Learning to Recognize Objects from Unseen Modalities

Christoudias, C. Mario; Urtasun, Raquel; Salzmann, Mathieu; Darrell, Trevor

doi:10.1007/978-3-642-15549-9_49

Cited by 19 publications

(21 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although effective, it was limited to transferring information between RGB models. Other approaches have been proposed to transfer generic information across modalities [8], but have only been shown with weak detection models. b) Region Proposals: We note that many topperforming supervised object detection methods [15] and weakly supervised methods [41], [24] rely on a good set of bottom-up bounding box object candidates.…”

Section: Related Workmentioning

confidence: 99%

Cross-modal adaptation for RGB-D detection

Hoffman

Gupta

Leong

et al. 2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Automatic detection of depression has attracted increasing attention from researchers in psychology, computer science , linguistics, and related disciplines. As a result, promising depression detection systems have been reported. This paper surveys these efforts by presenting the first cross-modal review of depression detection systems and discusses best practices and most promising approaches to this task.

show abstract

Section: Related Workmentioning

confidence: 99%

Cross-modal adaptation for RGB-D detection

Hoffman

Gupta

Leong

et al. 2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

show abstract

“…12. We used the three types of precomputed pairwise distances provided on the web 6 of Christoudias et al (2010); for the details of the distances, refer to that paper. The classification accuracies are evaluated by three-fold cross validations and are shown in Table 8.…”

Section: Fig 11 Oxford Flower Datasetmentioning

confidence: 99%

Low-Rank Bilinear Classification: Efficient Convex Optimization and Extensions

Kobayashi

2014

Int J Comput Vis

View full text Add to dashboard Cite

In pattern classification, it is needed to efficiently treat not only feature vectors but also feature matrices defined as two-way data, while preserving the two-way structure such as spatio-temporal relationships. The classifier for the feature matrix is generally formulated in a bilinear form composed of row and column weights which jointly result in a matrix weight. The rank of the matrix should be low from the viewpoint of generalization performance and computational cost. For that purpose, we propose a low-rank bilinear classifier based on the efficient convex optimization. In the proposed method, the classifier is optimized by minimizing the trace norm of the classifier (matrix) to reduce the rank without any hard constraint on it. We formulate the optimization problem in a tractable convex form and provide the procedure to solve it efficiently with the global optimum. In addition, we propose two novel extensions of the bilinear classifier in terms of multiple kernel learning and cross-modal learning. Through kernelizing the bilinear method, we naturally induce a novel multiple kernel learning. The method integrates both the inter kernels between heterogeneous reproducing kernel Hilbert spaces (RKHSs) and the ordinary kernels within respective RKHSs into a new discriminative kernel in a unified manner using the bilinear model. Besides, for crossmodal learning, we consider to map into the common space the multi-modal features which are subsequently classified in that space. We show that the projection and the classification Communicated by Carlo Colombo.This article is an extended version of the ECCV 2012 conference paper (Kobayashi and Otsu 2012a).. T. Kobayashi (B)National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan e-mail: takumi.kobayashi@aist.go.jp are jointly represented by the bilinear model, and then propose the method to optimize both of them simultaneously in the bilinear framework. In the experiments on various visual classification tasks, the proposed methods exhibit favorable performances compared to the other methods.

show abstract

“…The key conceptual difference is that domain adaptation seeks to apply the training examples in another modality, while image fusion seeks to create a new complementary modality. GP models have also featured in domain adaptation problems, for example to recognise objects in images that have a different resolution to the labelled training data [7].…”

Section: Related Workmentioning

confidence: 99%

Bayesian Fusion for Multi-Modal Aerial Images

Reid¹,

Ramos

Sukkarieh

2013

Robotics: Science and Systems IX

View full text Add to dashboard Cite

Abstract-This paper presents a fusion method to combine aerial images from a low flying Unmanned Aerial Vehicle (UAV) with images of other spectral bands from sources such as satellites or commercial hyperspectral imagers. The proposed method propagates information from high-resolution images into other low-resolution modalities while allowing the images to have different spectral channels. This means the relationship between the high-resolution and low-resolution channels is expected to be non-deterministic, non-linear and non-stationary. A novel Gaussian Process (GP) framework was developed to define a stochastic prior over the estimated images. Its covariance function is computed to replicate the local structure of the high-resolution image, and allows the model to infer a high-resolution estimate from a low-resolution channel. Results are presented for natural images acquired by a UAV in a farmland mapping application.

show abstract

Learning to Recognize Objects from Unseen Modalities

Cited by 19 publications

References 22 publications

Cross-modal adaptation for RGB-D detection

Cross-modal adaptation for RGB-D detection

Low-Rank Bilinear Classification: Efficient Convex Optimization and Extensions

Bayesian Fusion for Multi-Modal Aerial Images

Contact Info

Product

Resources

About