Search Results for author:
Found 92 papers, 16 papers with code
Revisiting the Role of Texture in 3D Person Re-identification
Our contributions include: (1) a novel technique for emphasizing texture in 3D models using UVTexture processing, (2) an innovative method for explicating person re-ID matches through a combination of 3D models and UVTexture mapping, and (3) achieving state-of-the-art performance in 3D person re-ID.
Physics Augmented Tuple Transformer for Autism Severity Level Detection
This paper proposes a novel framework that exploits the laws of physics for ASD severity recognition.
PseudoNeg-MAE: Self-Supervised Point Cloud Learning using Conditional Pseudo-Negative Embeddings
We propose PseudoNeg-MAE, a novel self-supervised learning framework that enhances global feature representation of point cloud mask autoencoder by making them both discriminative and sensitive to transformations.
Part-based Quantitative Analysis for Heatmaps
Heatmaps have been instrumental in helping understand deep network decisions, and are a common approach for Explainable AI (XAI).
AG-ReID.v2: Bridging Aerial and Ground Views for Person Re-identification
To address this, we introduce AG-ReID. v2, a dataset specifically designed for person Re-ID in mixed aerial and ground scenarios.
Ranked #1 on
Person Re-Identification
on AG-ReID.v2
WildScenes: A Benchmark for 2D and 3D Semantic Segmentation in Large-scale Natural Environments
Recent progress in semantic scene understanding has primarily been enabled by the availability of semantically annotated bi-modal (camera and LiDAR) datasets in urban environments.
FactoFormer: Factorized Hyperspectral Transformers with Self-Supervised Pretraining
However, current state-of-the-art hyperspectral transformers only tokenize the input HSI sample along the spectral dimension, resulting in the under-utilization of spatial information.
Learning Through Guidance: Knowledge Distillation for Endoscopic Image Classification
However, there is a lack of focus on developing lightweight models which can run in low-resource environments, which are typically encountered in medical clinics.
GeoAdapt: Self-Supervised Test-Time Adaptation in LiDAR Place Recognition Using Geometric Priors
LiDAR place recognition approaches based on deep learning suffer from significant performance degradation when there is a shift between the distribution of training and test datasets, often requiring re-training the networks to achieve peak performance.
General-Purpose Multimodal Transformer meets Remote Sensing Semantic Segmentation
In this work, we investigate the performance of PerceiverIO, one in the general-purpose multimodal family, in the remote sensing semantic segmentation domain.
Remembering What Is Important: A Factorised Multi-Head Retrieval and Auxiliary Memory Stabilisation Scheme for Human Motion Prediction
Humans exhibit complex motions that vary depending on the task that they are performing, the interactions they engage in, as well as subject-specific preferences.
Ranked #3 on
Human Pose Forecasting
on Human3.6M
Physical Adversarial Attacks for Surveillance: A Survey
In particular, we propose a framework to analyze physical adversarial attacks and provide a comprehensive survey of physical adversarial attacks on four key surveillance tasks: detection, identification, tracking, and action recognition under this framework.
Towards Self-Explainability of Deep Neural Networks with Heatmap Captioning and Large-Language Models
We proposed a template-based image captioning approach for context modelling to create text-based contextual information from the heatmap and input data.
Explainable Artificial Intelligence (XAI)
Image Captioning
+2
Aerial-Ground Person Re-ID
Our dataset presents a novel elevated-viewpoint challenge for person re-ID due to the significant difference in person appearance across these cameras.
Ranked #2 on
Person Re-Identification
on AG-ReID
Using Auxiliary Information for Person Re-Identification -- A Tutorial Overview
Person re-identification (re-id) is a pivotal task within an intelligent surveillance pipeline and there exist numerous re-id frameworks that achieve satisfactory performance in challenging benchmarks.
Spectral Geometric Verification: Re-Ranking Point Cloud Retrieval for Metric Localization
We demonstrate how the optimal inter-cluster score of the correspondence compatibility graph of two point clouds represents a robust fitness score measuring their spatial consistency.
SESS: Saliency Enhancing with Scaling and Sliding
High-quality saliency maps are essential in several machine learning application areas including explainable AI and weakly supervised object detection and segmentation.
Towards On-Board Panoptic Segmentation of Multispectral Satellite Images
To address this challenge, we propose a multimodal teacher network based on a cross-modality attention-based fusion strategy to improve the segmentation accuracy by exploiting data from multiple modes.
InCloud: Incremental Learning for Point Cloud Place Recognition
In this paper we address the problem of incremental learning for point cloud place recognition and introduce InCloud, a structure-aware distillation-based approach which preserves the higher-order structure of the network's embedding space.
The State of Aerial Surveillance: A Survey
The rapid emergence of airborne platforms and imaging sensors are enabling new forms of aerial surveillance due to their unprecedented advantages in scale, mobility, deployment and covert observation capabilities.
Point Cloud Segmentation Using Sparse Temporal Local Attention
Point clouds are a key modality used for perception in autonomous vehicles, providing the means for a robust geometric understanding of the surrounding environment.
LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition
Experiments on two large-scale public benchmarks (KITTI and MulRan) show that our method achieves mean $F1_{max}$ scores of $0. 939$ and $0. 968$ on KITTI and MulRan respectively, achieving state-of-the-art performance while operating in near real-time.
Discriminative Domain-Invariant Adversarial Network for Deep Domain Generalization
Domain generalization approaches aim to learn a domain invariant prediction model for unknown target domains from multiple training source domains with different distributions.
Multi-Slice Net: A novel light weight framework for COVID-19 Diagnosis
This paper presents a novel lightweight COVID-19 diagnosis framework using CT scans.
Robust and Interpretable Temporal Convolution Network for Event Detection in Lung Sound Recordings
We exceed the state-of-the-art results in all evaluations.
Preserving Semantic Consistency in Unsupervised Domain Adaptation Using Generative Adversarial Networks
This network can achieve source to target domain matching by capturing semantic information at the feature level and producing images for unsupervised domain adaptation from both the source and the target domains.
Generative Adversarial Network
Unsupervised Domain Adaptation
Deep Domain Generalization with Feature-norm Network
To tackle the aforementioned problem, we introduce an end-to-end feature-norm network (FNN) which is robust to negative transfer as it does not need to match the feature distribution among the source domains.
Semantic Consistency and Identity Mapping Multi-Component Generative Adversarial Network for Person Re-Identification
In a real world environment, person re-identification (Re-ID) is a challenging task due to variations in lighting conditions, viewing angles, pose and occlusions.
Pose-driven Attention-guided Image Generation for Person Re-Identification
Person re-identification (re-ID) concerns the matching of subject images across different camera views in a multi camera surveillance system.
Learning Regional Attention over Multi-resolution Deep Convolutional Features for Trademark Retrieval
However, R-MAC suffers in the presence of background clutter/trivial regions and scale variance, and discards important spatial information.
An Efficient Framework for Zero-Shot Sketch-Based Image Retrieval
Recently, Zero-shot Sketch-based Image Retrieval (ZS-SBIR) has attracted the attention of the computer vision community due to it's real-world applications, and the more realistic and challenging setting than found in SBIR.
Im2Mesh GAN: Accurate 3D Hand Mesh Recovery from a Single RGB Image
This work addresses hand mesh recovery from a single RGB image.
Deep Learning for Medical Anomaly Detection -- A Survey
Machine learning-based medical anomaly detection is an important problem that has been extensively studied.
Complex-valued Iris Recognition Network
Unlike the problem of general object recognition, where real-valued neural networks can be used to extract pertinent features, iris recognition depends on the extraction of both phase and magnitude information from the input iris texture in order to better represent its biometric content.
Patient-independent Epileptic Seizure Prediction using Deep Learning Models
Patient-independent seizure prediction models are designed to offer accurate performance across multiple subjects within a dataset, and have been identified as a real-world solution to the seizure prediction problem.
Domain Generalization in Biosignal Classification
Conclusion: Recognizing the complexity induced by the inherent temporal nature of biosignal data, the two-stage method proposed in this study is able to effectively simplify the whole process of domain generalization while demonstrating good results on unseen domains and the adopted basis domains.
Multi-modal Fusion for Single-Stage Continuous Gesture Recognition
Gesture recognition is a much studied research area which has myriad real-world applications including robotics and human-machine interaction.
Fast & Slow Learning: Incorporating Synthetic Gradients in Neural Memory Controllers
In addition, we demonstrate the practical implications of the proposed learning strategy, where the feedback path can be shared among multiple neural memory networks as a mechanism for knowledge sharing.
Attention Driven Fusion for Multi-Modal Emotion Recognition
In this paper, we present a deep learning-based approach to exploit and fuse text and acoustic data for emotion classification.
Memory based fusion for multi-modal deep learning
The use of multi-modal data for deep machine learning has shown promise when compared to uni-modal approaches with fusion of multi-modal features resulting in improved performance in several applications.
Two-Stream Deep Feature Modelling for Automated Video Endoscopy Data Analysis
Automating the analysis of imagery of the Gastrointestinal (GI) tract captured during endoscopy procedures has substantial potential benefits for patients, as it can provide diagnostic support to medical practitioners and reduce mistakes via human error.
Meta Transfer Learning for Emotion Recognition
To mitigate this challenge, transfer learning performing fine-tuning on pre-trained models has been applied.
