23 citations · 87 across the 24 of their papers we have counts for
31 papers
Centre Stage: Centricity-based Audio-Visual Temporal Action Detection
Hanyuan Wang, Majid Mirmehdi, Dima Damen +1
Previous one-stage action detection approaches have modelled temporal dependencies using only the visual modality. In this paper, we explore different strategies to incorporate the…
Use Your Head: Improving Long-Tail Video Recognition
Toby Perrett, Saptarshi Sinha, Tilo Burghardt +2
This paper presents an investigation into long-tail video recognition. We demonstrate that, unlike naturally-collected video datasets and existing long-tail image benchmarks, curre…
TranSOP: Transformer-based Multimodal Classification for Stroke Treatment Outcome Prediction
Zeynel A. Samak, Philip Clatworthy, Majid Mirmehdi
Acute ischaemic stroke, caused by an interruption in blood flow to brain tissue, is a leading cause of disability and mortality worldwide. The selection of patients for the most op…
Triple-stream Deep Metric Learning of Great Ape Behavioural Actions
Otto Brookes, Majid Mirmehdi, Hjalmar Kühl +1
We propose the first metric learning system for the recognition of great ape behavioural actions. Our proposed triple stream embedding architecture works on camera trap videos take…
Refining Action Boundaries for One-stage Detection
Hanyuan Wang, Majid Mirmehdi, Dima Damen +1
Current one-stage action detection methods, which simultaneously predict action boundaries and the corresponding class, do not estimate or use a measure of confidence in their boun…
Video-TransUNet: Temporally Blended Vision Transformer for CT VFSS Instance Segmentation
Chengxi Zeng, Xinyu Yang, Majid Mirmehdi +2
We propose Video-TransUNet, a deep architecture for instance segmentation in medical CT videos constructed by integrating temporal feature blending into the TransUNet deep learning…
Detecting Humans in RGB-D Data with CNNs
Kaiyang Zhou, Adeline Paiement, Majid Mirmehdi
We address the problem of people detection in RGB-D data where we leverage depth information to develop a region-of-interest (ROI) selection method that provides proposals to two c…
Inertial Hallucinations -- When Wearable Inertial Devices Start Seeing Things
Alessandro Masullo, Toby Perrett, Tilo Burghardt +3
We propose a novel approach to multimodal sensor fusion for Ambient Assisted Living (AAL) which takes advantage of learning using privileged information (LUPI). We address two majo…
Dynamic Curriculum Learning for Great Ape Detection in the Wild
Xinyu Yang, Tilo Burghardt, Majid Mirmehdi
We propose a novel end-to-end curriculum learning approach for sparsely labelled animal datasets leveraging large volumes of unlabelled data to improve supervised species detectors…
TVNet: Temporal Voting Network for Action Localization
Hanyuan Wang, Dima Damen, Majid Mirmehdi +1
We propose a Temporal Voting Network (TVNet) for action localization in untrimmed videos. This incorporates a novel Voting Evidence Module to locate temporal boundaries, more accur…
Auxiliary Learning for Self-Supervised Video Representation via Similarity-based Knowledge Distillation
Amirhossein Dadashzadeh, Alan Whone, Majid Mirmehdi
Despite the outstanding success of self-supervised pretraining methods for video representation learning, they generalise poorly when the unlabeled dataset for pretraining is small…
Small or Far Away? Exploiting Deep Super-Resolution and Altitude Data for Aerial Animal Surveillance
Mowen Xue, Theo Greenslade, Majid Mirmehdi +1
Visuals captured by high-flying aerial drones are increasingly used to assess biodiversity and animal population dynamics around the globe. Yet, challenging acquisition scenarios a…
Unsupervised View-Invariant Human Posture Representation
Faegheh Sardari, Björn Ommer, Majid Mirmehdi
Most recent view-invariant action recognition and performance assessment approaches rely on a large amount of annotated 3D skeleton data to extract view-invariant features. However…
Temporal-Relational CrossTransformers for Few-Shot Action Recognition
Toby Perrett, Alessandro Masullo, Tilo Burghardt +2
We propose a novel approach to few-shot action recognition, finding temporally-corresponding frame tuples between the query and videos in the support set. Distinct from previous fe…
Exploring Motion Boundaries in an End-to-End Network for Vision-based Parkinson's Severity Assessment
Amirhossein Dadashzadeh, Alan Whone, Michal Rolinski +1
Evaluating neurological disorders such as Parkinson's disease (PD) is a challenging task that requires the assessment of several motor and non-motor functions. In this paper, we pr…
Back to the Future: Cycle Encoding Prediction for Self-supervised Contrastive Video Representation Learning
Xinyu Yang, Majid Mirmehdi, Tilo Burghardt
In this paper we show that learning video feature spaces in which temporal cycles are maximally predictable benefits action classification. In particular, we propose a novel learni…
VI-Net: View-Invariant Quality of Human Movement Assessment
Faegheh Sardari, Adeline Paiement, Sion Hannuna +1
We propose a view-invariant method towards the assessment of the quality of human movements which does not rely on skeleton data. Our end-to-end convolutional neural network consis…
Meta-Learning with Context-Agnostic Initialisations
Toby Perrett, Alessandro Masullo, Tilo Burghardt +2
Meta-learning approaches have addressed few-shot problems by finding initialisations suited for fine-tuning to target tasks. Often there are additional properties within training d…
Prediction of Thrombectomy Functional Outcomes using Multimodal Data
Zeynel A. Samak, Philip Clatworthy, Majid Mirmehdi
Recent randomised clinical trials have shown that patients with ischaemic stroke {due to occlusion of a large intracranial blood vessel} benefit from endovascular thrombectomy. How…
Weakly-Supervised Completion Moment Detection using Temporal Attention
Farnoosh Heidarivincheh, Majid Mirmehdi, Dima Damen
Monitoring the progression of an action towards completion offers fine grained insight into the actor's behaviour. In this work, we target detecting the completion moment of action…
Sit-to-Stand Analysis in the Wild using Silhouettes for Longitudinal Health Monitoring
Alessandro Masullo, Tilo Burghardt, Toby Perrett +2
We present the first fully automated Sit-to-Stand or Stand-to-Sit (StS) analysis framework for long-term monitoring of patients in free-living environments using video silhouettes.…
Great Ape Detection in Challenging Jungle Camera Trap Footage via Attention-Based Spatial and Temporal Feature Blending
Xinyu Yang, Majid Mirmehdi, Tilo Burghardt
We propose the first multi-frame video object detection framework trained to detect great apes. It is applicable to challenging camera trap footage in complex jungle environments a…
CaloriNet: From silhouettes to calorie estimation in private environments
Alessandro Masullo, Tilo Burghardt, Dima Damen +3
We propose a novel deep fusion architecture, CaloriNet, for the online estimation of energy expenditure for free living monitoring in private environments, where RGB data is discar…
Semantically Selective Augmentation for Deep Compact Person Re-Identification
Víctor Ponce-López, Tilo Burghardt, Sion Hannunna +3
We present a deep person re-identification approach that combines semantically selective, deep data augmentation with clustering-based network compression to generate high performa…