Landmark Selection for Zero-shot Learning

Zero-shot learning (ZSL) is an emerging research topic whose goal is to build recognition models for previously unseen classes. The basic idea of ZSL is based on heterogeneous feature matching which learns a compatibility function between image and class features using seen classes. The function is constructed based on one-vs-all training in which each class has only one class feature and many image features. Existing ZSL works mostly treat all image features equivalently. However, in this paper we argue that it is more reasonable to use some representative cross-domain data instead of all. Motivated by this idea, we propose a novel approach, termed as Landmark Selection(LAST) for ZSL. LAST is able to identify representative cross-domain features which further lead to better image-class compatibility function. Experiments on several ZSL datasets including ImageNet demonstrate the superiority of LAST to the state-of-the-arts.

Download Full-text

Identity Verification Based on Facial Pose Pool and Bag of Words Model

Journal of Advanced Computational Intelligence and Intelligent Informatics ◽

10.20965/jaciii.2017.p0448 ◽

2017 ◽

Vol 21 (3) ◽

pp. 448-455 ◽

Cited By ~ 1

Author(s):

Wangbin Chu ◽

◽

Yepeng Guan

Keyword(s):

Spatial Information ◽

Gaussian Mixture ◽

Image Features ◽

Superior Performance ◽

Bag Of Words ◽

Incremental Clustering ◽

Identity Verification ◽

Facial Identity ◽

The Arts ◽

Novel Approach

There are many challenges for face based identity verification. It is one of fundamental topics in image processing and video analysis, and so on. A novel approach has been developed for facial identity verification based on a facial pose pool, which is constructed in an incremental clustering way to find both facial spatial information and orientation diversity. Bag of words is selected to extract image features from the facial pose pool in affine SIFT descriptor. The visual codebook is generated ink-means and Gaussian mixture model. Posterior pseudo probabilities are used to compute the similarities between each visual word and corresponding local features for image representation. Comparisons with some state-of-the-arts have highlighted the superior performance of the proposed method.

Download Full-text

Optimized Periocular Template Selection for Human Recognition

BioMed Research International ◽

10.1155/2013/481431 ◽

2013 ◽

Vol 2013 ◽

pp. 1-14 ◽

Cited By ~ 8

Author(s):

Sambit Bakshi ◽

Pankaj K. Sa ◽

Banshidhar Majhi

Keyword(s):

Feature Extraction ◽

Biometric System ◽

Human Recognition ◽

Novel Approach ◽

Database Size ◽

Periocular Region ◽

Template Selection ◽

Selection For ◽

Computationally Intensive

A novel approach for selecting a rectangular template around periocular region optimally potential for human recognition is proposed. A comparatively larger template of periocular image than the optimal one can be slightly more potent for recognition, but the larger template heavily slows down the biometric system by making feature extraction computationally intensive and increasing the database size. A smaller template, on the contrary, cannot yield desirable recognition though the smaller template performs faster due to low computation for feature extraction. These two contradictory objectives (namely, (a) to minimize the size of periocular template and (b) to maximize the recognition through the template) are aimed to be optimized through the proposed research. This paper proposes four different approaches for dynamic optimal template selection from periocular region. The proposed methods are tested on publicly available unconstrained UBIRISv2 and FERET databases and satisfactory results have been achieved. Thus obtained template can be used for recognition of individuals in an organization and can be generalized to recognize every citizen of a nation.

Download Full-text

DISSECT: DISentangle SharablE ConTent for Multimodal Integration and Crosswise-mapping

10.1101/2020.09.04.283234 ◽

2020 ◽

Author(s):

Geoffrey Schau ◽

Erik Burlingame ◽

Young Hwan Chang

Keyword(s):

