Search Results for author:
Found 40 papers, 23 papers with code
Two-Person Interaction Augmentation with Skeleton Priors
Close and continuous interaction with rich contacts is a crucial aspect of human activities (e. g. hugging, dancing) and of interest in many domains like activity recognition, motion prediction, character animation, etc.
MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessment
We propose Continual AQA (CAQA) to refine models using sparse new data.
HINT: High-quality INPainting Transformer with Mask-Aware Encoding and Enhanced Attention
In this paper, we propose an end-to-end High-quality INpainting Transformer, abbreviated as HINT, which consists of a novel mask-aware pixel-shuffle downsampling module (MPD) to preserve the visible information extracted from the corrupted image while maintaining the integrity of the information available for high-level inferences made within the model.
Enhancing Surgical Performance in Cardiothoracic Surgery with Innovations from Computer Vision and Artificial Intelligence: A Narrative Review
When technical requirements are high, and patient outcomes are critical, opportunities for monitoring and improving surgical skills via objective motion analysis feedback may be particularly beneficial.
Pose-based Tremor Type and Level Analysis for Parkinson's Disease from Video
The accuracy of diagnosis ranges between 73% and 84%, and is influenced by the experience of the clinical assessor.
Correlation-Distance Graph Learning for Treatment Response Prediction from rs-fMRI
To overcome that, we propose a graph learning framework that captures comprehensive features by integrating both correlation and distance-based similarity measures under a contrastive loss.
U3DS$^3$: Unsupervised 3D Semantic Scene Segmentation
To achieve this, U3DS$^3$ leverages a generalized unsupervised segmentation method for both object and background across both indoor and outdoor static 3D point clouds with no requirement for model pre-training, by leveraging only the inherent information of the point cloud to achieve full 3D scene segmentation.
Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers
Generating 3D images of complex objects conditionally from a few 2D views is a difficult synthesis problem, compounded by issues such as domain gap and geometric misalignment.
Enhancing Perception and Immersion in Pre-Captured Environments through Learning-Based Eye Height Adaptation
To explore this influence, we first propose a pilot study that captures real environments with multiple eye heights and asks participants to judge the egocentric distances and immersion.
Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient
Specifically, we first learn a motion manifold where we define an adversarial loss to compute a new gradient for the attack, named skeleton-motion-informed (SMI) gradient.
On the Design Fundamentals of Diffusion Models: A Survey
Diffusion models are generative models, which gradually add and remove noise to learn the underlying distribution of training data for data generation.
INCLG: Inpainting for Non-Cleft Lip Generation with a Multi-Task Image Processing Network
We present a software that predicts non-cleft facial images for patients with cleft lip, thereby facilitating the understanding, awareness and discussion of cleft lip surgeries.
Focalized Contrastive View-invariant Learning for Self-supervised Skeleton-based Action Recognition
Learning view-invariant representation is a key to improving feature discrimination power for skeleton-based action recognition.
Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation
Whilst the availability of 3D LiDAR point cloud data has significantly grown in recent years, annotation remains expensive and time-consuming, leading to a demand for semi-supervised semantic segmentation methods with application domains such as autonomous driving.
Ranked #1 on
3D Semantic Segmentation
on ScribbleKITTI
(mIoU-1% metric)
Tackling Data Bias in Painting Classification with Style Transfer
We propose a system to handle data bias in small paintings datasets like the Kaokore dataset while simultaneously accounting for domain adaptation in fine-tuning a model trained on real world images.
Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models
To achieve high-quality results, we design a multi-task architecture of diffusion model that strategically generates aspects of human motions for local guidance.
3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models
Acquiring the virtual equivalent of exhibits, such as sculptures, in virtual reality (VR) museums, can be labour-intensive and sometimes infeasible.
Denoising Diffusion Probabilistic Models for Styled Walking Synthesis
Generating realistic motions for digital humans is time-consuming for many graphics applications.
CP-AGCN: Pytorch-based Attention Informed Graph Convolutional Network for Identifying Infants at Risk of Cerebral Palsy
Early prediction is clinically considered one of the essential parts of cerebral palsy (CP) treatment.
