Selective Search for Object Recognition
Explore this paper's citation graph
Summary
This paper introduces selective search which combines the strength of both an exhaustive search and segmentation, and shows that its selective search enables the use of the powerful Bag-of-Words model for recognition.
- Type
- article
- Published
- 2013-04-02
- Cited by
- 5,672
- References
- 49
- Access
- Open access
- OpenAlex
- https://openalex.org/W2088049833
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:216077384
Keywords
Computer science, Artificial intelligence, Segmentation, Pattern recognition (psychology), Object (grammar)
References
- Graph based image segmentation
- Efficient Graph-Based Image Segmentation
- Constrained parametric min-cuts for automatic object segmentation
- The Pascal Visual Object Classes (VOC) Challenge
- Image Parsing: Unifying Segmentation, Detection, and Recognition
- Measuring the Objectness of Image Windows
- Mean Shift: A Robust Approach Toward Feature Space Analysis
- Exploring features in a Bayesian framework for material recognition
- Object recognition as ranking holistic figure-ground hypotheses
- Recognition using regions
- Object detection using a max-margin Hough transform
- Empowering Visual Categorization With the GPU
- Contour Detection and Hierarchical Image Segmentation
- Semantic segmentation using regions and parts
- Real-Time Visual Concept Classification
- An Exemplar Model for Learning Object Classes
- What is an object?
- Video Google: a text retrieval approach to object matching in videos
- Classification using intersection kernel support vector machines is efficient
- Robust Real-Time Face Detection
Cited by
- Object Proposal Generation Using Two-Stage Cascade SVMs
- Automatic Crop Pest Detection Oriented Multiscale Feature Fusion Approach
- A Deep Learning Pipeline for Image Understanding and Acoustic Modeling
- Do More Dropouts in Pool5 Feature Maps for Better Object Detection
- Context Based Image Analysis With Application in Dietary Assessment and Evaluation
- Exploiting Language Models for Visual Recognition
- A Stochastic Approach for Selective Search Algorithms
- Actions and Attributes from Wholes and Parts
- Unsupervised Visual Representation Learning by Context Prediction
- Convolutional Channel Features
- How Well Can a CNN Marginalize Simple Nuisances It is Designed for?
- Recognition of Partially Occluded Objects Based on the Three Different Color Spaces (RGB, YCbCr, HSV)
- End-to-End People Detection in Crowded Scenes
- Ego-Object Discovery in Lifelogging Datasets
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Cascaded Sparse Spatial Bins for Efficient and Effective Generic Object Detection
- Adding discriminative power to a generative hierarchical compositional model using histograms of compositions
- Learning to Segment Object Candidates
- Enhanced image and video representation for visual recognition
- Contextual Action Recognition with R*CNN
Related papers
- Intelligent Detection of Missing and Unattended Objects in Complex Scene of Surveillance Videos
- A segmentation system with model-assisted completion of video objects
- Automatic Video Object Segmentation with Opacity Estimate
- Towards Object Detection from Motion
- Object extraction from stereo vision using continuity of disparity map
- Object Recognition Method for Industrial Intelligent Robot
- 2A1-S02 Unknown Object Detection and Picking Based on Impacting and Keypoint Tracking
- AN EFFICIENT DETECTION APPROACHFOR VISUAL SURVEILLANCE SYSTEMUSING MORPHOLOGY
- Object recognition and 3D reconstruction of occluded objects using binocular stereo