• Publications
  • Influence
Deep Face Recognition
TLDR
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
TLDR
In this paper, we introduce a new large-scale face dataset named VGGFace2. Expand
  • 803
  • 207
  • PDF
Cats and dogs
TLDR
We investigate the fine grained object categorization problem of determining the breed of animal from an image. Expand
  • 387
  • 51
  • PDF
Fisher Vector Faces in the Wild
TLDR
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
  • 427
  • 46
  • PDF
Template Adaptation for Face Verification and Identification
TLDR
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
  • 114
  • 15
  • PDF
A Compact and Discriminative Face Track Descriptor
TLDR
We propose a novel face track descriptor, based on the Fisher Vector representation, and demonstrate that it has a number of favourable properties. Expand
  • 117
  • 10
  • PDF
The truth about cats and dogs
TLDR
Template-based object detectors such as the deformable parts model of Felzenszwalb et al. Expand
  • 129
  • 8
  • PDF
Total Cluster: A person agnostic clustering method for broadcast videos
TLDR
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
  • 36
  • 8
  • PDF
The AXES submissions at TRECVID 2013
TLDR
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
  • 34
  • 5
  • PDF
AXES at TRECVID 2012: KIS, INS, and MED
TLDR
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
  • 36
  • 2
  • PDF