- Bayesian learning; Bayesian signal processing (MLR-BAYL)
- Bounds on performance (MLR-PERF)
- Applications in Systems Biology (MLR-SYSB)
- Applications in Music and Audio Processing (MLR-MUSI)
- Applications in Data Fusion (MLR-FUSI)
- Cognitive information processing (MLR-COGP)
- Distributed and Cooperative Learning (MLR-DIST)
- Learning theory and algorithms (MLR-LEAR)
- Neural network learning (MLR-NNLR)
- Information-theoretic learning (MLR-INFO)
- Independent component analysis (MLR-ICAN)
- Graphical and kernel methods (MLR-GRKN)
- Other applications of machine learning (MLR-APPL)
- Pattern recognition and classification (MLR-PATT)
- Source separation (MLR-SSEP)
- Sequential learning; sequential decision methods (MLR-SLER)
![](https://sigport.org/sites/default/files/styles/home/public/MLSP_2019_0.jpg?itok=WfpQ022v)
- Read more about Deep Clustering based on a Mixture of Autoencoders
- Log in to post comments
In this paper we propose a Deep Autoencoder Mixture Clustering(DAMIC) algorithm based on a mixture of deep autoencoders whereeach cluster is represented by an autoencoder. A clustering networktransforms the data into another space and then selects one of theclusters. Next, the autoencoder associated with this cluster is usedto reconstruct the data-point. The clustering algorithm jointly learnsthe nonlinear data representation and the set of autoencoders. Theoptimal clustering is found by minimizing the reconstruction loss ofthe mixture of autoencoder network.
- Categories:
![](https://sigport.org/sites/default/files/styles/home/public/MLSP_2019_0.jpg?itok=WfpQ022v)
- Read more about VAE/WGAN-BASED IMAGE REPRESENTATION LEARNING FOR POSE-PRESERVING SEAMLESS IDENTITY REPLACEMENT IN FACIAL IMAGES
- Log in to post comments
We present a novel variational generative adversarial network (VGAN) based on Wasserstein loss to learn a latent representation
from a face image that is invariant to identity but preserves head-pose information. This facilitates synthesis of a realistic face
image with the same head pose as a given input image, but with a different identity. One application of this network is in
privacy-sensitive scenarios; after identity replacement in an image, utility, such as head pose, can still
- Categories:
![](https://sigport.org/sites/default/files/styles/home/public/MMSP_2019_0.jpg?itok=z1vEoTc7)
- Read more about Super-resolution of Omnidirectional Images Using Adversarial Learning
- Log in to post comments
An omnidirectional image (ODI) enables viewers to look in every direction from a fixed point through a head-mounted display providing an immersive experience compared to that of a standard image. Designing immersive virtual reality systems with ODIs is challenging as they require high resolution content. In this paper, we study super-resolution for ODIs and propose an improved generative adversarial network based model which is optimized to handle the artifacts obtained in the spherical observational space.
- Categories:
![](https://sigport.org/sites/default/files/styles/list/public/front.png?itok=xv-_cG6h)
- Read more about Injective State-Image Mapping facilitates Visual Adversarial Imitation Learning
- Log in to post comments
The growing use of virtual autonomous agents in applications like games and entertainment demands better control policies for natural-looking movements and actions. Unlike the conventional approach of hard-coding motion routines, we propose a deep learning method for obtaining control policies by directly mimicking raw video demonstrations. Previous methods in this domain rely on extracting low-dimensional features from expert videos followed by a separate hand-crafted reward estimation step.
mmps_final.pdf
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
- Categories:
![](https://sigport.org/sites/default/files/styles/home/public/ICIP_2019_0.jpg?itok=d6pml7cm)
- Read more about Single-image rain removal via multi-scale cascading image generation
- Log in to post comments
A novel single-image rain removal method is proposed based on multi-scale cascading image generation (MSCG). In particular, the proposed method consists of an encoder extracting multi-scale features from images and a decoder generating de-rained images with a cascading mechanism. The encoder ensembles the convolution neural networks using the kernels with different sizes, and integrates their outputs across different scales.
- Categories:
![](https://sigport.org/sites/default/files/styles/home/public/ICIP_2019_0.jpg?itok=d6pml7cm)
- Read more about A NOVEL MONOCULAR DISPARITY ESTIMATION NETWORK WITH DOMAIN TRANSFORMATION AND AMBIGUITY LEARNING
- Log in to post comments
Convolutional neural networks (CNN) have shown state-of-the-art results for low-level computer vision problems such as stereo and monocular disparity estimations, but still, have much room to further improve their performance in terms of accuracy, numbers of parameters, etc. Recent works have uncovered the advantages of using an unsupervised scheme to train CNN’s to estimate monocular disparity, where only the relatively-easy-to-obtain stereo images are needed for training.
- Categories:
![](https://sigport.org/sites/default/files/styles/home/public/ICIP_2019_0.jpg?itok=d6pml7cm)
- Read more about MULTI TASK LEARNING OF DEPTH FROM TELE AND WIDE STEREO IMAGE PAIRS
- 1 comment
- Log in to post comments
- Categories:
![](https://sigport.org/sites/default/files/styles/list/public/Deep%20Refinement%20of%20Image%20Matting.jpg?itok=HEEej5xT)
Portrait segmentation is becoming a hot topic nowadays.
In this paper we propose a novel framework to cope with
the high precision requirements that portrait segmentation
demands on boundary area by deep refinement of the
portrait matting. Our approach introduces three novel
techniques. First, a trimap is proposed by fusing information
coming from two well-known techniques for image
segmentation, i.e., Mask R-CNN and DensePose. Second,
an alpha matting algorithm runs over the previous trimap
- Categories:
![](https://sigport.org/sites/default/files/styles/home/public/ICIP_2019_0.jpg?itok=d6pml7cm)
Even though zero padding is usually a staple in convolutional
neural networks to maintain the output size, it is highly suspicious
because it significantly alters the input distribution
around border region. To mitigate this problem, in this paper,
we propose a new padding technique termed as distribution
padding. The goal of the method is to approximately maintain
the statistics of the input border regions. We introduce
two different ways to achieve our goal. In both approaches,
the padded values are derived from the means of the border
- Categories:
![](https://sigport.org/sites/default/files/styles/home/public/ICASSP_2019_0.jpg?itok=OnlvXQeZ)
- Read more about A History-based Stopping Criterion in Recursive Bayesian State Estimation
- Log in to post comments
In dynamic state-space models, the state can be estimated through recursive computation of the posterior distribution of the state given all measurements. In scenarios where active sensing/querying is possible, a hard decision is made when the state posterior achieves a pre-set confidence threshold. This mandate to meet a hard threshold may sometimes unnecessarily require more queries. In application domains where sensing/querying cost is of concern, some potential accuracy may be sacrificed for greater gains in sensing cost.
- Categories: