Hamming embedding similarity-based image classification
Proceedings of the 2nd ACM International Conference on Multimedia Retrieval
Local goemetrical feature with spatial context for shape-based 3D model retrieval
EG 3DOR'12 Proceedings of the 5th Eurographics conference on 3D Object Retrieval
Graph matching via sequential monte carlo
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Unsupervised and supervised visual codes with restricted boltzmann machines
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Semantic segmentation with second-order pooling
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Measuring image distances via embedding in a semantic manifold
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
Real-Time exact graph matching with application in human action recognition
HBU'12 Proceedings of the Third international conference on Human Behavior Understanding
Comparison of mid-level feature coding approaches and pooling strategies in visual concept detection
Computer Vision and Image Understanding
A spectral-multiplicity-tolerant approach to robust graph matching
Pattern Recognition
Projective analysis for 3D shape segmentation
ACM Transactions on Graphics (TOG)
| Hi-index | 0.00 |
This paper addresses the problem of category-level image classification. The underlying image model is a graph whose nodes correspond to a dense set of regions, and edges reflect the underlying grid structure of the image and act as springs to guarantee the geometric consistency of nearby regions during matching. A fast approximate algorithm for matching the graphs associated with two images is presented. This algorithm is used to construct a kernel appropriate for SVM-based image classification, and experiments with the Caltech 101, Caltech 256, and Scenes datasets demonstrate performance that matches or exceeds the state of the art for methods using a single type of features.