Evaluating bag-of-visual-words representations in scene classification

Based on keypoints extracted as salient image patches, an image can be described as a "bag of visual words" and this representation has been used in scene classification. The choice of dimension, selection, and weighting of visual words in this representation is crucial to the classification performance but has not been thoroughly studied in previous work. Given the analogy between this representation and the bag-of-words representation of text documents, we apply techniques used in text categorization, including term weighting, stop word removal, feature selection, to generate image representations that differ in the dimension, selection, and weighting of visual words. The impact of these representation choices to scene classification is studied through extensive experiments on the TRECVID and PASCAL collection. This study provides an empirical basis for designing visual-word representations that are likely to produce superior classification performance.

• Publication year

  2007

• Venue

  Multimedia Information Retrieval

• Publication date

  2007-09-24

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1145/1290082.1290111
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Supervised Learning of Semantic Classes for Image Annotation and Retrieval

  2007cited by this paper
• Towards optimal bag-of-features for object categorization and semantic video retrieval

  2007cited by this paper
• Scalable Recognition with a Vocabulary Tree

  2006cited by this paper
• Keyframe Retrieval by Keypoints: Can Point-to-Point Matching Help?

  2006influential reference
• Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

  2006influential reference
• Local Features and Kernels for Classification of Texture and Object Categories: An In-Depth Study

  2005influential reference
• A Bayesian hierarchical model for learning natural scene categories

  2005cited by this paper
• PCA-SIFT: a more distinctive representation for local image descriptors

  2004cited by this paper
• Scale & Affine Invariant Interest Point Detectors

  2004cited by this paper
• Distinctive Image Features from Scale-Invariant Keypoints

  2004cited by this paper
• A performance evaluation of local descriptors

  2003cited by this paper
• TRECVID: Benchmarking the Effectivenss of Information Retrieval Tasks on Digital Video

  2003cited by this paper
• Video Google: a text retrieval approach to object matching in videos

  2003influential reference
• A re-examination of text categorization methods

  1999cited by this paper
• Text Categorization with Support Vector Machines: Learning with Many Relevant Features

  1999cited by this paper
• A Tutorial on Support Vector Machines for Pattern Recognition

  1998cited by this paper
• A Comparative Study on Feature Selection in Text Categorization

  1997influential reference
• Ììì Öûûò Ë Blockinöö Óóóòòòö Áòøøöòòøøóòòð

  1992cited by this paper
• Term-Weighting Approaches in Automatic Text Retrieval

  1988cited by this paper
• Local Features and Kernels for Classification of Texture and Object Categories: An In-Depth Study

  year unknowninfluential reference
• Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Real-time Computerized Annotation of Pictures

  year unknowncited by this paper

• RECONHECIMENTO DE DOENÇAS EM FOLHAS DE MACIEIRA UTILIZANDO BAG OF FEATURES E SVM COM VARIAÇÃO DO VOCABULÁRIO VISUAL

  2026cites this paper
• Multimodal topic models for brand competitive analysis

  2026cites this paper
• Multi-modal semantic representation learning for zero-shot indoor scene recognition

  2026cites this paper
• A novel methodology for modelling images using level-sets with application to atopic asthma fibrin networks

  2025cites this paper
• A Comprehensive Hybrid Approach for Indoor Scene Recognition Combining CNNs and Text-Based Features

  2025cites this paper
• Violence Detection in Video Using Statistical Features of the Optical Flow and 2D Convolutional Neural Network

  2025cites this paper
• Diverse semantic representation learning based on vision-language models for zero-shot indoor scene recognition

  2025cites this paper
• Secne Image Classification Based on Combining Extended-Local Directional Ternary Pattern and Dense-SIFT Descriptor

  2025cites this paper
• Integrating Large Language Models with Deep Learning for Medical Imaging Modality Classification

  2025cites this paper
• KAZE features-based SLAM for autonomous UAV navigation in GPS-denied environments

  2025cites this paper
• TransWCD: Scene-Adaptive Joint Constrained Framework for Weakly Supervised Change Detection

  2025cites this paper
• Conv-LSTM for Real-Time Spatio-Temporal Analysis of Crowd Behavior in Public Spaces

  2025cites this paper
• Interactive Retrieval System for Multi-Stream Collections: multiXview at CASTLE 2025 Interactive Grand Challenge

  2025cites this paper
• NLP-driven customer segmentation: A comprehensive review of methods and applications in personalized marketing

  2025cites this paper
• Enhancing Classification Power: Tree Strength-Infused Enriched Random Forest

  2024cites this paper
• SpikingVPR: Spiking Neural Network-Based Feature Aggregation for Visual Place Recognition

