super-Resolution: A Paper Review

This article reviews the seminal SRCNN paper, detailing its contributions, architecture, training pipeline, hyper‑parameters, and extensive experiments that show how a shallow fully‑convolutional network achieves superior PSNR and runtime compared to traditional sparse‑coding and bicubic methods.

CNNDeep LearningPSNR
0 likes · 12 min read
How Deep Convolutional Networks Boost Image Super-Resolution: A Paper Review
Code DAO
Code DAO
May 28, 2022 · Artificial Intelligence

How to Build an Image Duplicate Detection System

This article explains how to construct an image duplicate and near‑duplicate detection system, compares five similarity methods (Euclidean distance, SSIM, image hashing, cosine similarity, and CNN‑based feature similarity), provides Python implementations, evaluates them on two datasets, and discusses speed, accuracy, and robustness results.

CNNEfficientNetPython
0 likes · 18 min read
How to Build an Image Duplicate Detection System
Code DAO
Code DAO
May 27, 2022 · Artificial Intelligence

Building an Image Classification Model with CNNs

This article explains how to train a convolutional neural network on a remote GPU for image classification, covering convolution, padding, activation, pooling, dropout, flattening, fully‑connected layers, dataset preparation, model definition, training, and prediction using TensorFlow/Keras.

CNNFood-101GPU training
0 likes · 13 min read
Building an Image Classification Model with CNNs
Code DAO
Code DAO
May 21, 2022 · Artificial Intelligence

How Quantization and Fusion Accelerate CNN Inference on Edge Devices

The article explains CNN inference optimization by applying PyTorch quantization and module‑fusion techniques, compares model size and latency before and after quantization, shows code for building, quantizing, and fusing a simple CNN, and presents benchmark results on CPU, highlighting a four‑fold size reduction and up to 1.7× speed‑up.

CNNPyTorchedge inference
0 likes · 11 min read
How Quantization and Fusion Accelerate CNN Inference on Edge Devices
Baobao Algorithm Notes
Baobao Algorithm Notes
Apr 11, 2022 · Artificial Intelligence

Can ResNet Still Beat Transformers? A Deep Dive into Modern Training Tricks

This article reviews recent research and official PyTorch blog updates that modify ResNet architectures and training tricks, compares their performance against EfficientNet, ConvNeXt, and Vision Transformers using extensive ImageNet benchmarks, and provides both literature‑based and local evaluation results to assess whether classic CNNs remain competitive.

CNNResNetmodel benchmarking
0 likes · 13 min read
Can ResNet Still Beat Transformers? A Deep Dive into Modern Training Tricks
Tencent Cloud Developer
Tencent Cloud Developer
Mar 3, 2022 · Artificial Intelligence

Model Distillation for Query-Document Matching: Techniques and Optimizations

We applied knowledge distillation to a video query‑document BERT matcher, compressing the 12‑layer teacher into production‑ready 1‑layer ALBERT and tiny TextCNN students using combined soft, hard, and relevance losses plus AutoML‑tuned hyper‑parameters, achieving sub‑5 ms latency and up to 2.4% AUC improvement over the original model.

ALBERTAutoMLBERT
0 likes · 12 min read
Model Distillation for Query-Document Matching: Techniques and Optimizations
IEG Growth Platform Technology Team
IEG Growth Platform Technology Team
Feb 14, 2022 · Artificial Intelligence

Multimodal Evolution and Application in Tencent Game Advertising System

This article describes the end‑to‑end multimodal modeling pipeline—covering text, image, and video understanding, model evolution from shallow to deep networks, key‑frame extraction, fine‑tuning, and multimodal fusion—used in Tencent's game ad exchange platform, along with practical deployment challenges and solutions.

AdvertisingCNNMultimodal Learning
0 likes · 22 min read
Multimodal Evolution and Application in Tencent Game Advertising System
Code DAO
Code DAO
Dec 2, 2021 · Artificial Intelligence

Transfer Learning with ShuffleNetV2 for Flower Classification

This article walks through building a PyTorch ShuffleNetV2 model, preparing the Kaggle Flowers dataset, training with transfer learning on a GPU, visualizing loss and accuracy, and performing inference on five test images, achieving nearly 90% validation accuracy after 95 epochs.

