Related papers: Efficient SDP Inference for Fully-connected CRFs B…

Numerous retrieval models, including sparse, dense and llm-based methods, have demonstrated remarkable performance in predicting the relevance between queries and corpora. However, the preliminary effectiveness analysis experiments indicate…

We propose a novel and principled hybrid CNN+CRF model for stereo estimation. Our model allows to exploit the advantages of both, convolutional neural networks (CNNs) and conditional random fields (CRFs) in an unified approach. The CNNs…

We develop a new collaborative filtering (CF) method that combines both previously known users' preferences, i.e. standard CF, as well as product/user attributes, i.e. classical function approximation, to predict a given user's interest in…

While deep learning has been successfully applied to many real-world computer vision tasks, training robust classifiers usually requires a large amount of well-labeled data. However, the annotation is often expensive and time-consuming.…

We explore the efficiency of the CRF inference module beyond image level semantic segmentation. The key idea is to combine the best of two worlds of semantic co-labeling and exploiting more expressive models. Similar to [Alvarez14] our…

Recent saliency models extensively explore to incorporate multi-scale contextual information from Convolutional Neural Networks (CNNs). Besides direct fusion strategies, many approaches introduce message-passing to enhance CNN features or…

Supervised dimensionality reduction strategies have been of great interest. However, current supervised dimensionality reduction approaches are difficult to scale for situations characterized by large datasets given the high computational…

Image Super Resolution (SR) finds applications in areas where images need to be closely inspected by the observer to extract enhanced information. One such focused application is an offline forensic analysis of surveillance feeds. Due to…

Discrete optimization is a central problem in artificial intelligence. The optimization of the aggregated cost of a network of cost functions arises in a variety of problems including (W)CSP, DCOP, as well as optimization in stochastic…

Across many domains, real-world problems can be represented as a network. Nodes represent domain-specific elements and edges capture the relationship between elements. Leveraging high-performance computing and optimized link prediction…

The Conditional Random Field as a Recurrent Neural Network layer is a recently proposed algorithm meant to be placed on top of an existing Fully-Convolutional Neural Network to improve the quality of semantic segmentation. In this paper, we…

3D decomposition/segmentation still remains a challenge as large-scale 3D annotated data is not readily available. Contemporary approaches typically leverage 2D machine-generated segments, integrating them for 3D consistency. While the…

Spectral computed tomography has received considerable interest in recent years since spectral measurements contain much richer information about the object of interest. In spectral computed tomography, we are interested in the energy…

We consider the class of optimization problems arising from computationally intensive L1-regularized M-estimators, where the function or gradient values are very expensive to compute. A particular instance of interest is the L1-regularized…

A new approach is proposed, namely CSSF MIMO radar, which applies the technique of step frequency (SF) to compressive sensing (CS) based multi-input multi-output (MIMO) radar. The proposed approach enables high resolution range, angle and…

In this paper we establish a mathematically rigorous connection between Causal inference (C-inf) and the low-rank recovery (LRR). Using Random Duality Theory (RDT) concepts developed in [46,48,50] and novel mathematical strategies related…

Conventional change detection methods require a large number of images to learn background models or depend on tedious pixel-level labeling by humans. In this paper, we present a weakly supervised approach that needs only image-level labels…

This paper introduces a deep architecture for segmenting 3D objects into their labeled semantic parts. Our architecture combines image-based Fully Convolutional Networks (FCNs) and surface-based Conditional Random Fields (CRFs) to yield…

Image or object recognition is an important task in computer vision. With the hight-speed processing power on modern platforms and the availability of mobile phones everywhere, millions of photos are uploaded to the internet per minute, it…

We present a novel feature matching algorithm that systematically utilizes the geometric properties of features such as position, scale, and orientation, in addition to the conventional descriptor vectors. In challenging scenes with the…