  2024cites this paper
• Semantic-Search: A Knowledge-Driven Classification Method for Plant Diseases

  2024cites this paper
• Watching Grass Grow: Long-term Visual Navigation and Mission Planning for Autonomous Biodiversity Monitoring

  2024cites this paper
• Multi-label remote sensing scene classification using two-level double channel spatial attention residual blocks

  2024cites this paper
• Analysis and Validation of Image Search Engines in Histopathology

  2024cites this paper
• Visual-Word Tokenizer: Beyond Fixed Sets of Tokens in Vision Transformers

  2024cites this paper
• Privacy-preserving geo-tagged image search in edge-cloud computing for IoT

  2024cites this paper
• Semantic-focused Patch Tokenizer with Multi-branch Mixer for Visual Place Recognition

  2024cites this paper
• A Novel Approach to Image Retrieval for Vision-Based Positioning Utilizing Graph Topology

  2024cites this paper
• RRSIS: Referring Remote Sensing Image Segmentation

  2023cites this paper
• A deep learning self-attention cross residual network with Info-WGANGP for mitotic cell identification in HEp-2 medical microscopic images

  2023cites this paper
• Schema Inference for Interpretable Image Classification

  2023influential citation
• Deep Active Learning for Automatic Mitotic Cell Detection on HEp-2 Specimen Medical Images

  2023cites this paper
• Augmented Transformers with Adaptive n-grams Embedding for Multilingual Scene Text Recognition

  2023cites this paper
• Automatic classification of pulmonary nodules in computed tomography images using pre-trained networks and bag of features

  2023cites this paper
• Aggregating Deep Features of Multi-CNN Models for Image Retrieval

  2023cites this paper
• Bounded multivariate generalized Gaussian mixture model using ICA and IVA

  2023cites this paper
• 3D Multi-Views Object Classification Based on a Fully Generalized Dirichlet Allocation Model

  2023cites this paper
• Historical insights at scale: A corpus-wide machine learning analysis of early modern astronomic tables

  2023cites this paper
• Semantic Similar Image Search: A Command-Line Tool Based on CLIP Regular Research Paper, CSCI-RTPC

  2023cites this paper
• A Robust Semi-Direct 3D SLAM for Mobile Robot Based on Dense Optical Flow in Dynamic Scenes

  2023cites this paper
• Video based crowd abnormal behavior detection

  2023cites this paper
• A Multi-label Filter Feature Selection Method Based on Approximate Pareto Dominance

  2023cites this paper
• Utility Model for Visual Recognition using Enhanced Long-term Recurrent Convolutional Network

  2023cites this paper
• Distilled representation using patch-based local-to-global similarity strategy for visual place recognition

  2023cites this paper
• Efficient Hyperbolic Perceptron for Image Classification

  2023cites this paper
• Indoor Scene Recognition: An Attention-Based Approach Using Feature Selection-Based Transfer Learning and Deep Liquid State Machine

  2023cites this paper
• To deliver more information in coverless information hiding

  2023cites this paper
• Weighted Bag of Visual Words with enhanced deep features for melanoma detection

  2023cites this paper
• An adaptive n-gram transformer for multi-scale scene text recognition

  2023cites this paper
• Text Vectorization Method Based on Concept Mining Using Clustering Techniques

  2022cites this paper
• Detection of mitotic HEp-2 cell images: role of feature representation and classification framework under class skew

  2022cites this paper
• An Outdoor Pedestrian Localization Scheme Fusing PDR and VPR

  2022cites this paper
• Linked Open Images: Visual similarity for the Semantic Web

  2022cites this paper
• Subsidiary Prototype Alignment for Universal Domain Adaptation

  2022cites this paper
• Attentional Graph Convolutional Network for Structure-Aware Audiovisual Scene Classification

  2022cites this paper
• Scene Level Image Classification: A Literature Review

  2022cites this paper
• Indoor Activity Recognition Using a Hybrid Generative-Discriminative Approach with Hidden Markov Models and Support Vector Machines

  2022cites this paper
• An Improved SLAM Based On The Indoor Mobile Robot

  2022cites this paper
• Towards Usable Multimedia Event Detection

  2022cites this paper
• Research on Mathematical Method Image Classification of Convolutional Neural Network Based on Firework Algorithm Optimization

  2022cites this paper
• A novel label-based multimodal topic model for social media analysis

  2022cites this paper
• A New Unsupervised Feature Learning Method for Object Recognition using Prior-Knowledge Data