CNNPyTorchShuffleNetV2
0 likes · 19 min read
Transfer Learning with ShuffleNetV2 for Flower Classification
DeWu Technology
DeWu Technology
Nov 18, 2021 · Artificial Intelligence

Background Complexity Detection for Sneaker Images Using MobileNet, FPN, and Modified SAM

The project presents a lightweight MobileNet‑FPN architecture enhanced with a modified spatial‑attention module that evaluates corner‑based self‑similarity to classify sneaker photo backgrounds, achieving 96% test accuracy—exceeding baseline CNN performance—and meeting business targets of over 80% hint accuracy and 90% mandatory enforcement.

CNNComputer VisionImage Processing
0 likes · 12 min read
Background Complexity Detection for Sneaker Images Using MobileNet, FPN, and Modified SAM
360 Smart Cloud
360 Smart Cloud
Aug 31, 2021 · Artificial Intelligence

Understanding Convolution, Convolutional Neural Networks, and Their Implementation in Image Processing

This article explains the mathematical concept of 2‑D convolution, demonstrates its use for image filtering with examples such as blurring and Sobel edge detection, introduces artificial neural networks and back‑propagation, and details the design, training, and performance of convolutional neural networks for tasks like Sobel filter learning and MNIST digit recognition, including full Python code examples.

CNNConvolutionDeep Learning
0 likes · 25 min read
Understanding Convolution, Convolutional Neural Networks, and Their Implementation in Image Processing
Python Programming Learning Circle
Python Programming Learning Circle
Jul 6, 2021 · Artificial Intelligence

Understanding ResNet and Building It from Scratch with PyTorch

This article explains the motivation behind residual networks, describes the architecture of ResNet including residual blocks and skip connections, lists available Keras implementations, and provides a step‑by‑step PyTorch tutorial with complete code to construct and test ResNet‑50/101/152 models.

CNNDeep LearningPyTorch
0 likes · 10 min read
Understanding ResNet and Building It from Scratch with PyTorch
TiPaiPai Technical Team
TiPaiPai Technical Team
Jun 18, 2021 · Artificial Intelligence

Mastering Text Recognition: Encoder & Decoder Strategies Explained

This article reviews modern text‑recognition systems, detailing how encoders such as CNN, CNN‑BiLSTM, and Transformer‑based models extract visual features, and how decoders like Position Attention, Transformer decoders, and RNN Seq2Seq align variable‑length text, while also discussing CTC loss and practical design choices.

CNNCTCDecoder
0 likes · 9 min read
Mastering Text Recognition: Encoder & Decoder Strategies Explained
Sohu Tech Products
Sohu Tech Products
May 12, 2021 · Artificial Intelligence

Zero‑Basis Food Sound Recognition with ASR: Theory, Workflow, and Complete Python Code

This article introduces the fundamentals of automatic speech recognition (ASR) for food‑sound classification, explains key audio representations and modeling approaches, and provides a fully runnable Python implementation using librosa, TensorFlow/Keras, and classic machine‑learning tools to train and predict on the Tianchi competition dataset.

ASRAudio ClassificationCNN
0 likes · 11 min read
Zero‑Basis Food Sound Recognition with ASR: Theory, Workflow, and Complete Python Code
DeWu Technology
DeWu Technology
Apr 30, 2021 · Artificial Intelligence

Deep Learning Based Image Aesthetic Quality Assessment

The paper presents a deep‑learning approach that uses an ImageNet‑pretrained CNN to predict full human rating distributions for images via an Earth Mover’s Distance loss, trained on the AVA dataset, and demonstrates accurate assessment of aesthetic factors such as tone, contrast, and composition.

AVA datasetCNNDeep Learning
0 likes · 8 min read
Deep Learning Based Image Aesthetic Quality Assessment
Didi Tech
Didi Tech
Sep 17, 2020 · Artificial Intelligence

Machine Learning Practices in DiDi's Network Positioning: From Unsupervised Probabilistic Models to End‑to‑End CNN

DiDi’s network‑positioning system, which serves billions of daily location requests using Wi‑Fi and cellular signals, has evolved from an unsupervised probabilistic fingerprint matcher through a supervised GBDT‑DeepFM regression model to a fully end‑to‑end CNN that directly predicts coordinates, delivering markedly higher accuracy.