A Two-stream Convolutional Network for Musculoskeletal and Neurological Disorders Prediction
As a result, we propose a solution that explicitly takes both individual joint features and inter-joint features as input, relieving the system from the need of discovering more complicated features from small data.
Towards Graph Representation Learning Based Surgical Workflow Anticipation
Hence, we propose a graph representation learning framework to comprehensively represent instrument motions in the surgical workflow anticipation problem.
A Feasibility Study on Image Inpainting for Non-cleft Lip Generation from Patients with Cleft Lip
A Cleft lip is a congenital abnormality requiring surgical repair by a specialist.
Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos
Consider that geometric features such as human pose and object position provide meaningful information to understand HOIs, we argue to combine the benefits of both visual and geometric features in HOI recognition, and propose a novel Two-level Geometric feature-informed Graph Convolutional Network (2G-GCN).
Pose-based Tremor Classification for Parkinson's Disease Diagnosis from Video
To this end, we propose to classify Parkinson's tremor since it is one of the most predominant symptoms of PD with strong generalizability.
A Skeleton-aware Graph Convolutional Network for Human-Object Interaction Detection
Our network exploits the spatial connections between human keypoints and object keypoints to capture their fine-grained structural interactions via graph convolutions.
Ranked #22 on
Human-Object Interaction Detection
on V-COCO
Multiclass-SGCN: Sparse Graph-based Trajectory Prediction with Agent Class Embedding
Trajectory prediction of road users in real-world scenarios is challenging because their movement patterns are stochastic and complex.
Ranked #1 on
Trajectory Prediction
on SDD
Cerebral Palsy Prediction with Frequency Attention Informed Graph Convolutional Networks
Our prediction performance achieves state-of-the-art research on both datasets.
RobIn: A Robust Interpretable Deep Network for Schizophrenia Diagnosis
We collect a data set of psychiatric observations of patients based on DSM-5 criteria.
360 Depth Estimation in the Wild -- The Depth360 Dataset and the SegFuse Network
In this work, we first establish a large-scale dataset with varied settings called Depth360 to tackle the training data problem.
MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-aware CT-Projections from a Single X-ray
Computed tomography (CT) is an effective medical imaging modality, widely used in the field of clinical medicine for the diagnosis of various pathologies.
DurLAR: A High-Fidelity 128-Channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-Modal Autonomous Driving Applications
Leveraging DurLAR, with a resolution exceeding that of prior benchmarks, we consider the task of monocular depth estimation and use this increased avail- ability of higher resolution, yet sparse ground truth scene depth information to propose a novel joint supervised/self- supervised loss formulation.
Spoofing Detection on Hand Images Using Quality Assessment
A presentation attack detection approach is addressed by assessing the visual quality of genuine and fake hand images.
Semi-Supervised Crowd Counting from Unlabeled Data
Our method achieved competitive performance in semi-supervised learning approaches on these crowd counting datasets.
Semantics-STGCNN: A Semantics-guided Spatial-Temporal Graph Convolutional Network for Multi-class Trajectory Prediction
This is because they ignore the impact of the implicit correlations between different types of road users on the trajectory to be predicted - for example, a nearby pedestrian has a different level of influence from a nearby car.
Interpreting Deep Learning based Cerebral Palsy Prediction with Channel Attention
To highlight the capacity of the deep network in modelling input features, we utilize raw joint positions instead of hand-crafted features.
UAV-ReID: A Benchmark on Unmanned Aerial Vehicle Re-identification in Video Imagery
As unmanned aerial vehicles (UAVs) become more accessible with a growing range of applications, the potential risk of UAV disruption increases.
Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark
Unmanned Aerial Vehicles (UAV) can pose a major risk for aviation safety, due to both negligent and malicious use.
Illumination-Based Data Augmentation for Robust Background Subtraction
A core challenge in background subtraction (BGS) is handling videos with sudden illumination changes in consecutive frames.
Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling
In this paper, we propose a new deep network to tackle these challenges by creating a natural motion manifold that is versatile for many applications.
