Omkar M. Parkhi

Publications
Influence

Omkar M. Parkhi, A. Vedaldi, Andrew Zisserman
Computer Science
BMVC
2015

The goal of this paper is face recognition – from either a single photograph or from a set of faces tracked in a video. Expand

3,214
602
PDF

VGGFace2: A Dataset for Recognising Faces across Pose and Age

Q. Cao, Li Shen, Weidi Xie, Omkar M. Parkhi, Andrew Zisserman
Computer Science
13th IEEE International Conference on Automatic…
23 October 2017

In this paper, we introduce a new large-scale face dataset named VGGFace2. Expand

Cats and dogs

Omkar M. Parkhi, A. Vedaldi, Andrew Zisserman, C. Jawahar
Computer Science
IEEE Conference on Computer Vision and Pattern…
16 June 2012

We investigate the fine grained object categorization problem of determining the breed of animal from an image. Expand

Fisher Vector Faces in the Wild

K. Simonyan, Omkar M. Parkhi, A. Vedaldi, Andrew Zisserman
Computer Science
BMVC
2013

This paper makes two contributions: first, and somewhat surprisingly, we show that Fisher vectors on densely sampled SIFT features, i.e. an off-the-shelf object recognition representation, are capable of achieving state-of- the-art face verification performance on the challenging “Labeled Faces in the Wild” benchmark. Expand

Template Adaptation for Face Verification and Identification

Nate Crosswhite, J. Byrne, C. Stauffer, Omkar M. Parkhi, Q. Cao, Andrew Zisserman
Computer Science
12th IEEE International Conference on Automatic…
12 March 2016

Face recognition performance evaluation has traditionally focused on one-to-one verification, popularized by the Labeled Faces in the Wild dataset [1] for imagery and the YouTubeFaces dataset [2] for videos. Expand

A Compact and Discriminative Face Track Descriptor

Omkar M. Parkhi, K. Simonyan, A. Vedaldi, Andrew Zisserman
Computer Science
IEEE Conference on Computer Vision and Pattern…
23 June 2014

We propose a novel face track descriptor, based on the Fisher Vector representation, and demonstrate that it has a number of favourable properties. Expand

The truth about cats and dogs

Omkar M. Parkhi, A. Vedaldi, C. Jawahar, Andrew Zisserman
Computer Science
International Conference on Computer Vision
6 November 2011

Template-based object detectors such as the deformable parts model of Felzenszwalb et al. Expand

Total Cluster: A person agnostic clustering method for broadcast videos

Makarand Tapaswi, Omkar M. Parkhi, Esa Rahtu, Eric Sommerlade, R. Stiefelhagen, Andrew Zisserman
Computer Science
ICVGIP '14
14 December 2014

The goal of this paper is unsupervised face clustering in edited video material – where face tracks arising from different people are assigned to separate clusters, with one cluster for each person. Expand

The AXES submissions at TRECVID 2013

R. Aly, R. Arandjelović, +16 authors Andrew Zisserman
Computer Science
TRECVID
2013

We use state-of-the-art local low-level descriptors for motion, image, and sound, as well as high-level features to capture speech and text and the visual and audio stream respectively. Expand

AXES at TRECVID 2012: KIS, INS, and MED

Dan Oneata, M. Douze, +16 authors T. Tuytelaars
Engineering, Computer Science
TRECVID
1 September 2012

The AXES project participated in the interactive instance search task (INS), the known-item searchtask (KIS), and the multimedia event detection task (MED) for TRECVid 2012. Expand

Recommended Authors