CNNLBSnetwork positioning
0 likes · 11 min read
Machine Learning Practices in DiDi's Network Positioning: From Unsupervised Probabilistic Models to End‑to‑End CNN
Architects' Tech Alliance
Architects' Tech Alliance
Sep 3, 2020 · Artificial Intelligence

Deep Learning Specialization Infographic Overview

This article presents a comprehensive English summary of the deep learning specialization infographics originally shared by Andrew Ng, covering fundamentals, logistic regression, shallow and deep neural networks, regularization, optimization, hyperparameters, convolutional and recurrent networks, and practical advice for model building and evaluation.

CNNDeep LearningNeural Networks
0 likes · 21 min read
Deep Learning Specialization Infographic Overview
360 Quality & Efficiency
360 Quality & Efficiency
Aug 7, 2020 · Artificial Intelligence

Replacing Fully Connected Layers with Fully Convolutional Networks for Variable‑Scale Image Tasks

This article analyses the drawbacks of using fully‑connected layers in convolutional neural networks for image tasks, proposes fully‑convolutional alternatives with 1×1 convolutions and strategic max‑pooling, provides TensorFlow code examples, compares model sizes and performance, and discusses deployment considerations for variable‑size inputs.

CNNFully Convolutional NetworkImage Classification
0 likes · 7 min read
Replacing Fully Connected Layers with Fully Convolutional Networks for Variable‑Scale Image Tasks
Tencent Advertising Technology
Tencent Advertising Technology
Jul 30, 2020 · Artificial Intelligence

Tencent Advertising Algorithm Competition 2020: Problem Overview, Data, Model Implementation, and Results

This article details the 2020 Tencent Advertising Algorithm Competition, describing the user profiling task, data fields, feature engineering, Python code for ID mapping and Word2Vec training, multiple model architectures (LSTM, CNN-Inception, transformer), and the final performance results achieved by the team.

AdvertisingCNNLSTM
0 likes · 13 min read
Tencent Advertising Algorithm Competition 2020: Problem Overview, Data, Model Implementation, and Results
Tencent Cloud Developer
Tencent Cloud Developer
Jun 13, 2020 · Artificial Intelligence

Tencent Cloud Face Effects: Features, AI Techniques, Architecture, and Service Practices

Tencent Cloud’s senior engineer Li Kaibin outlines the cloud‑based face‑effects platform, detailing its AI‑driven features such as face fusion, beauty, virtual makeup, segmentation and age‑gender transformation, the CNN‑based model training pipeline, a layered service architecture with elastic scaling and robust monitoring, and future expansions into video effects, international regions and low‑code integration.

AICNNCloud Services
0 likes · 32 min read
Tencent Cloud Face Effects: Features, AI Techniques, Architecture, and Service Practices
Python Programming Learning Circle
Python Programming Learning Circle
Jun 12, 2020 · Artificial Intelligence

Visualizing Convolutional Neural Networks: Methods and Practical Examples

This article explains why visualizing CNN models is crucial for understanding and debugging deep learning systems, outlines three main visualization approaches—basic architecture, activation‑based, and gradient‑based methods—and provides step‑by‑step Keras code examples, including model summary, filter visualization, occlusion mapping, saliency maps, and class activation maps.

CNNDeep LearningKeras
0 likes · 13 min read
Visualizing Convolutional Neural Networks: Methods and Practical Examples
System Architect Go
System Architect Go
Jun 4, 2020 · Artificial Intelligence

Evolution and Underlying Principles of the Billion‑Scale Image Search System at Youpai Image Manager

This article describes the two‑generation evolution of Youpai Image Manager's billion‑scale image search system, explaining the mathematical representation of images, the limitations of MD5, the first‑generation pHash‑ElasticSearch solution, and the second‑generation CNN‑Milvus approach for robust, large‑scale visual similarity search.

