Search Results for author: Michael Sapienza

Found 10 papers, 5 papers with code

Straight to Shapes++: Real-time Instance Segmentation Made More Accurate

1 code implementation27 May 2019 Laurynas Miksys, Saumya Jetley, Michael Sapienza, Stuart Golodetz, Philip H. S. Torr

The STS model can run at 35 FPS on a high-end desktop, but its accuracy is significantly worse than that of offline state-of-the-art methods.

Autonomous Driving Data Augmentation +4

InfiniTAM v3: A Framework for Large-Scale 3D Reconstruction with Loop Closure

1 code implementation2 Aug 2017 Victor Adrian Prisacariu, Olaf Kähler, Stuart Golodetz, Michael Sapienza, Tommaso Cavallari, Philip H. S. Torr, David W. Murray

Representing the reconstruction volumetrically as a TSDF leads to most of the simplicity and efficiency that can be achieved with GPU implementations of these systems.

3D Reconstruction Simultaneous Localization and Mapping

Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos

no code implementations22 Jul 2017 Suman Saha, Gurkirt Singh, Michael Sapienza, Philip H. S. Torr, Fabio Cuzzolin

Current state-of-the-art human action recognition is focused on the classification of temporally trimmed videos in which only one action occurs per frame.

Action Recognition Instance Segmentation +1

Incremental Tube Construction for Human Action Detection

1 code implementation5 Apr 2017 Harkirat Singh Behl, Michael Sapienza, Gurkirt Singh, Suman Saha, Fabio Cuzzolin, Philip H. S. Torr

In this work, we introduce a real-time and online joint-labelling and association algorithm for action detection that can incrementally construct space-time action tubes on the most challenging action videos in which different action categories occur concurrently.

Action Detection Association

Online Real-time Multiple Spatiotemporal Action Localisation and Prediction

4 code implementations ICCV 2017 Gurkirt Singh, Suman Saha, Michael Sapienza, Philip Torr, Fabio Cuzzolin

To the best of our knowledge, ours is the first real-time (up to 40fps) system able to perform online S/T action localisation and early action prediction on the untrimmed videos of UCF101-24.

Early Action Prediction

Straight to Shapes: Real-time Detection of Encoded Shapes

1 code implementation CVPR 2017 Saumya Jetley, Michael Sapienza, Stuart Golodetz, Philip H. S. Torr

To achieve this, we use a denoising convolutional auto-encoder to establish an embedding space, and place the decoder after a fast end-to-end network trained to regress directly to the encoded shape vectors.

Denoising object-detection +1

Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos

no code implementations4 Aug 2016 Suman Saha, Gurkirt Singh, Michael Sapienza, Philip H. S. Torr, Fabio Cuzzolin

In stage 2, the appearance network detections are boosted by combining them with the motion detection scores, in proportion to their respective spatial overlap.

Action Detection Motion Detection +1

Joint Object-Material Category Segmentation from Audio-Visual Cues

no code implementations10 Jan 2016 Anurag Arnab, Michael Sapienza, Stuart Golodetz, Julien Valentin, Ondrej Miksik, Shahram Izadi, Philip Torr

It is not always possible to recognise objects and infer material properties for a scene from visual cues alone, since objects can look visually similar whilst being made of very different materials.

Feature sampling and partitioning for visual vocabulary generation on large action classification datasets

no code implementations29 May 2014 Michael Sapienza, Fabio Cuzzolin, Philip H. S. Torr

The recent trend in action recognition is towards larger datasets, an increasing number of action classes and larger visual vocabularies.

Action Classification Action Recognition +1

Cannot find the paper you are looking for? You can Submit a new open access paper.