When is scene identification just texture recognition?

By Laura Walker Renninger, Jitendra Malik. 2004

271 citations recorded by the source corpus.

Subjects were asked to identify scenes after very brief exposures (<70 ms). Their performance was always above chance and improved with exposure duration, confirming that subjects can get the gist of a scene with one fixation. We propose that a simple texture analysis of the image can provide a useful cue towards rapid scene identification. Our model learns texture features across scene categories and then uses this knowledge to identify new scenes. The texture analysis leads to similar identifications and confusions as subjects with limited processing time. We conclude that early scene identification can be explained with a simple texture recognition model.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

SUN Database: Exploring a Large Collection of Scene Categories (2014, background): “Whereas most computational work on scene and place recognition has used a limited number of semantic categories, representing typical indoor and outdoor settings (Lazebnik et al. 2006; Fei-Fei and Perona 2005; Renninger and Malik 2004; Vogel and Schiele 2007; Oliva and Torralba 2001; Barnard et al. ”
Modeling Search for People in 900 Scenes: A combined source model of eye guidance (2009, unknown): “…years (Bosch, Zisserman, & Mun˜oz, 2008; Fei Fei & Perona, 2005; Grossberg, & Huang, 2009; Lazebnik, Schmidt, & Ponce, 2006; Oliva & Torralba, 2001; Renninger & Malik, 2004; Vogel & Schiele, 2007), with most of the approaches summarizing an image’s ‘‘global’’ features by pooling responses from…”
From BoW to CNN: Two Decades of Texture Representation for Texture Classification (2018, background): “The importance of texture representations (such as Gabor filters [148], LBP [163], BoT [114], Fisher Vector (FV) [203], and wavelet Scattering Convolution Networks (ScatNet) [24]) is that they were found to be well applicable to other problems of image understanding and computer vision, such as obje”
Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search. (2006, background): “Correspondingly, computational modeling work has shown that real world scenes can be interpreted as a member of a basic-level category based on holistic mechanisms, without the need for segmentation and grouping stages (Fei Fei & Perona, 2005; Oliva & Torralba, 2001; Walker Renninger & Malik, 2004; ”
Separate channels for processing form, texture, and color: evidence from FMRI adaptation and visual object agnosia. (2010, background): “(Oliva and Schyns 1997) and texture (Renninger and Malik 2004) in the rapid categorization of scenes (scene ‘‘gist’’).”
Trajectons: Action recognition through the motion analysis of tracked features (2009, background): “These approaches are backed by some degree of psychological research suggesting that even human vision may employ unstructured statistical approaches at early stages [15], and can scale well even to large datasets when used with sparse features [5].”