CNNMilvusVector Search
0 likes · 9 min read
Evolution and Underlying Principles of the Billion‑Scale Image Search System at Youpai Image Manager
Xianyu Technology
Xianyu Technology
Jun 4, 2020 · Artificial Intelligence

NBDT: Neural-Backed Decision Trees for Interpretable Image Classification

NBDT (Neural‑Backed Decision Trees) merges a pretrained CNN with a WordNet‑derived hierarchical tree, using the network’s final‑layer weights as class embeddings and a combined classification loss, to deliver state‑of‑the‑art image classification that remains interpretable through explicit hierarchical reasoning.

CNNDecision TreesExplainable Machine Learning
0 likes · 11 min read
NBDT: Neural-Backed Decision Trees for Interpretable Image Classification
System Architect Go
System Architect Go
Apr 11, 2020 · Artificial Intelligence

How to Build an Image Search Engine with CNN and Milvus: A Step‑by‑Step Guide

This article walks through the complete engineering workflow for building an image‑search system, covering CNN‑based feature extraction with VGG16, vector normalization, image preprocessing, black‑edge removal, and practical deployment of the Milvus vector database including hardware requirements, capacity planning, collection/partition design, and search result handling.

CNNMilvusPython
0 likes · 11 min read
How to Build an Image Search Engine with CNN and Milvus: A Step‑by‑Step Guide
System Architect Go
System Architect Go
Mar 30, 2020 · Artificial Intelligence

Overview of Image Search System

This article explains the fundamentals of building an image‑by‑image search system, covering image feature extraction methods such as hashing, traditional descriptors, CNN‑based vectors, and the use of vector search engines like Milvus for similarity retrieval.

CNNMilvusVector Search
0 likes · 6 min read
Overview of Image Search System
DataFunTalk
DataFunTalk
Dec 16, 2019 · Artificial Intelligence

A Comprehensive Overview of Sequential Recommendation Models and Techniques

This article provides an in-depth overview of sequential recommendation, defining the problem, discussing data preparation, and reviewing various neural architectures—including MLP, CNN, RNN, Temporal CNN, self‑attention, and reinforcement‑learning approaches—while offering practical guidance on model selection and implementation.

CNNDeep LearningRNN
0 likes · 36 min read
A Comprehensive Overview of Sequential Recommendation Models and Techniques
DataFunTalk
DataFunTalk
Dec 13, 2019 · Artificial Intelligence

Fundamentals of Deep Learning: Neural Networks, CNNs, RNNs, LSTM, and GRU

This article provides a comprehensive overview of deep learning fundamentals, covering neural network basics, forward and backward feedback architectures, key models such as MLP, CNN, RNN, LSTM and GRU, training techniques like gradient descent, learning rate schedules, momentum, weight decay, and batch normalization.

CNNDeep LearningGRU
0 likes · 14 min read
Fundamentals of Deep Learning: Neural Networks, CNNs, RNNs, LSTM, and GRU
Qunar Tech Salon
Qunar Tech Salon
Dec 10, 2019 · Artificial Intelligence

Comprehensive Overview of Face Detection Methods and Techniques

This article provides an in‑depth review of face detection, covering traditional knowledge‑, model‑, feature‑ and appearance‑based approaches, modern deep‑learning methods such as cascade CNN, MTCNN and Facebox, strategies for handling multi‑scale faces, anchor‑box densification, and practical training considerations.

CNNCascade CNNComputer Vision
0 likes · 10 min read
Comprehensive Overview of Face Detection Methods and Techniques
Alibaba Cloud Developer
Alibaba Cloud Developer
Nov 21, 2019 · Artificial Intelligence

How Alibaba’s ‘Guess‑Draw Treasure’ Game Powers Real‑Time Sketch AI

During the 2023 Lunar New Year, Taobao Live launched the real‑time interactive game ‘Guess‑Draw Treasure’, which lets users sketch on mobile devices and have AI instantly recognize their drawings to win cash rewards; this article reveals the underlying AI techniques, challenges, model choices, datasets, and future plans.

AI sketch recognitionAlibabaCNN
0 likes · 13 min read
How Alibaba’s ‘Guess‑Draw Treasure’ Game Powers Real‑Time Sketch AI
360 Tech Engineering
360 Tech Engineering
Nov 13, 2019 · Artificial Intelligence

Text Anti‑Spam Techniques and TextCNN Model for Real‑Time Spam Detection on the Huajiao Platform

This article introduces the Huajiao platform's text anti‑spam architecture, analyzes spam categories and challenges, compares rule‑based and machine‑learning approaches, details traditional NLP methods and the TextCNN deep‑learning model, provides its TensorFlow implementation, and describes the online deployment workflow.

