Kernel Principal Component Analysis
ICANN '97 Proceedings of the 7th International Conference on Artificial Neural Networks
Unsupervised Improvement of Visual Detectors using Co-Training
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Semi-Supervised Cross Feature Learning for Semantic Concept Detection in Videos
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Priors for People Tracking from Small Training Sets
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
A Visual Vocabulary for Flower Classification
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Co-Adaptation of audio-visual speech and gesture classifiers
Proceedings of the 8th international conference on Multimodal interfaces
Gaussian Processes for Object Categorization
International Journal of Computer Vision
Adapting visual category models to new domains
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Efficient optimization for low-rank integrated bilinear classifiers
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Efficient similarity derived from kernel-based transition probability
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI
| Hi-index | 0.00 |
In this paper we investigate the problem of exploiting multiple sources of information for object recognition tasks when additional modalities that are not present in the labeled training set are available for inference. This scenario is common to many robotics sensing applications and is in contrast with the assumption made by existing approaches that require at least some labeled examples for each modality. To leverage the previously unseen features, we make use of the unlabeled data to learn a mapping from the existing modalities to the new ones. This allows us to predict the missing data for the labeled examples and exploit all modalities using multiple kernel learning. We demonstrate the effectiveness of our approach on several multi-modal tasks including object recognition from multi-resolution imagery, grayscale and color images, as well as images and text. Our approach outperforms multiple kernel learning on the original modalities, as well as nearest-neighbor and bootstrapping schemes.