Hubert P. H. Shum

Shuang Chen, Amir Atapour-Abarghouei, Haozheng Zhang et al.

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 technique requires a precise balance of local texture replication and global contextual understanding to ensure the restored image integrates seamlessly with its surroundings. Traditional methods using Convolutional Neural Networks (CNNs) are effective at capturing local patterns but often struggle with broader contextual relationships due to the limited receptive fields. Recent advancements have incorporated transformers, leveraging their ability to understand global interactions. However, these methods face computational inefficiencies and struggle to maintain fine-grained details. To overcome these challenges, we introduce MxT composed of the proposed Hybrid Module (HM), which combines Mamba with the transformer in a synergistic manner. Mamba is adept at efficiently processing long sequences with linear computational costs, making it an ideal complement to the transformer for handling long-scale data interactions. Our HM facilitates dual-level interaction learning at both pixel and patch levels, greatly enhancing the model to reconstruct images with high quality and contextual accuracy. We evaluate MxT on the widely-used CelebA-HQ and Places2-standard datasets, where it consistently outperformed existing state-of-the-art methods. The code will be released: {\url{https://github.com/ChrisChen1023/MxT}}.

Li Li, Hubert P. H. Shum, Toby P. Breckon

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. Existing work very often employs relatively large segmentation backbone networks to improve segmentation accuracy, at the expense of computational costs. In addition, many use uniform sampling to reduce ground truth data requirements for learning needed, often resulting in sub-optimal performance. To address these issues, we propose a new pipeline that employs a smaller architecture, requiring fewer ground-truth annotations to achieve superior segmentation accuracy compared to contemporary approaches. This is facilitated via a novel Sparse Depthwise Separable Convolution module that significantly reduces the network parameter count while retaining overall task performance. To effectively sub-sample our training data, we propose a new Spatio-Temporal Redundant Frame Downsampling (ST-RFD) method that leverages knowledge of sensor motion within the environment to extract a more diverse subset of training data frame samples. To leverage the use of limited annotated data samples, we further propose a soft pseudo-label method informed by LiDAR reflectivity. Our method outperforms contemporary semi-supervised work in terms of mIoU, using less labeled data, on the SemanticKITTI (59.5@5%) and ScribbleKITTI (58.1@5%) benchmark datasets, based on a 2.3x reduction in model parameters and 641x fewer multiply-add operations whilst also demonstrating significant performance improvement on limited training data (i.e., Less is More).

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 on the spatial positioning and distribution of points for accurate segmentation. However, these methods, while robust in variable conditions, encounter challenges due to sole reliance on coordinates and point intensity, leading to poor isometric invariance and suboptimal segmentation. To tackle this challenge, our work introduces Range-Aware Pointwise Distance Distribution (RAPiD) features and the associated RAPiD-Seg architecture. Our RAPiD features exhibit rigid transformation invariance and effectively adapt to variations in point density, with a design focus on capturing the localized geometry of neighboring structures. They utilize inherent LiDAR isotropic radiation and semantic categorization for enhanced local representation and computational efficiency, while incorporating a 4D distance metric that integrates geometric and surface material reflectivity for improved semantic segmentation. To effectively embed high-dimensional RAPiD features, we propose a double-nested autoencoder structure with a novel class-aware embedding objective to encode high-dimensional features into manageable voxel-wise embeddings. Additionally, we propose RAPiD-Seg which incorporates a channel-wise attention fusion and two effective RAPiD-Seg variants, further optimizing the embedding for enhanced performance and generalization. Our method outperforms contemporary LiDAR segmentation work in terms of mIoU on SemanticKITTI (76.1) and nuScenes (83.6) datasets.

Jiaxu Liu, Zhengdi Yu, Toby P. Breckon et al.

Contemporary point cloud segmentation approaches largely rely on richly annotated 3D training data. However, it is both time-consuming and challenging to obtain consistently accurate annotations for such 3D scene data. Moreover, there is still a lack of investigation into fully unsupervised scene segmentation for point clouds, especially for holistic 3D scenes. This paper presents U3DS$^3$, as a step towards completely unsupervised point cloud segmentation for any holistic 3D scenes. 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. The initial step of our proposed approach involves generating superpoints based on the geometric characteristics of each scene. Subsequently, it undergoes a learning process through a spatial clustering-based methodology, followed by iterative training using pseudo-labels generated in accordance with the cluster centroids. Moreover, by leveraging the invariance and equivariance of the volumetric representations, we apply the geometric transformation on voxelized features to provide two sets of descriptors for robust representation learning. Finally, our evaluation provides state-of-the-art results on the ScanNet and SemanticKITTI, and competitive results on the S3DIS, benchmark datasets.