CNNNLPTensorFlow
0 likes · 14 min read
Text Anti‑Spam Techniques and TextCNN Model for Real‑Time Spam Detection on the Huajiao Platform
Huajiao Technology
Huajiao Technology
Nov 12, 2019 · Artificial Intelligence

Text Anti‑Spam Detection with TextCNN: From Traditional Methods to Online Deployment

This article introduces the challenges of text‑based spam on the Huajiao platform, reviews traditional rule‑based and machine‑learning classification methods, explains the TextCNN architecture for robust character‑level detection, and details its TensorFlow Serving deployment for real‑time anti‑spam services.

CNNTensorFlowanti-spam
0 likes · 16 min read
Text Anti‑Spam Detection with TextCNN: From Traditional Methods to Online Deployment
Tencent Cloud Developer
Tencent Cloud Developer
Jul 19, 2019 · Artificial Intelligence

Multi-turn Dialogue Intent Classification: Data Processing, Model Construction, and Operational Optimization

The article details a multi‑turn dialogue intent classification pipeline that extracts and expands labeled utterances, preprocesses text with custom tokenization, trains a two‑layer CNN‑Highway and a multi‑head self‑attention model, analyzes errors, and achieves up to 98.7% accuracy on a large, balanced dataset.

BERTCNNdialogue system
0 likes · 15 min read
Multi-turn Dialogue Intent Classification: Data Processing, Model Construction, and Operational Optimization
Alibaba Cloud Developer
Alibaba Cloud Developer
May 27, 2019 · Artificial Intelligence

From Neurons to BERT: Tracing the Evolution of Deep Learning in NLP

This article walks through the development of deep learning for natural language processing, starting with basic neural cells and shallow networks, then exploring CNNs, RNNs, LSTMs, TextCNN, ESIM, ELMo, and culminating with the Transformer‑based BERT model, its training objectives, fine‑tuning strategies, and performance comparisons.

BERTCNNDeep Learning
0 likes · 19 min read
From Neurons to BERT: Tracing the Evolution of Deep Learning in NLP
Hulu Beijing
Hulu Beijing
Apr 16, 2019 · Artificial Intelligence

How Deep Learning Transforms Network Bandwidth Prediction: From RNN to CNN‑RNN Hybrids

This article explores how deep learning techniques such as RNN, LSTM, 3D‑CNN, and CNN‑RNN hybrids can be applied to predict network bandwidth and traffic, comparing traditional time‑series methods with modern AI approaches and highlighting the potential of graph neural networks for future improvements.

CNNDeep LearningNetwork Traffic
0 likes · 9 min read
How Deep Learning Transforms Network Bandwidth Prediction: From RNN to CNN‑RNN Hybrids
Xianyu Technology
Xianyu Technology
Mar 19, 2019 · Artificial Intelligence

Page Difference Detection for Automated Regression Testing in Mobile Apps

The paper proposes a method for automated regression testing in mobile apps by detecting page differences via layout segmentation, ORB alignment of scrollable areas, SSIM similarity, and CNN filtering to ignore scroll or cursor changes while highlighting semantic UI changes, demonstrated on the Xianyu app.

CNNORBSSIM
0 likes · 10 min read
Page Difference Detection for Automated Regression Testing in Mobile Apps
DataFunTalk
DataFunTalk
Mar 15, 2019 · Artificial Intelligence

A Comprehensive Overview of Deep Learning Applications in Computer Vision

This article provides an extensive review of deep learning techniques applied to computer vision, covering the evolution of CNN architectures, image and video processing tasks, 2.5‑D and 3‑D reconstruction, object detection, segmentation, tracking, SLAM, and various practical applications such as AR, content retrieval, and autonomous driving.

CNNComputer VisionImage Processing
0 likes · 22 min read
A Comprehensive Overview of Deep Learning Applications in Computer Vision
Hulu Beijing
Hulu Beijing
Mar 7, 2019 · Artificial Intelligence

From AlexNet to ResNeXt: Key Milestones in CNN Evolution

This article traces the evolution of convolutional neural networks from the pioneering AlexNet through VGG, Inception, ResNet, Inception‑v4, Inception‑ResNet and ResNeXt, highlighting architectural innovations, performance gains, and the underlying biological inspirations that shaped modern deep learning models.

