In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

FusionGAN: A generative adversarial network for infrared and visible image fusion

Infrared and visible image fusion methods and applications: A survey

Multifocus image fusion using the nonsubsampled contourlet transform

Deep learning for pixel-level image fusion: Recent advances and future prospects

In this paper, a new image fusion algorithm based on fourth order partial differential equations and principal component analysis is introduced. This is for the first time fourth order partial differential equations brought into the context of image fusion. The proposed algorithm is as follows: First, fourth order partial differential equations are applied on each source image to obtain approximation and detail images. Second, principal component analysis is applied on detail images to obtain optimal weights. Third, final detail image is obtained by fusing these detail images with help of optimal weights. Fourth, final approximation image is obtained by employing an average operation on approximation images. Finally, resultant fused image is calculated by combining the final approximation and detail images. Experiments are conducted on standard fusion datasets. Results are analyzed with help of petrovic metrics and further compared with traditional and recent fusion methods. Results justify that performance of the proposed method is superior to state-of-the-art fusion methods. Moreover, reasonable computational time, easy and effective implementation of the proposed method makes it suitable for real time applications.

Multi-sensor image fusion based on fourth order partial differential equations

In this paper, we propose a general purpose, simple and fast fusion algorithm based on guided image filter. 
The proposed method can well combine useful source image information into the fused image supported by multi-scale image decomposition, structure transferring property, visual saliency detection, and weight map construction. Multi-scale image decomposition is appropriate to represent and manipulate image features at various scales. Structure transferring property enabled by our algorithm can induce structures of one source image into the other. A new visual saliency detection based on guided image filter introduced in this paper is able to extract significant regions from visually different images of the same scene. The choice of weight maps helped to integrate the complementary information pixel by pixel at each scale. Experimental outcomes of the proposed method are compared and analyzed with traditional and recent guided image filter-based fusion algorithms in terms of visual quality, fusion metrics and run time. In addition, to enhance fusion results further we made an effort to find a suitable image and video enhancement algorithm. The fusion performance analysis clearly indicates that the proposed method is very promising along with less run time.

Multi-scale Guided Image and Video Fusion: A Fast and Efficient Approach

Image fusion can be performed at various levels of information representation A generic classification is given as pixel, feature, and decision levels In this chapter, our focus in on pixel-level image fusion The pixel-level fusion mainly finds applications in image processing where human perception is given due priority than machine vision Possible applications are digital photography, medical imaging, remote sensing, surveillance, pilot navigation, and so on In this chapter, first a brief introduction, different categories, and traditional pixel-level image fusion approaches are presented Next, new image fusion methods based on pyramids, wavelet filter banks, and edge-preserving decomposition methods are introduced Both qualitative and quantitative analyses are considered for in-depth discussion on these methods

Pixel-Level Image Fusion

This paper describes a region-based multiresolution (MR) image fusion algorithm. The MR segmentations of source images to be fused are obtained by fuzzy c-means clustering. From these MR region representations of all the input images, we obtain a shared MR region representation to label all the input images. The fusion process is guided by these MR region representations. Experiment results using real data show that the proposed algorithm works well in multisensor image fusion.

A region-based image fusion algorithm using multiresolution segmentation

This paper proposes a novel region based image fusion scheme based on multiresolution analysis. The low frequency band of the image multiresolution representation is segmented into important regions, sub-important regions and background regions. Each feature of the regions is used to determine the region’s degree of membership in the multiresolution representation, and then to achieve multiresolution representation of the fusion result. The final image fusion result can be obtained by using the inverse multiresolution transform. Experiments showed that the proposed image fusion method can have better performance than existing image fusion methods.

Gang Liu

Papers

Multi-sensor image fusion based on fourth order partial differential equations

Multi-scale Guided Image and Video Fusion: A Fast and Efficient Approach

Pixel-Level Image Fusion

A region-based image fusion algorithm using multiresolution segmentation

Multiresolution image fusion scheme based on fuzzy region feature