Tanqiu Qiao, Qianhui Men, Frederick W. B. Li et al.

Human-Object Interaction (HOI) recognition in videos is important for analyzing human activity. Most existing work focusing on visual features usually suffer from occlusion in the real-world scenarios. Such a problem will be further complicated when multiple people and objects are involved in HOIs. 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). The geometric-level graph models the interdependency between geometric features of humans and objects, while the fusion-level graph further fuses them with visual features of humans and objects. To demonstrate the novelty and effectiveness of our method in challenging scenarios, we propose a new multi-person HOI dataset (MPHOI-72). Extensive experiments on MPHOI-72 (multi-person HOI), CAD-120 (single-human HOI) and Bimanual Actions (two-hand HOI) datasets demonstrate our superior performance compared to state-of-the-arts.

Qianhui Men, Edmond S. L. Ho, Hubert P. H. Shum et al.

Learning view-invariant representation is a key to improving feature discrimination power for skeleton-based action recognition. Existing approaches cannot effectively remove the impact of viewpoint due to the implicit view-dependent representations. In this work, we propose a self-supervised framework called Focalized Contrastive View-invariant Learning (FoCoViL), which significantly suppresses the view-specific information on the representation space where the viewpoints are coarsely aligned. By maximizing mutual information with an effective contrastive loss between multi-view sample pairs, FoCoViL associates actions with common view-invariant properties and simultaneously separates the dissimilar ones. We further propose an adaptive focalization method based on pairwise similarity to enhance contrastive learning for a clearer cluster boundary in the learned space. Different from many existing self-supervised representation learning work that rely heavily on supervised classifiers, FoCoViL performs well on both unsupervised and supervised classifiers with superior recognition performance. Extensive experiments also show that the proposed contrastive-based focalization generates a more discriminative latent representation.

Ziyi Chang, Edmund J. C. Findlay, Haozheng Zhang et al.

Generating realistic motions for digital humans is a core but challenging part of computer animations and games, as human motions are both diverse in content and rich in styles. While the latest deep learning approaches have made significant advancements in this domain, they mostly consider motion synthesis and style manipulation as two separate problems. This is mainly due to the challenge of learning both motion contents that account for the inter-class behaviour and styles that account for the intra-class behaviour effectively in a common representation. To tackle this challenge, we propose a denoising diffusion probabilistic model solution for styled motion synthesis. As diffusion models have a high capacity brought by the injection of stochasticity, we can represent both inter-class motion content and intra-class style behaviour in the same latent. This results in an integrated, end-to-end trained pipeline that facilitates the generation of optimal motion and exploration of content-style coupled latent space. To achieve high-quality results, we design a multi-task architecture of diffusion model that strategically generates aspects of human motions for local guidance. We also design adversarial and physical regulations for global guidance. We demonstrate superior performance with quantitative and qualitative results and validate the effectiveness of our multi-task architecture.

Haozheng Zhang, Edmond S. L. Ho, Xiatian Zhang et al.

Parkinson's disease (PD) is a progressive neurodegenerative disorder that results in a variety of motor dysfunction symptoms, including tremors, bradykinesia, rigidity and postural instability. The diagnosis of PD mainly relies on clinical experience rather than a definite medical test, and the diagnostic accuracy is only about 73-84% since it is challenged by the subjective opinions or experiences of different medical experts. Therefore, an efficient and interpretable automatic PD diagnosis system is valuable for supporting clinicians with more robust diagnostic decision-making. To this end, we propose to classify Parkinson's tremor since it is one of the most predominant symptoms of PD with strong generalizability. Different from other computer-aided time and resource-consuming Parkinson's Tremor (PT) classification systems that rely on wearable sensors, we propose SPAPNet, which only requires consumer-grade non-intrusive video recording of camera-facing human movements as input to provide undiagnosed patients with low-cost PT classification results as a PD warning sign. For the first time, we propose to use a novel attention module with a lightweight pyramidal channel-squeezing-fusion architecture to extract relevant PT information and filter the noise efficiently. This design aids in improving both classification performance and system interpretability. Experimental results show that our system outperforms state-of-the-arts by achieving a balanced accuracy of 90.9% and an F1-score of 90.6% in classifying PT with the non-PT class.

