Search Results for author:
Found 24 papers, 5 papers with code
Are you Struggling? Dataset and Baselines for Struggle Determination in Assembly Videos
Determining when people are struggling from video enables a finer-grained understanding of actions and opens opportunities for building intelligent support visual interfaces.
SuperTran: Reference Based Video Transformer for Enhancing Low Bitrate Streams in Real Time
This work focuses on low bitrate video streaming scenarios (e. g. 50 - 200Kbps) where the video quality is severely compromised.
AROS: Affordance Recognition with One-Shot Human Stances
We present AROS, a one-shot learning approach that uses an explicit representation of interactions between highly-articulated human poses and 3D scenes.
On-Sensor Binarized Fully Convolutional Neural Network with A Pixel Processor Array
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.
Direct Servo Control from In-Sensor CNN Inference with A Pixel Processor Array
This work demonstrates direct visual sensory-motor control using high-speed CNN inference via a SCAMP-5 Pixel Processor Array (PPA).
Filter Distribution Templates in Convolutional Networks for Image Classification Tasks
Neural network designers have reached progressive accuracy by increasing models depth, introducing new layer types and discovering new combinations of layers.
Towards Efficient Convolutional Network Models with Filter Distribution Templates
Increasing number of filters in deeper layers when feature maps are decreased is a widely adopted pattern in convolutional network design.
Agile Reactive Navigation for A Non-Holonomic Mobile Robot Using A Pixel Processor Array
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.
Geometric Affordance Perception: Leveraging Deep 3D Saliency With the Interaction Tensor
Agents that need to act on their surroundings can significantly benefit from the perception of their interaction possibilities or affordances.
Fully Embedding Fast Convolutional Networks on Pixel Processor Arrays
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.
Action Modifiers: Learning from Adverbs in Instructional Videos
We present a method to learn a representation for adverbs from instructional videos using weak supervision from the accompanying narrations.
A Camera That CNNs: Towards Embedded Neural Networks on Pixel Processor Arrays
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.
Egocentric affordance detection with the one-shot geometry-driven Interaction Tensor
In this abstract we describe recent [4, 7] and latest work on the determination of affordances in visually perceived 3D scenes.
The Pros and Cons: Rank-aware Temporal Attention for Skill Determination in Long Videos
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.
What can I do here? Leveraging Deep 3D saliency and geometry for fast and scalable multiple affordance detection
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.
Visual Odometry for Pixel Processor Arrays
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.
Towards CNN map representation and compression for camera relocalisation
This paper presents a study on the use of Convolutional Neural Networks for camera relocalisation and its application to map compression.
Geometric Affordances from a Single Example via the Interaction Tensor
This paper develops and evaluates a new tensor field representation to express the geometric affordance of one object over another.
Who's Better? Who's Best? Pairwise Deep Ranking for Skill Determination
We present a method for assessing skill from video, applicable to a variety of tasks, ranging from surgery to drawing and rolling pizza dough.
Trespassing the Boundaries: Labeling Temporal Bounds for Object Interactions in Egocentric Video
Manual annotations of temporal bounds for object interactions (i. e. start and end times) are typical training input to recognition, localization and detection algorithms.
Improving Classification by Improving Labelling: Introducing Probabilistic Multi-Label Object Interaction Recognition
This work deviates from easy-to-define class boundaries for object interactions.
Towards CNN Map Compression for camera relocalisation
We use a CNN map representation and introduce the notion of CNN map compression by using a smaller CNN architecture.
SEMBED: Semantic Embedding of Egocentric Action Videos
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.
You-Do, I-Learn: Unsupervised Multi-User egocentric Approach Towards Video-Based Guidance
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.
