no code implementations • 16 Feb 2024 • Shijia Feng, Michael Wray, Brian Sullivan, Youngkyoon Jang, Casimir Ludwig, Iain Gilchrist, Walterio Mayol-Cuevas
Determining when people are struggling from video enables a finer-grained understanding of actions and opens opportunities for building intelligent support visual interfaces.
no code implementations • 22 Nov 2022 • Tejas Khot, Nataliya Shapovalova, Silviu Andrei, Walterio Mayol-Cuevas
This work focuses on low bitrate video streaming scenarios (e. g. 50 - 200Kbps) where the video quality is severely compromised.
no code implementations • 21 Oct 2022 • Abel Pacheco-Ortega, Walterio Mayol-Cuevas
We present AROS, a one-shot learning approach that uses an explicit representation of interactions between highly-articulated human poses and 3D scenes.
no code implementations • 2 Feb 2022 • Yanan Liu, Laurie Bose, Yao Lu, Piotr Dudek, Walterio Mayol-Cuevas
This work presents a method to implement fully convolutional neural networks (FCNs) on Pixel Processor Array (PPA) sensors, and demonstrates coarse segmentation and object localisation tasks.
no code implementations • 26 May 2021 • Yanan Liu, Jianing Chen, Laurie Bose, Piotr Dudek, Walterio Mayol-Cuevas
This work demonstrates direct visual sensory-motor control using high-speed CNN inference via a SCAMP-5 Pixel Processor Array (PPA).
no code implementations • 28 Apr 2021 • Ramon Izquierdo-Cordova, Walterio Mayol-Cuevas
Neural network designers have reached progressive accuracy by increasing models depth, introducing new layer types and discovering new combinations of layers.
no code implementations • 17 Apr 2021 • Ramon Izquierdo-Cordova, Walterio Mayol-Cuevas
Increasing number of filters in deeper layers when feature maps are decreased is a widely adopted pattern in convolutional network design.
no code implementations • 27 Sep 2020 • Yanan Liu, Laurie Bose, Colin Greatwood, Jianing Chen, Rui Fan, Thomas Richardson, Stephen J. Carey, Piotr Dudek, Walterio Mayol-Cuevas
Experimental results demonstrate that the algorithm's ability to enable a ground vehicle to navigate at an average speed of 2. 20 m/s for passing through multiple gates and 3. 88 m/s for a 'slalom' task in an environment featuring significant visual clutter.
1 code implementation • 7 Jul 2020 • Eduardo Ruiz, Walterio Mayol-Cuevas
Agents that need to act on their surroundings can significantly benefit from the perception of their interaction possibilities or affordances.
no code implementations • ECCV 2020 • Laurie Bose, Jianing Chen, Stephen J. Carey, Piotr Dudek, Walterio Mayol-Cuevas
This is in contrast to previous works that only use a sensor-level processing to sequentially compute image convolutions, and must transfer data to an external digital processor to complete the computation.
1 code implementation • CVPR 2020 • Hazel Doughty, Ivan Laptev, Walterio Mayol-Cuevas, Dima Damen
We present a method to learn a representation for adverbs from instructional videos using weak supervision from the accompanying narrations.
no code implementations • ICCV 2019 • Laurie Bose, Jianing Chen, Stephen J. Carey, Piotr Dudek, Walterio Mayol-Cuevas
This allows images to be stored and manipulated directly at the point of light capture, rather than having to transfer images to external processing hardware.
no code implementations • 13 Jun 2019 • Eduardo Ruiz, Walterio Mayol-Cuevas
In this abstract we describe recent [4, 7] and latest work on the determination of affordances in visually perceived 3D scenes.
1 code implementation • CVPR 2019 • Hazel Doughty, Walterio Mayol-Cuevas, Dima Damen
In addition to attending to task relevant video parts, our proposed loss jointly trains two attention modules to separately attend to video parts which are indicative of higher (pros) and lower (cons) skill.
1 code implementation • 3 Dec 2018 • Eduardo Ruiz, Walterio Mayol-Cuevas
This paper develops and evaluates a novel method that allows for the detection of affordances in a scalable and multiple-instance manner on visually recovered pointclouds.
no code implementations • ICCV 2017 • Laurie Bose, Jianing Chen, Stephen J. Carey, Piotr Dudek, Walterio Mayol-Cuevas
We present an approach of estimating constrained motion of a novel Cellular Processor Array (CPA) camera, on which each pixel is capable of limited processing and data storage allowing for fast low power parallel computation to be carried out directly on the focal-plane of the device.
no code implementations • 15 Sep 2017 • Luis Contreras, Walterio Mayol-Cuevas
This paper presents a study on the use of Convolutional Neural Networks for camera relocalisation and its application to map compression.
1 code implementation • 30 Mar 2017 • Eduardo Ruiz, Walterio Mayol-Cuevas
This paper develops and evaluates a new tensor field representation to express the geometric affordance of one object over another.
no code implementations • CVPR 2018 • Hazel Doughty, Dima Damen, Walterio Mayol-Cuevas
We present a method for assessing skill from video, applicable to a variety of tasks, ranging from surgery to drawing and rolling pizza dough.
no code implementations • ICCV 2017 • Davide Moltisanti, Michael Wray, Walterio Mayol-Cuevas, Dima Damen
Manual annotations of temporal bounds for object interactions (i. e. start and end times) are typical training input to recognition, localization and detection algorithms.
no code implementations • 24 Mar 2017 • Michael Wray, Davide Moltisanti, Walterio Mayol-Cuevas, Dima Damen
This work deviates from easy-to-define class boundaries for object interactions.
no code implementations • 2 Mar 2017 • Luis Contreras, Walterio Mayol-Cuevas
We use a CNN map representation and introduce the notion of CNN map compression by using a smaller CNN architecture.
no code implementations • 28 Jul 2016 • Michael Wray, Davide Moltisanti, Walterio Mayol-Cuevas, Dima Damen
We present SEMBED, an approach for embedding an egocentric object interaction video in a semantic-visual graph to estimate the probability distribution over its potential semantic labels.
no code implementations • 16 Oct 2015 • Dima Damen, Teesid Leelasawassuk, Walterio Mayol-Cuevas
This paper presents an unsupervised approach towards automatically extracting video-based guidance on object usage, from egocentric video and wearable gaze tracking, collected from multiple users while performing tasks.