134 citations · 197 across the 9 of their papers we have counts for
10 papers
Learning Free-Form Deformations for 3D Object Reconstruction
Dominic Jack, Jhony K. Pontes, Sridha Sridharan +4
Representing 3D shape in deep learning frameworks in an accurate, efficient and compact manner still remains an open challenge. Most existing work addresses this issue by employing…
On Encoding Temporal Evolution for Real-time Action Prediction
Fahimeh Rezazadegan, Sareh Shirazi, Mahsa Baktashmotlagh +1
Anticipating future actions is a key component of intelligence, specifically when it applies to real-time systems, such as robots or autonomous cars. While recent works have addres…
What Would You Do? Acting by Learning to Predict
Adam Tow, Niko Sünderhauf, Sareh Shirazi +2
We propose to learn tasks directly from visual demonstrations by learning to predict the outcome of human and robot actions on an environment. We enable a robot to physically perfo…
Action Recognition: From Static Datasets to Moving Robots
Fahimeh Rezazadegan, Sareh Shirazi, Ben Upcroft +1
Deep learning models have achieved state-of-the- art performance in recognizing human activities, but often rely on utilizing background cues present in typical computer vision dat…
Unsupervised Human Action Detection by Action Matching
Basura Fernando, Sareh Shirazi, Stephen Gould
We propose a new task of unsupervised action detection by action matching. Given two long videos, the objective is to temporally detect all pairs of matching video segments. A pair…
ARTiS: Appearance-based Action Recognition in Task Space for Real-Time Human-Robot Collaboration
Markus Eich, Sareh Shirazi, Gordon Wyeth
To have a robot actively supporting a human during a collaborative task, it is crucial that robots are able to identify the current action in order to predict the next one. Common…
Evaluation of Object Detection Proposals Under Condition Variations
Fahimeh Rezazadegan, Sareh Shirazi, Michael Milford +1
Object detection is a fundamental task in many computer vision applications, therefore the importance of evaluating the quality of object detection is well acknowledged in this dom…
On the Performance of ConvNet Features for Place Recognition
Niko Sünderhauf, Feras Dayoub, Sareh Shirazi +2
After the incredible success of deep learning in the computer vision domain, there has been much interest in applying Convolutional Network (ConvNet) features in robotic fields suc…
Bags of Affine Subspaces for Robust Object Tracking
Sareh Shirazi, Conrad Sanderson, Chris McCool +1
We propose an adaptive tracking algorithm where the object is modelled as a continuously updated bag of affine subspaces, with each subspace constructed from the object's appearanc…
Object Tracking via Non-Euclidean Geometry: A Grassmann Approach
Sareh Shirazi, Mehrtash T. Harandi, Brian C. Lovell +1
A robust visual tracking system requires an object appearance model that is able to handle occlusion, pose, and illumination variations in the video stream. This can be difficult t…