Search Results for author: Ognjen Arandjelovic

Found 32 papers, 0 papers with code

Sequential Normalization: an improvement over Ghost Normalization

no code implementations1 Jan 2021 Neofytos Dimitriou, Ognjen Arandjelovic

Batch normalization (BatchNorm) is an effective yet poorly understood technique for neural network optimization.

A New Look at Ghost Normalization

no code implementations16 Jul 2020 Neofytos Dimitriou, Ognjen Arandjelovic

Batch normalization (BatchNorm) is an effective yet poorly understood technique for neural network optimization.

Understanding Ancient Coin Images

no code implementations7 Mar 2019 Jessica Cooper, Ognjen Arandjelovic

In recent years, a range of problems within the broad umbrella of automatic, computer vision based analysis of ancient coins has been attracting an increasing amount of attention.

Synthesising Wider Field Images from Narrow-Field Retinal Video Acquired Using a Low-Cost Direct Ophthalmoscope (Arclight) Attached to a Smartphone

no code implementations26 Aug 2017 Keylor Daniel Chaves Viquez, Ognjen Arandjelovic, Andrew Blaikie, In Ae Hwang

Access to low cost retinal imaging devices in low and middle income countries is limited, compromising progress in preventing needless blindness.

Achieving stable subspace clustering by post-processing generic clustering results

no code implementations27 May 2016 Duc-Son Pham, Ognjen Arandjelovic, Svetha Venkatesh

We propose an effective subspace selection scheme as a post-processing step to improve results obtained by sparse subspace clustering (SSC).

Face Clustering Motion Segmentation

Identification of promising research directions using machine learning aided medical literature analysis

no code implementations16 May 2016 Victor Andrei, Ognjen Arandjelovic

The rapidly expanding corpus of medical research literature presents major challenges in the understanding of previous work, the extraction of maximum information from collected data, and the identification of promising research directions.

Highly accurate gaze estimation using a consumer RGB-depth sensor

no code implementations5 Apr 2016 Reza Shoja Ghiass, Ognjen Arandjelovic

The method we propose starts by performing accurate head pose estimation achieved by fitting a person specific morphable model of the face to depth data.

Gaze Estimation Head Pose Estimation

Descriptor transition tables for object retrieval using unconstrained cluttered video acquired using a consumer level handheld mobile device

no code implementations16 Mar 2016 Warren Rieutort-Louis, Ognjen Arandjelovic

In this paper we propose a novel recognition method from video sequences suitable for retrieval from databases acquired in highly unconstrained conditions e. g. using a mobile consumer-level device such as a phone.

Learnt quasi-transitive similarity for retrieval from large collections of faces

no code implementations CVPR 2016 Ognjen Arandjelovic

We are interested in identity-based retrieval of face sets from large unlabelled collections acquired in uncontrolled environments.

Prediction of future hospital admissions - what is the tradeoff between specificity and accuracy?

no code implementations27 Feb 2016 Ieva Vasiljeva, Ognjen Arandjelovic

Large amounts of electronic medical records collected by hospitals across the developed world offer unprecedented possibilities for knowledge discovery using computer based data mining and machine learning.

Discovering topic structures of a temporally evolving document corpus

no code implementations25 Dec 2015 Adham Beykikhoshk, Ognjen Arandjelovic, Dinh Phung, Svetha Venkatesh

In this paper we describe a novel framework for the discovery of the topical content of a data corpus, and the tracking of its complex structural changes across the temporal dimension.

Automatic vehicle tracking and recognition from aerial image sequences

no code implementations23 Jun 2015 Ognjen Arandjelovic

This paper addresses the problem of automated vehicle tracking and recognition from aerial image sequences.

Groupwise registration of aerial images

no code implementations21 Apr 2015 Ognjen Arandjelovic, Duc-Son Pham, Svetha Venkatesh

This paper addresses the task of time separated aerial image registration.

Image Registration

Viewpoint distortion compensation in practical surveillance systems

no code implementations21 Apr 2015 Ognjen Arandjelovic, Duc-Son Pham, Svetha Venkatesh

Our aim is to estimate the perspective-effected geometric distortion of a scene from a video feed.

Global Optimization

The adaptable buffer algorithm for high quantile estimation in non-stationary data streams

no code implementations21 Apr 2015 Ognjen Arandjelovic, Duc-Son Pham, Svetha Venkatesh

The need to estimate a particular quantile of a distribution is an important problem which frequently arises in many computer vision and signal processing applications.

Automatic Face Recognition from Video

no code implementations21 Apr 2015 Ognjen Arandjelovic

The objective of this work is to automatically recognize faces from video sequences in a realistic, unconstrained setup in which illumination conditions are extreme and greatly changing, viewpoint and user motion pattern have a wide variability, and video input is of low quality.

