Tools
Sorted by:
Try your query at:
 |
 |
 |
 |
 |
 |
Results 11 - 20
of
246
Image segmentation by probabilistic bottom-up aggregation and cue integration
, 2007
"... We present a parameter free approach that utilizes multiple cues for image segmentation. Beginning with an image, we execute a sequence of bottom-up aggregation steps in which pixels are gradually merged to produce larger and larger regions. In each step we consider pairs of adjacent regions and pro ..."
Abstract
-
Cited by 76 (1 self)
- Add to MetaCart
We present a parameter free approach that utilizes multiple cues for image segmentation. Beginning with an image, we execute a sequence of bottom-up aggregation steps in which pixels are gradually merged to produce larger and larger regions. In each step we consider pairs of adjacent regions
Models of bottom-up attention and saliency
- Tsotsos (Eds.), Neurobiology of Attention, Elsevier
, 2005
"... Abstract: Visually conspicuous, or so-called salient, stimuli often have the capability of attracting fo-cal visual attention towards their locations. Several computational architectures subserving this bottom-up, stimulus-driven, spatiotemporal deployment of attention are reviewed in this article. ..."
Abstract
-
Cited by 21 (0 self)
- Add to MetaCart
aware of possible preys, mates or predators in their cluttered visual world. It has become clear that attention guides where to look next based on both bottom-up (image-based) and top-down (task-dependent) cues (James, 1890/1981). As such, attention implements an information processing bottleneck, only
LOCUS: Learning Object Classes with Unsupervised Segmentation
- in ICCV
, 2005
"... We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation) which uses a generative probabilistic model to combine bottom-up cues of color and edge with top-down cues of shape and ..."
Abstract
-
Cited by 195 (8 self)
- Add to MetaCart
We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation) which uses a generative probabilistic model to combine bottom-up cues of color and edge with top-down cues of shape
Brief article Chinese and Americans see opposite apparent motions in a Chinese character
, 1997
"... The perceived direction of apparent motion can be in¯uenced by both ``top-down' ' factors, such as expectation, and by ``bottom-up' ' or stimulus-driven factors, such as grouping (Tse, P., Cavanagh, P. & Nakayama, K. (1998). The role of parsing in high-level motion processing ..."
Abstract
- Add to MetaCart
processing. In T. Watanabe, High-level motion processing ± computational, neurobiological and psychophysical perspectives. Cambridge, MA: MIT Press). Here we report the results of a single experiment that pitted top-down cues against bottom-up cues in an apparent motion sequence over the successive strokes
1 Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration
"... Abstract—We present a bottom-up aggregation approach to image segmentation. Beginning with an image, we execute a sequence of steps in which pixels are gradually merged to produce larger and larger regions. In each step we consider pairs of adjacent regions and provide a probability measure to asses ..."
Abstract
- Add to MetaCart
Abstract—We present a bottom-up aggregation approach to image segmentation. Beginning with an image, we execute a sequence of steps in which pixels are gradually merged to produce larger and larger regions. In each step we consider pairs of adjacent regions and provide a probability measure
Unsupervised Tattoo Segmentation Combining Bottom-Up and Top-Down Cues
"... Tattoo segmentation is challenging due to the complexity and large variance in tattoo structures. We have developed a segmentation algorithm for finding tattoos in an image. Our basic idea is split-merge: split each tattoo image into clusters through a bottom-up process, learn to merge the clusters ..."
Abstract
- Add to MetaCart
Tattoo segmentation is challenging due to the complexity and large variance in tattoo structures. We have developed a segmentation algorithm for finding tattoos in an image. Our basic idea is split-merge: split each tattoo image into clusters through a bottom-up process, learn to merge the clusters
An integrated model of top-down and bottom-up attention for optimal object detection
- Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR
, 2006
"... Integration of goal-driven, top-down attention and image-driven, bottom-up attention is crucial for visual search. Yet, previous research has mostly focused on models that are purely top-down or bottom-up. Here, we propose a new model that combines both. The bottom-up component computes the visual s ..."
Abstract
-
Cited by 71 (5 self)
- Add to MetaCart
is maximized. Testing on 750 artificial and natural scenes shows that the model’s predictions are consistent with a large body of available literature on human psychophysics of visual search. These results suggest that our model may provide good approximation of how humans combine bottom-up and top-down cues
Object Localization via Bottom-up and Top-down Image Cues.
"... •Image features play the role of object parts. ..."
Early vision is bottom-up, except for focal attention
- In Cold Spring Harbor Symposia on Quantitative Biology - The Brain
, 1990
"... It is the 30-year anniversary of the introduction of computer-generated random-dot stereograms and cinematograms in psychology (Julesz 1960). These stimuli, together with texture pairs with identical second-order statistics (Julesz 1962), are devoid of all familiarity cues and are briefly presented ..."
Abstract
-
Cited by 13 (0 self)
- Add to MetaCart
It is the 30-year anniversary of the introduction of computer-generated random-dot stereograms and cinematograms in psychology (Julesz 1960). These stimuli, together with texture pairs with identical second-order statistics (Julesz 1962), are devoid of all familiarity cues and are briefly presented
Learning to Attend — From Bottom-Up to Top-Down
"... Abstract. The control of overt visual attention relies on an interplay of bottom-up and top-down mechanisms. Purely bottom-up models may provide a reasonable account of the looking behaviors of young infants, but they cannot accurately account for attention orienting of adults in many natural behavi ..."
Abstract
- Add to MetaCart
Abstract. The control of overt visual attention relies on an interplay of bottom-up and top-down mechanisms. Purely bottom-up models may provide a reasonable account of the looking behaviors of young infants, but they cannot accurately account for attention orienting of adults in many natural
Results 11 - 20
of
246