AlexNetCNNComputer Vision
0 likes · 13 min read
From AlexNet to ResNeXt: Key Milestones in CNN Evolution
JD Tech Talk
JD Tech Talk
Jan 16, 2019 · Artificial Intelligence

Combining CNN and LSTM for Purchase User Prediction: Architecture, Implementation, and Results

This article presents a detailed case study of building a purchase‑user prediction model by integrating Convolutional Neural Networks for feature extraction with Long Short‑Term Memory networks for time‑series forecasting, covering background, model structure, data augmentation, experimental results, and business impact.

CNNDeep LearningLSTM
0 likes · 10 min read
Combining CNN and LSTM for Purchase User Prediction: Architecture, Implementation, and Results
Alibaba Cloud Developer
Alibaba Cloud Developer
Jan 2, 2019 · Artificial Intelligence

How AI Detects Screenshot Bugs: From CNN Models to Image Clustering

Leveraging TensorFlow's CNN and OCR‑LSTM models, this article details how AI can automatically spot blank pages, UI anomalies, and garbled text in app screenshots, and describes a Jenkins‑driven retraining pipeline and hierarchical clustering to de‑duplicate images and boost manual review efficiency.

AICNNOCR
0 likes · 7 min read
How AI Detects Screenshot Bugs: From CNN Models to Image Clustering
DataFunTalk
DataFunTalk
Dec 16, 2018 · Artificial Intelligence

Practical Applications of Video Content Understanding at Hulu

This article details Hulu's AI-driven techniques for fine-grained video segmentation, end‑cap detection, subtitle detection and language recognition, background‑music classification, automated processing pipelines, tag generation, and cover‑image regeneration, illustrating how these methods improve user experience and operational efficiency.

AI pipelinesCNNcontent understanding
0 likes · 14 min read
Practical Applications of Video Content Understanding at Hulu
37 Interactive Technology Team
37 Interactive Technology Team
Dec 13, 2018 · Artificial Intelligence

A 2‑Channel CNN Method for Automatic Game Asset Tag Generation and Similarity Recommendation

The paper introduces an improved two‑channel CNN, built on a shared VGG16 backbone and a hinge‑loss metric, to automatically generate numeric tags for game advertising assets by learning content and style similarity, achieving over 97% test accuracy and enabling efficient ad placement and asset management.

2-channel networkCNNDeep Learning
0 likes · 14 min read
A 2‑Channel CNN Method for Automatic Game Asset Tag Generation and Similarity Recommendation
Tencent Cloud Developer
Tencent Cloud Developer
Oct 12, 2018 · Artificial Intelligence

Understanding Convolutional Neural Networks (CNN) with Keras

The article introduces convolutional neural networks, explains core concepts such as convolution, padding, stride, and pooling, demonstrates how to calculate output dimensions, and provides a step‑by‑step Keras example that builds, compiles, and trains a multi‑layer CNN for image classification.

CNNComputer VisionDeep Learning
0 likes · 8 min read
Understanding Convolutional Neural Networks (CNN) with Keras
MaGe Linux Operations
MaGe Linux Operations
Aug 21, 2018 · Artificial Intelligence

How Deep Learning Transformed Face Recognition: From Images to Real‑Time Video

This article surveys the evolution of face recognition from early statistical methods to modern deep‑learning approaches, outlines key researchers, open‑source projects, popular APIs, core processing steps, the DeepFace architecture, datasets, and experimental results, providing a comprehensive guide for practitioners and researchers.

CNNComputer VisionDatasets
0 likes · 22 min read
How Deep Learning Transformed Face Recognition: From Images to Real‑Time Video
Tencent Cloud Developer
Tencent Cloud Developer
Aug 13, 2018 · Artificial Intelligence

Computer Vision Technology: From Viral Social Media Apps to Enterprise AI Applications

The article surveys computer‑vision fundamentals and evolution—from early filters and feature extractors to modern deep‑learning models—illustrating how techniques like face detection, image matching, and caption generation powered viral social‑media trends and now underpin enterprise AI services on Tencent Cloud, while offering practical implementation and skill‑development guidance.

