Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
Explore this paper's citation graph
Summary
The performance of the spatial envelope model shows that specific information about object shape or identity is not a requirement for scene categorization and that modeling a holistic representation of the scene informs about its probable semantic category.
- Type
- article
- Published
- 2001-05-01
- Cited by
- 7,172
- References
- 47
- OpenAlex
- https://openalex.org/W1566135517
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:11664336
Keywords
Naturalness, Representation (politics), Categorization, Computer science, Artificial intelligence
References
- Global semantic classification of scenes using power spectrum templates
- RECOVERING INTRINSIC SCENE CHARACTERISTICS FROM IMAGES
- Does Figural Goodness Influence the Processing and Representation of SpatialLayout
- Pattern Recognition and Neural Networks
- Change-blindness as a result of ‘mudsplashes’
- Framing pictures: the role of knowledge in automatized encoding and memory for gist.
- Textural Features Corresponding to Visual Perception
- Family Resemblances: Studies in the Internal Structure of Categories
- A Demonstration of the Visual Importance and Flexibility of Spatial-Frequency Amplitude and Phase
- Using Discriminant Eigenfeatures for Image Retrieval
- Textural features corresponding to textural properties
- Region-based image querying
- On image classification: city images vs. landscapes
- What Does the Retina Know about Natural Scenes?
- Review of "Reviews Vision, by David Marr" San Franclsco: WH Freeman, 1982
- Similarity and Features of Natural Textures
- The relative importance of local phase and local amplitude in patchwise image reconstruction
- What Is the Goal of Sensory Coding?
- Categories of environmental scenes
- Meaning in visual search.
Cited by
- Real-time Road Scene Classification using Infrared Images
- Scene Classification using Spatial Relationship between Local Posterior Probabilities
- Contextual priming for artificial visual perception
- Symmetric Graph Regularized Constraint Propagation
- Classifying objects based on their visual similarity to target categories
- Classification multi-modèles des images dans les bases Hétérogènes. (Multi-model image classification in heterogeneous databases)
- Region- and edge-based configurational effects in texture segmentation.
- Context-based Media Geotagging of Personal Photos
- Rapid visual categorization of natural scene contexts with equalized amplitude spectrum and increasing phase noise.
- Scene perception in age-related macular degeneration.
- Sketch-Based Image Retrieval: Benchmark and Bag-of-Features Descriptors
- Detection of Visual Concepts and Annotation of Images Using Predictive Clustering Trees
- From spatial frequency contrast to edge preponderance: the differential modulation of early visual evoked potentials by natural scene stimuli
- When does repeated search in scenes involve memory? Looking AT versus looking FOR objects in scenes
- Random Sampling Image to Class Distance for Photo Annotation
- Manifold Regularized Multitask Learning for Semi-Supervised Multilabel Image Classification
- Cross-Domain Object Recognition Via Input-Output Kernel Analysis
- Scene Recognition by Manifold Regularized Deep Learning Architecture
- Linking Major Depression and The Neural Substrates of Associative Processing
- In Defense of Locality-Sensitive Hashing
Related papers
- Modeling categorization of scenes containing consistent versus inconsistent objects.
- Disentangling diagnostic object properties for human scene categorization
- Localized information is necessary for scene categorization, including the Natural/Man-made distinction.
- Is one object enough? Diagnosticity of single objects for fast scene categorization
- Processing scene context: fast categorization and object interference.
- Biologically-inspired object recognition system for recognizing natural scene categories
- Categorization Goals Modulate the Use of Natural Scene Statistics
- Structural, not spectral properties underlie human categorization of natural scenes
- Seeing the closed+camouflage+natural=forest for the trees: Rapid scene categorization can be mediated by conjunctions of global scene properties