Face Recognition

Hierarchical Dirichlet process for tracking complex topical structure evolution and its application to autism research literature

no code implementations8 Feb 2015 Adham Beykikhoshk, Ognjen Arandjelovic, Dinh Phung, Svetha Venkatesh

In this paper we describe a novel framework for the discovery of the topical content of a data corpus, and the tracking of its complex structural changes across the temporal dimension.

Sample-targeted clinical trial adaptation

no code implementations14 Nov 2014 Ognjen Arandjelovic

Clinical trial adaptation refers to any adjustment of the trial protocol after the onset of the trial.

A unified framework for thermal face recognition

no code implementations28 Jul 2014 Reza Shoja Ghiass, Ognjen Arandjelovic, Hakim Bendada, Xavier Maldague

The reduction of the cost of infrared (IR) cameras in recent years has made IR imaging a highly viable modality for face recognition in practice.

Face Recognition

A framework for improving the performance of verification algorithms with a low false positive rate requirement and limited training data

no code implementations28 Jun 2014 Ognjen Arandjelovic

Our approach is based on the interpretation of an inter-pattern distance as implicitly defining a pattern embedding which approximately distributes patterns according to an isotropic multi-variate normal distribution in some space.

Face Verification

Hallucinating optimal high-dimensional subspaces

no code implementations31 Jan 2014 Ognjen Arandjelovic

Linear subspace representations of appearance variation are pervasive in computer vision.

Infrared face recognition: a comprehensive review of methodologies and databases

no code implementations29 Jan 2014 Reza Shoja Ghiass, Ognjen Arandjelovic, Hakim Bendada, Xavier Maldague

Automatic face recognition is an area with immense practical potential which includes a wide range of commercial and law enforcement applications.

Face Recognition

Computer simulation based parameter selection for resistance exercise

no code implementations20 Jun 2013 Ognjen Arandjelovic

In contrast to most scientific disciplines, sports science research has been characterized by comparatively little effort investment in the development of relevant phenomenological models.

Matching objects across the textured-smooth continuum

no code implementations14 Jun 2013 Ognjen Arandjelovic

However, no previous work has attempted to achieve a holistic treatment of the problem by jointly using textural and shape features which is what we describe herein.

3D Object Recognition

Live-wire 3D medical images segmentation

no code implementations14 Jun 2013 Ognjen Arandjelovic

This report describes the design, implementation, evaluation and original enhancements to the Live-Wire method for 2D and 3D image segmentation.

Semantic Segmentation

Discriminative k-means clustering

no code implementations10 Jun 2013 Ognjen Arandjelovic

The k-means algorithm is a partitional clustering method.

Face Recognition

Discriminative extended canonical correlation analysis for pattern set matching

no code implementations10 Jun 2013 Ognjen Arandjelovic

Our second major contribution is to show that in contrast to CCA, E-CCA is readily adapted to match sets in a discriminative learning scheme which we call discriminative extended canonical correlation analysis (DE-CCA).

Face Recognition set matching

Vesselness features and the inverse compositional AAM for robust face recognition using thermal IR

no code implementations7 Jun 2013 Reza Shoja Ghiass, Ognjen Arandjelovic, Hakim Bendada, Xavier Maldague

To overcome the problem of thermal IR image sensitivity to the pattern of facial temperature emissions we describe a representation based on reliable anatomical features.

Face Recognition Robust Face Recognition

Illumination-invariant face recognition from a single image across extreme pose using a dual dimension AAM ensemble in the thermal infrared spectrum

no code implementations7 Jun 2013 Reza Shoja Ghiass, Ognjen Arandjelovic, Hakim Bendada, Xavier Maldague

Over the course of the last decade, infrared (IR) and particularly thermal IR imaging based face recognition has emerged as a promising complement to conventional, visible spectrum based approaches which continue to struggle when applied in practice.

Face Recognition

Infrared face recognition: a literature review

no code implementations7 Jun 2013 Reza Shoja Ghiass, Ognjen Arandjelovic, Hakim Bendada, Xavier Maldague

Automatic face recognition (AFR) is an area with immense practical potential which includes a wide range of commercial and law enforcement applications, and it continues to be one of the most active research areas of computer vision.

Face Recognition

Assessing Blinding in Clinical Trials

no code implementations NeurIPS 2012 Ognjen Arandjelovic

The current standard is follow up the trial with an auxiliary questionnaire, which allows trial participants to express their belief concerning the assigned intervention and which is used to compute a measure of the extent of blinding in the trial.

Cannot find the paper you are looking for? You can Submit a new open access paper.