AI applicationsCNNImage Processing
0 likes · 18 min read
Computer Vision Technology: From Viral Social Media Apps to Enterprise AI Applications
Alibaba Cloud Developer
Alibaba Cloud Developer
Aug 10, 2018 · Artificial Intelligence

How Multi-Level Similarity‑Aware CNN Boosts Person Re‑Identification Accuracy

This article reviews a 2017 ACM MM paper that introduces a multi‑level similarity‑aware CNN (MSP‑CNN) for person re‑identification, detailing its siamese architecture, dual similarity constraints, multi‑task training, experimental results on CUHK03, Market‑1501 and CUHK01, and its advantages for large‑scale deployment.

CNNDeep Learningmulti-task learning
0 likes · 16 min read
How Multi-Level Similarity‑Aware CNN Boosts Person Re‑Identification Accuracy
Tencent Cloud Developer
Tencent Cloud Developer
Aug 3, 2018 · Artificial Intelligence

Analysis of Google Quickdraw CNN‑RNN Model for Sketch Recognition

The article dissects Google’s Quickdraw sketch‑recognition model, detailing its 1‑D convolutional front‑end, Bi‑LSTM encoder, and softmax classifier, explaining the TFRecord‑based normalization and interpolation steps, why pooling harms accuracy, and how the massive dataset can fuel diverse sequential‑learning applications and product concepts.

CNNRNNSketch Recognition
0 likes · 7 min read
Analysis of Google Quickdraw CNN‑RNN Model for Sketch Recognition
Alibaba Cloud Developer
Alibaba Cloud Developer
Jul 31, 2018 · Artificial Intelligence

How Multi-Level Similarity‑Aware CNN Boosts Person Re‑Identification

This paper introduces a novel multi‑level similarity‑aware CNN (MSP‑CNN) for person re‑identification, applying distinct similarity constraints to low‑ and high‑level feature maps, integrating classification and similarity losses in a multitask framework, and demonstrating superior performance on CUHK03, CUHK01 and Market‑1501 benchmarks.

CNNDeep Learningmulti-task learning
0 likes · 15 min read
How Multi-Level Similarity‑Aware CNN Boosts Person Re‑Identification
Qizhuo Club
Qizhuo Club
Jul 30, 2018 · Artificial Intelligence

Mastering Inception v3: From Codebase to Rose Recognition with TensorFlow

This article walks through the Inception v3 TensorFlow codebase, explains its design principles, details the training script flags and loss calculations, shows how to fine‑tune the model on a flower dataset, and provides practical tips for building custom datasets and optimizing hyper‑parameters for image classification.

CNNImage ClassificationInception
0 likes · 25 min read
Mastering Inception v3: From Codebase to Rose Recognition with TensorFlow
Meitu Technology
Meitu Technology
Jul 24, 2018 · Artificial Intelligence

Interaction-aware Spatio-Temporal Pyramid Attention Networks for Action Classification

Researchers introduce an Interaction‑aware Spatio‑Temporal Pyramid Attention network that embeds a PCA‑guided loss to capture complementary multi‑scale features, enabling end‑to‑end video action classification with state‑of‑the‑art accuracy on UCF101, HMDB51, Charades and internal datasets.

Attention MechanismCNNaction classification
0 likes · 7 min read
Interaction-aware Spatio-Temporal Pyramid Attention Networks for Action Classification
Alibaba Cloud Developer
Alibaba Cloud Developer
Jul 24, 2018 · Artificial Intelligence

Dimension Stretching Lets One CNN Tackle Diverse Degradations in Image Super‑Resolution

Recent advances in CNN‑based single image super‑resolution assume bicubic down‑sampling, limiting real‑world performance; this paper introduces a dimension‑stretching strategy that feeds blur kernels and noise levels into a CNN, enabling a single model (SRMD) to efficiently handle multiple, even spatially varying, degradation types with strong quantitative and visual results.

CNNSRMDdegradation modeling
0 likes · 10 min read
Dimension Stretching Lets One CNN Tackle Diverse Degradations in Image Super‑Resolution