Facial Expression Recognition
Facial Expression Recognition (FER)
+2
A Robust Interpretable Deep Learning Classifier for Heart Anomaly Detection Without Segmentation
In this study, we explicitly examine the importance of heart sound segmentation as a prior step for heart sound classification, and then seek to apply the obtained insights to propose a robust classifier for abnormal heart sound detection.
End-to-End Domain Adaptive Attention Network for Cross-Domain Person Re-Identification
Person re-identification (re-ID) remains challenging in a real-world scenario, as it requires a trained network to generalise to totally unseen target data in the presence of variations across domains.
Hierarchical Attention Network for Action Segmentation
The temporal segmentation of events is an essential task and a precursor for the automatic recognition of human actions in the video.
Deep Auto-Encoders with Sequential Learning for Multimodal Dimensional Emotion Recognition
Multimodal dimensional emotion recognition has drawn a great attention from the affective computing community and numerous schemes have been extensively investigated, making a significant progress in this area.
Temporarily-Aware Context Modelling using Generative Adversarial Networks for Speech Activity Detection
This paper presents a novel framework for Speech Activity Detection (SAD).
Heart Sound Segmentation using Bidirectional LSTMs with Attention
This paper proposes a novel framework for the segmentation of phonocardiogram (PCG) signals into heart states, exploiting the temporal evolution of the PCG as well as considering the salient information that it provides for the detection of the heart state.
Joint Deep Cross-Domain Transfer Learning for Emotion Recognition
Deep learning has been applied to achieve significant progress in emotion recognition.
Learning Test-time Augmentation for Content-based Image Retrieval
However, their invariance to target data is pre-defined by the network architecture and training data.
Spatiotemporal Camera-LiDAR Calibration: A Targetless and Structureless Approach
The demand for multimodal sensing systems for robotics is growing due to the increase in robustness, reliability and accuracy offered by these systems.
Predicting the Future: A Jointly Learnt Model for Action Anticipation
Inspired by human neurological structures for action anticipation, we present an action anticipation model that enables the prediction of plausible future actions by forecasting both the visual and temporal future.
MTRNet++: One-stage Mask-based Scene Text Eraser
The results of ablation studies demonstrate that the proposed multi-branch architecture with attention blocks is effective and essential.
Correlation-aware Adversarial Domain Adaptation and Generalization
Domain adaptation (DA) and domain generalization (DG) have emerged as a solution to the domain shift problem where the distribution of the source and target data is different.
Ranked #16 on
Domain Adaptation
on ImageCLEF-DA
Exploiting Human Social Cognition for the Detection of Fake and Fraudulent Faces via Memory Networks
Advances in computer vision have brought us to the point where we have the ability to synthesise realistic fake content.
Neural Memory Plasticity for Anomaly Detection
In the domain of machine learning, Neural Memory Networks (NMNs) have recently achieved impressive results in a variety of application areas including visual question answering, trajectory prediction, object tracking, and language modelling.
Coupled Generative Adversarial Network for Continuous Fine-grained Action Segmentation
The goal of both GANs is to generate similar `action codes', a vector representation of the current action.
Fine-grained Action Segmentation using the Semi-Supervised Action GAN
In this paper we address the problem of continuous fine-grained action segmentation, in which multiple actions are present in an unsegmented video stream.
Forecasting Future Action Sequences with Neural Memory Networks
We propose a novel neural memory network based framework for future action sequence forecasting.
Rethinking Planar Homography Estimation Using Perspective Fields
In addition, the new parameterization of this task is general and can be implemented by any fully convolutional network (FCN) architecture.
Ranked #1 on
Homography Estimation
on COCO 2014
Constrained Design of Deep Iris Networks
On the other hand, it allows us to investigate the optimality of the classic IrisCode and recent iris networks.
Geometry-constrained Car Recognition Using a 3D Perspective Network
Unlike existing methods which only use attention mechanisms to locate 2D discriminative information, our work learns a novel 3D perspective feature representation of a vehicle, which is then fused with 2D appearance feature to predict the category.
MTRNet: A Generic Scene Text Eraser
Developing such a generic text eraser for real scenes is a challenging task, since it inherits all the challenges of multi-lingual and curved text detection and inpainting.
Memory Augmented Deep Generative models for Forecasting the Next Shot Location in Tennis
This paper presents a novel framework for predicting shot location and type in tennis.
On Minimum Discrepancy Estimation for Deep Domain Adaptation
In the presence of large sets of labeled data, Deep Learning (DL) has accomplished extraordinary triumphs in the avenue of computer vision, particularly in object classification and recognition tasks.
Multi-component Image Translation for Deep Domain Generalization
If DA methods are applied directly to DG by a simple exclusion of the target data from training, poor performance will result for a given task.
