• Publications
  • Influence
Adapting Visual Category Models to New Domains
TLDR
This paper introduces a method that adapts object models acquired in a particular visual domain to new imaging conditions by learning a transformation that minimizes the effect of domain-induced changes in the feature distribution.
Appearance-based gaze estimation in the wild
TLDR
An extensive evaluation of several state-of-the-art image-based gaze estimation algorithms on three current datasets, including the MPIIGaze dataset, which contains 213,659 images collected from 15 participants during natural everyday laptop use over more than three months.
A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input
TLDR
This work proposes a method for automatically answering questions about images by bringing together recent advances from natural language processing and computer vision by a multi-world approach that represents uncertainty about the perceived world in a bayesian framework.
ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models
TLDR
This most comprehensive study so far on this emerging and developing threat using eight diverse datasets which show the viability of the proposed attacks across domains and proposes the first effective defense mechanisms against such broader class of membership inference attacks that maintain a high level of utility of the ML model.
On the Significance of Real-World Conditions for Material Classification
TLDR
A first contribution of this paper is to further advance the state-of-the-art by applying Support Vector Machines to this problem and record the best results to date on the CUReT database.
Ask Your Neurons: A Neural-Based Approach to Answering Questions about Images
We address a question answering task on real-world images that is set up as a Visual Turing Test. By combining latest advances in image representation and natural language processing, we propose
It’s Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation
TLDR
This work proposes an appearance-based method that, in contrast to a long-standing line of work in computer vision, only takes the full face image as input, and encodes the face image using a convolutional neural network with spatial weights applied on the feature maps to flexibly suppress or enhance information in different facial regions.
Disentangled Person Image Generation
TLDR
A novel, two-stage reconstruction pipeline is proposed that learns a disentangled representation of the aforementioned image factors and generates novel person images at the same time and can manipulate the foreground, background and pose of the input image, and also sample new embedding features to generate targeted manipulations, that provide more control over the generation process.
Knockoff Nets: Stealing Functionality of Black-Box Models
TLDR
This work forms model functionality stealing as a two-step approach: querying a set of input images to the blackbox model to obtain predictions, and training a ``knockoff'' with queried image-prediction pairs.
MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation
TLDR
It is shown that image resolution and the use of both eyes affect gaze estimation performance, while head pose and pupil centre information are less informative, and GazeNet is proposed, the first deep appearance-based gaze estimation method.
...
...