  2022cites this paper
• Indoor Scene Recognition via Object Detection and TF-IDF

  2022cites this paper
• A novel feature selection method using generalized inverted Dirichlet-based HMMs for image categorization

  2022cites this paper
• A Comprehensive Review on Vision-Based Violence Detection in Surveillance Videos

  2022cites this paper
• VividGraph: Learning to Extract and Redesign Network Graphs From Visualization Images

  2022cites this paper
• Efficient CNN with uncorrelated Bag of Features pooling

  2022cites this paper
• Knowledge-guided land pattern depiction for urban land use mapping: A case study of Chinese cities

  2022cites this paper
• DESSERT: An Efficient Algorithm for Vector Set Search with Vector Set Queries

  2022cites this paper
• A Comprehensive Review on Vision-based Violence Detection in Surveillance Videos

  2022influential citation
• Product Based Classification of Bulk Food Grains using Bag of Visual Words and Deep Features

  2021cites this paper
• An Efficient Bag-of-Feature Representation for Object Classification

  2021cites this paper
• An evolutionary event detection model using the Matrix Decomposition Oriented Dirichlet Process

  2021cites this paper
• Automatic indoor scene recognition based on mandatory and desirable objects with a simple coding scheme

  2021cites this paper
• AI-Based Analysis of Policies and Images for Privacy-Conscious Content Sharing

  2021cites this paper
• Improved Deep Hashing with Scalable Interblock for Tourist Image Retrieval

  2021cites this paper
• Evaluierung von Merkmalen zur Abbildung von Veränderungen in ungeordneten Bilddaten

  2021cites this paper
• Scene Recognition by Joint Learning of DNN from Bag of Visual Words and Convolutional DCT Features

  2021influential citation
• Thermodynamics of order and randomness in dopant distributions inferred from atomically resolved imaging

  2021cites this paper
• HAMIL: Hierarchical Aggregation-Based Multi-Instance Learning for Microscopy Image Classification

  2021cites this paper
• Image Retrieval using Bag-of-Features for Lung Cancer Classification

  2021cites this paper
• Multi-Faceted Hierarchical Image Segmentation Taxonomy (MFHIST)

  2021cites this paper
• Vision-Based Human Detection Techniques: A Descriptive Review

  2021influential citation
• Point Pattern Feature-Based Anomaly Detection for Manufacturing Defects, in the Random Finite Set Framework

  2021cites this paper
• A Multi-Level Convolution Pyramid Semantic Fusion Framework for High-Resolution Remote Sensing Image Scene Classification and Annotation

  2021cites this paper
• Structured Inverted-File k-Means Clustering for High-Dimensional Sparse Data

  2021cites this paper
• RIT Scholar Works RIT Scholar Works

  2021cites this paper
• Content-Based Image Retrieval Using Deep Learning

  2021cites this paper
• Automatic Scale Severity Assessment Method in Psoriasis Skin Images Using Local Descriptors

  2020cites this paper
• A Novel Algorithm to Classify Hand Drawn Sketches with Respect to Content Quality

  2020influential citation
• Bag-of-Attributes Representation: A Vector Space Model for Electronic Health Records Analysis in OMOP

  2020cites this paper
• High-level image representation-based on Gestalt theory for image classification

  2020cites this paper
• Multi-Instance Learning Algorithm Based on LSTM for Chinese Painting Image Classification

  2020cites this paper
• Combination of spatially enhanced bag-of-visual-words model and genuine difference subspace for fake coin detection

  2020cites this paper
• Multi-Temporal Scene Classification and Scene Change Detection With Correlation Based Fusion

  2020cites this paper
• A Novel Coverless Information Hiding Method Based on the Most Significant Bit of the Cover Image

  2020cites this paper
• Multi-deep features fusion for high-resolution remote sensing image scene classification

  2020cites this paper
• Near-Duplicate Image Detection System Using Coarse-to-Fine Matching Scheme Based on Global and Local CNN Features

  2020cites this paper
• Relationship between Machine-Learning Image Classification of T2-Weighted Intramedullary Hypointensity on 3 Tesla Magnetic Resonance Imaging and Clinical Outcome in Dogs with Severe Spinal Cord Injury

  2020cites this paper
• The hypergeometric test performs comparably to TF-IDF on standard text analysis tasks

  2020cites this paper
• A bag-of-words feature engineering approach for assessing health conditions using accelerometer data

  2020cites this paper
• Survey on Scene Classification techniques

  2020cites this paper
• Visual Search Target Inference in Natural Interaction Settings with Machine Learning

  2020cites this paper
• KSR-BOF: a new and exemplified method (as KSRs method) for image classification

  2020influential citation