Ranked #125 on
Domain Generalization
on PACS
A Deep Four-Stream Siamese Convolutional Neural Network with Joint Verification and Identification Loss for Person Re-detection
In this paper, we propose a four stream Siamese deep convolutional neural network for person redetection that jointly optimises verification and identification losses over a four image input group.
GD-GAN: Generative Adversarial Networks for Trajectory Prediction and Group Detection in Crowds
This paper presents a novel deep learning framework for human trajectory prediction and detecting social group membership in crowds.
Multi-Level Sequence GAN for Group Activity Recognition
The generator is fed with person-level and scene-level features that are mapped temporally through LSTM networks.
Component-based Attention for Large-scale Trademark Retrieval
The demand for large-scale trademark retrieval (TR) systems has significantly increased to combat the rise in international trademark infringement.
Skeleton Driven Non-rigid Motion Tracking and 3D Reconstruction
We propose a puppet model-based tracking approach using skeleton prior, which provides a better initialization for tracking articulated movements.
Pedestrian Trajectory Prediction with Structured Memory Hierarchies
This paper presents a novel framework for human trajectory prediction based on multimodal data (video and radar).
Sparse Over-complete Patch Matching
State -of-the-art patch matching techniques take image patches as input to a convolutional neural network to extract the patch features and evaluate their similarity.
Non-rigid Reconstruction with a Single Moving RGB-D Camera
Our approach uses camera pose estimated from the rigid background for foreground tracking.
Meta Transfer Learning for Facial Emotion Recognition
The use of deep learning techniques for automatic facial expression recognition has recently attracted great interest but developed models are still unable to generalize well due to the lack of large emotion datasets for deep learning.
Deep Decision Trees for Discriminative Dictionary Learning with Adversarial Multi-Agent Trajectories
With the explosion in the availability of spatio-temporal tracking data in modern sports, there is an enormous opportunity to better analyse, learn and predict important events in adversarial group environments.
Learning Temporal Strategic Relationships using Generative Adversarial Imitation Learning
This paper presents a novel framework for automatic learning of complex strategies in human decision making.
Learning Free-Form Deformations for 3D Object Reconstruction
Representing 3D shape in deep learning frameworks in an accurate, efficient and compact manner still remains an open challenge.
Tracking by Prediction: A Deep Generative Model for Mutli-Person localisation and Tracking
We present a novel, complete deep learning framework for multi-person localisation and tracking.
Generative Adversarial Network
Pedestrian Trajectory Prediction
+2
Task Specific Visual Saliency Prediction with Memory Augmented Conditional Generative Adversarial Networks
Visual saliency patterns are the result of a variety of factors aside from the image being parsed, however existing approaches have ignored these.
Deep Classification of Epileptic Signals
Electrophysiological observation plays a major role in epilepsy evaluation.
Image2Mesh: A Learning Framework for Single Image 3D Reconstruction
One challenge that remains open in 3D deep learning is how to efficiently represent 3D data to feed deep networks.
Elastic LiDAR Fusion: Dense Map-Centric Continuous-Time SLAM
The concept of continuous-time trajectory representation has brought increased accuracy and efficiency to multi-modal sensor fusion in modern SLAM.
Robotics
Compact Model Representation for 3D Reconstruction
3D reconstruction from 2D images is a central problem in computer vision.
Joint Max Margin and Semantic Features for Continuous Event Detection in Complex Scenes
In this paper the problem of complex event detection in the continuous domain (i. e. events with unknown starting and ending locations) is addressed.
Two Stream LSTM: A Deep Fusion Framework for Human Action Recognition
Our contribution in this paper is a deep fusion framework that more effectively exploits spatial features from CNNs with temporal features from LSTM models.
Tree Memory Networks for Modelling Long-term Temporal Dependencies
In this paper, we propose a Tree Memory Network (TMN) for modelling long term and short term relationships in sequence-to-sequence mapping problems.
Soft + Hardwired Attention: An LSTM Framework for Human Trajectory Prediction and Abnormal Event Detection
We illustrate how a simple approximation of attention weights (i. e hard-wired) can be merged together with soft attention weights in order to make our model applicable for challenging real world scenarios with hundreds of neighbours.
Fast, Dense Feature SDM on an iPhone
In this paper, we present our method for enabling dense SDM to run at over 90 FPS on a mobile device.
Automatic Event Detection for Signal-based Surveillance
Though such systems are still heavily reliant on human labour to monitor the captured information, there have been a number of automatic techniques proposed to analysing the data.
Learning Temporal Alignment Uncertainty for Efficient Event Detection
A popular approach in this regard is to represent a sequence using a bag of words (BOW) representation due to its: (i) fixed dimensionality irrespective of the sequence length, and (ii) its ability to compactly model the statistics in the sequence.
Learning detectors quickly using structured covariance matrices
Computer vision is increasingly becoming interested in the rapid estimation of object detectors.
