• Publications
  • Influence
Unsupervised Learning of Generative Topic Saliency for Person Re-identification
TLDR
We propose a novel unsupervised modelling approach to saliency learning for person re-identification and show that it can be used to solve the re-id problem. Expand
  • 89
  • 6
  • PDF
Towards unsupervised open-set person re-identification
TLDR
We introduce a more challenging yet realistic ReID setting termed OneShot-OpenSet-RelD, and propose a novel Regularised Kernel Subspace Learning model for ReID under this setting. Expand
  • 49
  • 6
Generalized Zero-Shot Recognition Based on Visually Semantic Embedding
TLDR
We propose a novel Generalized Zero-Shot learning (GZSL) method that is agnostic to both unseen images and unseen semantic vectors during training. Expand
  • 41
  • 6
  • PDF
Zero Shot Detection
TLDR
We propose a novel zero-shot method based on training an end-to-end model that fuses semantic attribute prediction with visual features to propose object bounding boxes for seen and unseen classes. Expand
  • 41
  • 5
  • PDF
Person Re-identification in Identity Regression Space
TLDR
We propose to construct an identity regression space (IRS) based on embedding different person identities (classes) and formulate re-id as a regression problem solved by identity regression in the IRS. Expand
  • 22
  • 5
  • PDF
Time-Inconsistent Stochastic Optimal Control Problems and Backward Stochastic Volterra Integral Equations
An optimal control problem is considered for a stochastic differential equation with the cost functional determined by a backward stochastic Volterra integral equation (BSVIE, for short). This kindExpand
  • 7
  • 4
  • PDF
Human-in-the-Loop Person Re-identification
TLDR
A novel human-in-the-loop re-id model based on Human Verification Incremental Learning (HVIL) is formulated which does not require any pre-labelled training data to learn a model, therefore readily scalable to new camera pairs. Expand
  • 64
  • 2
  • PDF
Recursive Utility Processes, Dynamic Risk Measures and Quadratic Backward Stochastic Volterra Integral Equations.
For an $\cF_T$-measurable payoff of a European type contingent claim, the recursive utility process/dynamic risk measure can be described by the adapted solution to a backward stochastic differentialExpand
  • 8
  • 2
Quadratic Backward Stochastic Volterra Integral Equations
This paper is concerned with backward stochastic Volterra integral equations (BSVIEs, for short) with generators having quadratic growth. The existence and uniqueness for both the so-called adaptedExpand
  • 4
  • 2
  • PDF
Highly Efficient Regression for Scalable Person Re-Identification
TLDR
We propose a Highly Efficient Regression (HER) model is formulated by embedding the Fisher's criterion to a ridge regression model for very fast re-id model learning with scalable memory/storage usage. Expand
  • 21
  • 1
  • PDF
...
1
2
3
4
...