84 citations · 186 across the 62 of their papers we have counts for
48 papers · 1 filter
Where Will They Go? Modelling Multimodal Pedestrian Manoeuvres from Ego-centric Videos
Yuxuan Xie, Nicolas Pugeault, Chongfeng Wei +2
Pedestrian trajectory prediction from an on-board ego-centric camera is challenging since it depends on complex interactions with vehicles and scene context, as well as the intenti…
Feed-forward Motion In-betweening for Any 4D
Hiroki Nishizawa, Hubert P. H. Shum, Yoshihiro Fukuhara +2
4D dynamics (3D geometry evolving over time) is a fundamental representation of the physical world and plays a crucial role in world modeling (e.g., animation and games). Owing to…
Quality-Preserving Imperceptible Adversarial Attack on Skeleton-based Human Action Recognition
Ziyi Chang, Kanglei Zhou, Xiaohui Liang +1
Adversarial attacks on skeletal human action recognition have received significant attention. However, existing methods typically introduce noise-like perturbations that degrade mo…
KD360-VoxelBEV: LiDAR and 360-degree Camera Cross Modality Knowledge Distillation for Bird's-Eye-View Segmentation
Wenke E, Yixin Sun, Jiaxu Liu +3
We present the first cross-modality distillation framework specifically tailored for single-panoramic-camera Bird's-Eye-View (BEV) segmentation. Our approach leverages a novel LiDA…
Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videos
Tanqiu Qiao, Ruochen Li, Frederick W. B. Li +3
Human-Object Interaction (HOI) recognition in videos requires understanding both visual patterns and geometric relationships as they evolve over time. Visual and geometric features…
TFDM: Time-Variant Frequency-Based Point Cloud Diffusion with Mamba
Jiaxu Liu, Li Li, Hubert P. H. Shum +1
Diffusion models currently demonstrate impressive performance over various generative tasks. Recent work on image diffusion highlights the strong capabilities of Mamba (state space…
BP-SGCN: Behavioral Pseudo-Label Informed Sparse Graph Convolution Network for Pedestrian and Heterogeneous Trajectory Prediction
Ruochen Li, Stamos Katsigiannis, Tae-Kyun Kim +1
Trajectory prediction allows better decision-making in applications of autonomous vehicles or surveillance by predicting the short-term future movement of traffic agents. It is cla…
Unified Spatial-Temporal Edge-Enhanced Graph Networks for Pedestrian Trajectory Prediction
Ruochen Li, Tanqiu Qiao, Stamos Katsigiannis +2
Pedestrian trajectory prediction aims to forecast future movements based on historical paths. Spatial-temporal (ST) methods often separately model spatial interactions among pedest…
SEM-Net: Efficient Pixel Modelling for image inpainting with Spatially Enhanced SSM
Shuang Chen, Haozheng Zhang, Amir Atapour-Abarghouei +1
Image inpainting aims to repair a partially damaged image based on the information from known regions of the images. \revise{Achieving semantically plausible inpainting results is…
Two-Stage Human Verification using HandCAPTCHA and Anti-Spoofed Finger Biometrics with Feature Selection
Asish Bera, Debotosh Bhattacharjee, Hubert P H Shum
This paper presents a human verification scheme in two independent stages to overcome the vulnerabilities of attacks and to enhance security. At the first stage, a hand image-based…
One-Index Vector Quantization Based Adversarial Attack on Image Classification
Haiju Fan, Xiaona Qin, Shuang Chen +2
To improve storage and transmission, images are generally compressed. Vector quantization (VQ) is a popular compression method as it has a high compression ratio that suppresses ot…
TraIL-Det: Transformation-Invariant Local Feature Networks for 3D LiDAR Object Detection with Unsupervised Pre-Training
Li Li, Tanqiu Qiao, Hubert P. H. Shum +1
3D point clouds are essential for perceiving outdoor scenes, especially within the realm of autonomous driving. Recent advances in 3D LiDAR Object Detection focus primarily on the…
MxT: Mamba x Transformer for Image Inpainting
Shuang Chen, Amir Atapour-Abarghouei, Haozheng Zhang +1
Image inpainting, or image completion, is a crucial task in computer vision that aims to restore missing or damaged regions of images with semantically coherent content. This techn…
From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos
Tanqiu Qiao, Ruochen Li, Frederick W. B. Li +1
Video-based Human-Object Interaction (HOI) recognition explores the intricate dynamics between humans and objects, which are essential for a comprehensive understanding of human be…
RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentation
Li Li, Hubert P. H. Shum, Toby P. Breckon
3D point clouds play a pivotal role in outdoor scene perception, especially in the context of autonomous driving. Recent advancements in 3D LiDAR segmentation often focus intensely…
Geometric Features Enhanced Human-Object Interaction Detection
Manli Zhu, Edmond S. L. Ho, Shuang Chen +2
Cameras are essential vision instruments to capture images for pattern detection and measurement. Human-object interaction (HOI) detection is one of the most popular pattern detect…
Repeat and Concatenate: 2D to 3D Image Translation with 3D to 3D Generative Modeling
Abril Corona-Figueroa, Hubert P. H. Shum, Chris G. Willcocks
This paper investigates a 2D to 3D image translation method with a straightforward technique, enabling correlated 2D X-ray to 3D CT-like reconstruction. We observe that existing ap…
DurLAR: A High-fidelity 128-channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-modal Autonomous Driving Applications
Li Li, Khalid N. Ismail, Hubert P. H. Shum +1
We present DurLAR, a high-fidelity 128-channel 3D LiDAR dataset with panoramic ambient (near infrared) and reflectivity imagery, as well as a sample benchmark task using depth esti…
Two-Person Interaction Augmentation with Skeleton Priors
Baiyi Li, Edmond S. L. Ho, Hubert P. H. Shum +1
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, motio…
HINT: High-quality INPainting Transformer with Mask-Aware Encoding and Enhanced Attention
Shuang Chen, Amir Atapour-Abarghouei, Hubert P. H. Shum
Existing image inpainting methods leverage convolution-based downsampling approaches to reduce spatial dimensions. This may result in information loss from corrupted images where t…
Pose-based Tremor Type and Level Analysis for Parkinson's Disease from Video
Haozheng Zhang, Edmond S. L. Ho, Xiatian Zhang +2
Purpose:Current methods for diagnosis of PD rely on clinical examination. The accuracy of diagnosis ranges between 73% and 84%, and is influenced by the experience of the clinical…
U3DS: Unsupervised 3D Semantic Scene Segmentation
Jiaxu Liu, Zhengdi Yu, Toby P. Breckon +1
Contemporary point cloud segmentation approaches largely rely on richly annotated 3D training data. However, it is both time-consuming and challenging to obtain consistently accura…
Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers
Abril Corona-Figueroa, Sam Bond-Taylor, Neelanjan Bhowmik +4
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. For…
Enhancing Perception and Immersion in Pre-Captured Environments through Learning-Based Eye Height Adaptation
Qi Feng, Hubert P. H. Shum, Shigeo Morishima
Pre-captured immersive environments using omnidirectional cameras provide a wide range of virtual reality applications. Previous research has shown that manipulating the eye height…