Ruochen Li, Stamos Katsigiannis, Hubert P. H. Shum

Trajectory prediction of road users in real-world scenarios is challenging because their movement patterns are stochastic and complex. Previous pedestrian-oriented works have been successful in modelling the complex interactions among pedestrians, but fail in predicting trajectories when other types of road users are involved (e.g., cars, cyclists, etc.), because they ignore user types. Although a few recent works construct densely connected graphs with user label information, they suffer from superfluous spatial interactions and temporal dependencies. To address these issues, we propose Multiclass-SGCN, a sparse graph convolution network based approach for multi-class trajectory prediction that takes into consideration velocity and agent label information and uses a novel interaction mask to adaptively decide the spatial and temporal connections of agents based on their interaction scores. The proposed approach significantly outperformed state-of-the-art approaches on the Stanford Drone Dataset, providing more realistic and plausible trajectory predictions.

Haozheng Zhang, Hubert P. H. Shum, Edmond S. L. Ho

Early diagnosis and intervention are clinically considered the paramount part of treating cerebral palsy (CP), so it is essential to design an efficient and interpretable automatic prediction system for CP. We highlight a significant difference between CP infants' frequency of human movement and that of the healthy group, which improves prediction performance. However, the existing deep learning-based methods did not use the frequency information of infants' movement for CP prediction. This paper proposes a frequency attention informed graph convolutional network and validates it on two consumer-grade RGB video datasets, namely MINI-RGBD and RVI-38 datasets. Our proposed frequency attention module aids in improving both classification performance and system interpretability. In addition, we design a frequency-binning method that retains the critical frequency of the human joint position data while filtering the noise. Our prediction performance achieves state-of-the-art research on both datasets. Our work demonstrates the effectiveness of frequency information in supporting the prediction of CP non-intrusively and provides a way for supporting the early diagnosis of CP in the resource-limited regions where the clinical resources are not abundant.

Abril Corona-Figueroa, Sam Bond-Taylor, Neelanjan Bhowmik et al.

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 instance, a unified framework such as Generative Adversarial Networks cannot achieve this unless they explicitly define both a domain-invariant and geometric-invariant joint latent distribution, whereas Neural Radiance Fields are generally unable to handle both issues as they optimize at the pixel level. By contrast, we propose a simple and novel 2D to 3D synthesis approach based on conditional diffusion with vector-quantized codes. Operating in an information-rich code space enables high-resolution 3D synthesis via full-coverage attention across the views. Specifically, we generate the 3D codes (e.g. for CT images) conditional on previously generated 3D codes and the entire codebook of two 2D views (e.g. 2D X-rays). Qualitative and quantitative results demonstrate state-of-the-art performance over specialized methods across varied evaluation criteria, including fidelity metrics such as density, coverage, and distortion metrics for two complex volumetric imagery datasets from in real-world scenarios.

Zhengzhi Lu, He Wang, Ziyi Chang et al.

Recently, methods for skeleton-based human activity recognition have been shown to be vulnerable to adversarial attacks. However, these attack methods require either the full knowledge of the victim (i.e. white-box attacks), access to training data (i.e. transfer-based attacks) or frequent model queries (i.e. black-box attacks). All their requirements are highly restrictive, raising the question of how detrimental the vulnerability is. In this paper, we show that the vulnerability indeed exists. To this end, we consider a new attack task: the attacker has no access to the victim model or the training data or labels, where we coin the term hard no-box attack. 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. Our gradient contains information of the motion dynamics, which is different from existing gradient-based attack methods that compute the loss gradient assuming each dimension in the data is independent. The SMI gradient can augment many gradient-based attack methods, leading to a new family of no-box attack methods. Extensive evaluation and comparison show that our method imposes a real threat to existing classifiers. They also show that the SMI gradient improves the transferability and imperceptibility of adversarial samples in both no-box and transfer-based black-box settings.

Edmund J. C. Findlay, Haozheng Zhang, Ziyi Chang et al.

