• Publications
  • Influence
Shallow and Deep Convolutional Networks for Saliency Prediction
TLDR
This paper addresses the problem with a completely data-driven approach by training a convolutional neural network (convnet) and proposes two designs: a shallow convnet trained from scratch, and a another deeper solution whose first three layers are adapted from another network trained for classification. Expand
SalGAN: Visual Saliency Prediction with Generative Adversarial Networks
TLDR
This work introduces SalGAN, a deep convolutional neural network for visual saliency prediction trained with adversarial examples and shows how adversarial training allows reaching state-of-the-art performance across different metrics when combined with a widely-used loss function like BCE. Expand
Unsupervised label noise modeling and loss correction
TLDR
A suitable two-component mixture model is suggested as an unsupervised generative model of sample loss values during training to allow online estimation of the probability that a sample is mislabelled and correct the loss by relying on the network prediction. Expand
A comparative evaluation of interactive segmentation algorithms
TLDR
A comparative evaluation of four popular interactive segmentation algorithms using the well-known Jaccard index for measuring object accuracy and a new fuzzy metric, proposed in this paper, designed for measuring boundary accuracy, demonstrates the effectiveness of the suggested measures. Expand
A multiscale representation method for nonrigid shapes with a single closed contour
TLDR
The criteria that should be satisfied by a descriptor for nonrigid shapes with a single closed contour are discussed and a shape representation method that fulfills these criteria is proposed that is very efficient and invariant to several kinds of transformations. Expand
Event detection in field sports video using audio-visual features and a support vector Machine
TLDR
A novel audio-visual feature-based framework for event detection in broadcast video of multiple different field sports and the results suggest that high event retrieval and content rejection statistics are achievable. Expand
Fully Convolutional Crowd Counting on Highly Congested Scenes
TLDR
The state-of-the-art for crowd counting in high density scenes is advanced by further exploring the idea of a fully convolutional crowd counting model introduced by (Zhang et al., 2016), and a training set augmentation scheme that minimises redundancy among training samples to improve model generalisation and overall counting performance is developed. Expand
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning
TLDR
This work shows that a naive pseudo-labeling overfits to incorrect pseudo-labels due to the so-called confirmation bias and demonstrates that mixup augmentation and setting a minimum number of labeled samples per mini-batch are effective regularization techniques for reducing it. Expand
Evaluating a dancer's performance using kinect-based skeleton tracking
TLDR
A novel system that automatically evaluates dance performances against a gold-standard performance and provides visual feedback to the performer in a 3D virtual environment and is proposed for temporally aligning dance movements from two different users and quantitatively evaluating one performance against another. Expand
Touch Screens for the Older User
It has been 20 years since Ben Schneiderman predicted that there would be an increase in the use of touch screen applications yet it has been only in recent years that this prediction has come toExpand
...
1
2
3
4
5
...