Object recognition with features inspired by visual cortex
Citations
23,074 citations
8,059 citations
Cites background from "Object recognition with features in..."
...For example, the standard model of the visual cortex (Hubel and Wiesel 1962; Serre et al. 2005; Ranzato et al. 2007) suggests that (roughly speaking) the brain first extracts edges, then patches, then surfaces, then objects, etc....
[...]
4,545 citations
4,146 citations
4,087 citations
Cites methods from "Object recognition with features in..."
...Motivated by the organization of visual cortex, a similar model, called HMAX (Serre et al., 2005), has been developed for visual object recognition....
[...]
References
16,989 citations
"Object recognition with features in..." refers background or methods or result in this paper
...We also compared our C2 features to SIFT-based features [12]....
[...]
...The SIFT-based features [12], for instance, have been shown to excel in the re-detection of a previously seen object under new image transformations....
[...]
...At the other extreme, histogram-based descriptors [12, 2] are very robust with respect to object transformations....
[...]
13,037 citations
6,693 citations
4,713 citations
"Object recognition with features in..." refers background in this paper
...Models of biological vision [5, 13, 16, 1] have not been extended to deal with real-world object recognition tasks (e....
[...]
3,478 citations
"Object recognition with features in..." refers background or methods in this paper
...1It is likely that our (non-biological) final classifier could correspond to the task-specific circuits found in prefrontal cortex (PFC) and C2 units with neurons in inferotemporal (IT) cortex [16]....
[...]
...Our system follows the standard model of object recognition in primate cortex [16], which summarizes in a quantitative way what most visual neuroscientists agree on: the first few hundreds milliseconds of visual processing in primate cortex follows a mostly feedforward hierarchy....
[...]
...The model originally used a very simple static dictionary of features (for the recognition of segmented objects) although it was suggested in [16] that features in intermediate layers should instead be learned from visual experience....
[...]
...Models of biological vision [5, 13, 16, 1] have not been extended to deal with real-world object recognition tasks (e....
[...]
...In particular, Riesenhuber & Poggio showed that such a class of models accounts quantitatively for the tuning properties of view-tuned units in inferotemporal cortex (tested with idealized object stimuli on uniform backgrounds), which respond to images of the learned object more strongly than to distractor objects, despite significant changes in position and size [16]....
[...]