Deep Learning ◽

Complete Information ◽

Specific Information ◽

Multimodal Integration ◽

Specific Data ◽

Domain Specific ◽

Cross Domain ◽

Input Feature ◽

Novel Approach ◽

Latent Representations

AbstractDeep learning systems have emerged as powerful mechanisms for learning domain translation models. However, in many cases, complete information in one domain is assumed to be necessary for sufficient cross-domain prediction. In this work, we motivate a formal justification for domain-specific information separation in a simple linear case and illustrate that a self-supervised approach enables domain translation between data domains while filtering out domain-specific data features. We introduce a novel approach to identify domainspecific information from sets of unpaired measurements in complementary data domains by considering a deep learning cross-domain autoencoder architecture designed to learn shared latent representations of data while enabling domain translation. We introduce an orthogonal gate block designed to enforce orthogonality of input feature sets by explicitly removing non-sharable information specific to each domain and illustrate separability of domain-specific information on a toy dataset.

Download Full-text

Content based Image Retrieval System using Combination of Color and Shape Features, and Siamese Neural Network

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.b1053.1292s19 ◽

2019 ◽

Vol 9 (2S) ◽

pp. 71-77

Keyword(s):

Neural Network ◽

World Wide ◽

Retrieval System ◽

Image Features ◽

Shape Features ◽

Retrieval Performance ◽

Novel Approach ◽

Learning Technique ◽

Image Retrieval System ◽

Similar Images

With an advent of technologya huge collection of digital images is formed as repositories on world wide web (WWW). The task of searching for similar images in the repository is difficult. In this paper, retrieval of similar images from www is demonstrated with the help of combination of image features as color and shape and then using Siamese neural network which is constructed to the requirement as a novel approach. Here, one-shot learning technique is used to test the Siamese Neural Network model for retrieval performance. Various experiments are conducted with both the methods and results obtained are tabulated. The performance of the system is evaluated with precision parameter and which is found to be high.Also, relative study is made with existing works.

Download Full-text

International Real Estate Review

International Real Estate Review ◽

10.53383/100319 ◽

2021 ◽

Vol 24 (2) ◽

pp. 139-183

Author(s):

Kristoffer B. Birkeland ◽

◽

Allan D. D’Silva ◽

Roland Füss ◽

Are Oust ◽

...

Keyword(s):

Real Estate ◽

Real Estate Market ◽

Percentage Error ◽

Residential Real Estate ◽

Valuation Model ◽

Stacked Generalization ◽

Novel Approach ◽

Out Of Sample ◽

Selection For ◽

Automated Valuation

We develop an automated valuation model (AVM) for the residential real estate market by leveraging stacked generalization and a comparable market analysis. Specifically, we combine four novel ensemble learning methods with a repeat sales method and tailor the data selection for each value estimate. We calibrate and evaluate the model for the residential real estate market in Oslo by producing out-of-sample estimates for the value of 1,979 dwellings sold in the first quarter of 2018. Our novel approach of using stacked generalization achieves a median absolute percentage error of 5.4%, and more than 96% of the dwellings are estimated within 20% of their actual sales price. A comparison of the valuation accuracy of our AVM to that of the local estate agents in Oslo generally demonstrates its viability as a valuation tool. However, in stable market phases, the machine falls short of human capability.

Download Full-text

Explaining feature detection Mechanisms: A Survey

10.54216/jcim.060103 ◽

2021 ◽

pp. 51-64

Author(s):

Ahmed A. Elngar ◽

◽

...

Keyword(s):

Feature Detection ◽

Feature Matching ◽

Image Features ◽

Mathematical Concepts ◽

Detection Algorithms ◽

Feature Detectors ◽

Essential Components ◽

Basic Notation ◽

Computer Vision Applications ◽

Detection Mechanisms

Feature detection, description and matching are essential components of various computer vision applications; thus, they have received a considerable attention in the last decades. Several feature detectors and descriptors have been proposed in the literature with a variety of deﬁnitions for what kind of points in an image is potentially interesting (i.e., a distinctive attribute). This chapter introduces basic notation and mathematical concepts for detecting and describing image features. Then, it discusses properties of perfect features and gives an overview of various existing detection and description methods. Furthermore, it explains some approaches to feature matching. Finally, the chapter discusses the most used techniques for performance evaluation of detection algorithms.

Download Full-text