When is scene recognition just texture recognition?
Open accessThe DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
It remains unclear whether humans recognize scenes by using “diagnostic objects” or by using global attributes of the scene. Based on our work, we argue that not all scenes are created equal and that varying levels of information are needed for recognition at different category levels. We hypothesize that there is a time course to scene processing. Global scene information may be accessed early and can be used for superordinate-level categorization, but recognition of “diagnostic objects” takes longer and is necessary for basic-level categorization. EXPERIMENT ONE: Subjects were asked to divide grayscale images into multiple sub-groups based on global visual similarity, while ignoring the object and scene content of the image. We found that the resulting sub-groups could be categorized at the superordinate-level as natural or man-made scenes, but categorization beyond that level was not achieved. EXPERIMENT TWO: Subjects were shown grayscale images of scenes, followed by two basic-level category choices. The task was to select the category that best described the image. When subjects were allowed to view the images for 150ms, they demonstrated nearly perfect performance. When the viewing time was reduced to 30ms, subjects made more errors categorizing man-made scenes than natural scenes. The distribution of errors revealed a higher level of confusion among indoor scenes. EXPERIMENT THREE: A simple texture-based classifier was tested and compared to human performance at 30ms. The classifier made similar errors, but was outperformed overall. Based on this result, it is clear that subjects are using more than just global texture to do basic-level scene classification in 30ms. CONCLUSIONS: Global properties of a scene, such as texture and shape, may be instructive in the early, superordinate-level categorization of scenes. Basic-level categorization may require more time and more information, such as the processing of “diagnostic objects”.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Speed of processing in the human visual system
Thorpe, S., Fize, D., & Marlot, C. (1996) · Nature · doi:10.1038/381520a0 · Cited by 3,538
Textons, the elements of texture perception, and their interactions
Julesz, B. (1981) · Nature · doi:10.1038/290091a0 · Cited by 1,703 · cited 1×
“Julesz (1981, 1986) proposed that the first order statistics of " textons " determine the strength of texture discrimination.”
Cited by
SUN database: Large-scale scene recognition from abbey to zoo
Xiao, J., Hays, J., Ehinger, K. A., Oliva, A., & Torralba, A. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539970 · Cited by 3,283
80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition
Torralba, A., Fergus, R., & Freeman, W. T. (2008) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.128 · Cited by 1,921
Robust Object Recognition with Cortex-Like Mechanisms
Serre, T., Wolf, L., Bileschi, S., Riesenhuber, M., & Poggio, T. (2007) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.56 · Cited by 1,667
IM2GPS: estimating geographic information from a single image
Hays, J., & Efros, A. A. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587784 · Cited by 877
On the give and take between event apprehension and utterance formulation
Gleitman, L. R., January, D., Nappa, R., & Trueswell, J. C. (2007) · Journal of Memory and Language · doi:10.1016/j.jml.2007.01.007 · Cited by 426
Metadata
- Authors
- Walker, L. L., & Malik, J.
- Venue
- Journal of Vision
- Published
- 2010-03-15
- Volume
- 2
- Issue
- 7
- Pages
- 255-255
- ISSN
- 1534-7362 (ISSN-L)
- OpenAlex
- W2070093385
- Cited by
- 44
- References
- 2
- FWCI
- 3.62
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.