Object-Centric spatial pooling for image classification
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Unsupervised discovery of mid-level discriminative patches
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
In defence of negative mining for annotating weakly labelled data
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Learning hybrid part filters for scene recognition
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Latent pyramidal regions for recognizing scenes
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Spring lattice counting grids: scene recognition using deformable positional constraints
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI
Scene recognition on the semantic manifold
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
Data decomposition and spatial mixture modeling for part based model
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Object templates for visual place categorization
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part IV
Weakly-supervised multi-class object detection using multi-type 3D features
Proceedings of the 21st ACM international conference on Multimedia
Robust subspace discovery via relaxed rank minimization
Neural Computation
Object Bank: An Object-Level Image Representation for High-Level Visual Recognition
International Journal of Computer Vision
| Hi-index | 0.00 |
Weakly supervised discovery of common visual structure in highly variable, cluttered images is a key problem in recognition. We address this problem using deformable part-based models (DPM's) with latent SVM training [6]. These models have been introduced for fully supervised training of object detectors, but we demonstrate that they are also capable of more open-ended learning of latent structure for such tasks as scene recognition and weakly supervised object localization. For scene recognition, DPM's can capture recurring visual elements and salient objects; in combination with standard global image features, they obtain state-of-the-art results on the MIT 67-category indoor scene dataset. For weakly supervised object localization, optimization over latent DPM parameters can discover the spatial extent of objects in cluttered training images without ground-truth bounding boxes. The resulting method outperforms a recent state-of-the-art weakly supervised object localization approach on the PASCAL-07 dataset.