Joint semantic segmentation by searching for compatible-competitive references
Proceedings of the 20th ACM international conference on Multimedia
Annotation propagation in large image databases via dense image correspondence
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
PATCHMATCHGRAPH: building a graph of dense patch correspondences for label transfer
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Beyond the line of sight: labeling the underlying surfaces
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Local label descriptor for example based semantic image labeling
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
International Journal of Computer Vision
Projective analysis for 3D shape segmentation
ACM Transactions on Graphics (TOG)
Fusion of 3D-LIDAR and camera data for scene parsing
Journal of Visual Communication and Image Representation
| Hi-index | 0.14 |
While there has been a lot of recent work on object recognition and image understanding, the focus has been on carefully establishing mathematical models for images, scenes, and objects. In this paper, we propose a novel, nonparametric approach for object recognition and scene parsing using a new technology we name label transfer. For an input image, our system first retrieves its nearest neighbors from a large database containing fully annotated images. Then, the system establishes dense correspondences between the input image and each of the nearest neighbors using the dense SIFT flow algorithm [28], which aligns two images based on local image structures. Finally, based on the dense scene correspondences obtained from SIFT flow, our system warps the existing annotations and integrates multiple cues in a Markov random field framework to segment and recognize the query image. Promising experimental results have been achieved by our nonparametric scene parsing system on challenging databases. Compared to existing object recognition approaches that require training classifiers or appearance models for each object category, our system is easy to implement, has few parameters, and embeds contextual information naturally in the retrieval/alignment procedure.