Generating realistic motions for digital humans is time-consuming for many graphics applications. Data-driven motion synthesis approaches have seen solid progress in recent years through deep generative models. These results offer high-quality motions but typically suffer in motion style diversity. For the first time, we propose a framework using the denoising diffusion probabilistic model (DDPM) to synthesize styled human motions, integrating two tasks into one pipeline with increased style diversity compared with traditional motion synthesis methods. Experimental results show that our system can generate high-quality and diverse walking motions.

Haozheng Zhang, Edmond S. L. Ho, Hubert P. H. Shum

Early prediction is clinically considered one of the essential parts of cerebral palsy (CP) treatment. We propose to implement a low-cost and interpretable classification system for supporting CP prediction based on General Movement Assessment (GMA). We design a Pytorch-based attention-informed graph convolutional network to early identify infants at risk of CP from skeletal data extracted from RGB videos. We also design a frequency-binning module for learning the CP movements in the frequency domain while filtering noise. Our system only requires consumer-grade RGB videos for training to support interactive-time CP prediction by providing an interpretable CP classification result.

Ziyi Chang, George Alex Koulieris, Hyung Jin Chang et al.

Diffusion models are learning pattern-learning systems to model and sample from data distributions with three functional components namely the forward process, the reverse process, and the sampling process. The components of diffusion models have gained significant attention with many design factors being considered in common practice. Existing reviews have primarily focused on higher-level solutions, covering less on the design fundamentals of components. This study seeks to address this gap by providing a comprehensive and coherent review of seminal designable factors within each functional component of diffusion models. This provides a finer-grained perspective of diffusion models, benefiting future studies in the analysis of individual components, the design factors for different purposes, and the implementation of diffusion models.

Shuang Chen, Amir Atapour-Abarghouei, Jane Kerby et al.

A Cleft lip is a congenital abnormality requiring surgical repair by a specialist. The surgeon must have extensive experience and theoretical knowledge to perform surgery, and Artificial Intelligence (AI) method has been proposed to guide surgeons in improving surgical outcomes. If AI can be used to predict what a repaired cleft lip would look like, surgeons could use it as an adjunct to adjust their surgical technique and improve results. To explore the feasibility of this idea while protecting patient privacy, we propose a deep learning-based image inpainting method that is capable of covering a cleft lip and generating a lip and nose without a cleft. Our experiments are conducted on two real-world cleft lip datasets and are assessed by expert cleft lip surgeons to demonstrate the feasibility of the proposed method.

Li Li, Tanqiu Qiao, Hubert P. H. Shum et al.

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 spatial positioning and distribution of points to ensure accurate detection. However, despite their robust performance in variable conditions, these methods are hindered by their sole reliance on coordinates and point intensity, resulting in inadequate isometric invariance and suboptimal detection outcomes. To tackle this challenge, our work introduces Transformation-Invariant Local (TraIL) features and the associated TraIL-Det architecture. Our TraIL features exhibit rigid transformation invariance and effectively adapt to variations in point density, with a design focus on capturing the localized geometry of neighboring structures. They utilize the inherent isotropic radiation of LiDAR to enhance local representation, improve computational efficiency, and boost detection performance. To effectively process the geometric relations among points within each proposal, we propose a Multi-head self-Attention Encoder (MAE) with asymmetric geometric features to encode high-dimensional TraIL features into manageable representations. Our method outperforms contemporary self-supervised 3D object detection approaches in terms of mAP on KITTI (67.8, 20% label, moderate) and Waymo (68.9, 20% label, moderate) datasets under various label ratios (20%, 50%, and 100%).

Xiatian Zhang, Noura Al Moubayed, Hubert P. H. Shum

Surgical workflow anticipation can give predictions on what steps to conduct or what instruments to use next, which is an essential part of the computer-assisted intervention system for surgery, e.g. workflow reasoning in robotic surgery. However, current approaches are limited to their insufficient expressive power for relationships between instruments. Hence, we propose a graph representation learning framework to comprehensively represent instrument motions in the surgical workflow anticipation problem. In our proposed graph representation, we maps the bounding box information of instruments to the graph nodes in the consecutive frames and build inter-frame/inter-instrument graph edges to represent the trajectory and interaction of the instruments over time. This design enhances the ability of our network on modeling both the spatial and temporal patterns of surgical instruments and their interactions. In addition, we design a multi-horizon learning strategy to balance the understanding of various horizons indifferent anticipation tasks, which significantly improves the model performance in anticipation with various horizons. Experiments on the Cholec80 dataset demonstrate the performance of our proposed method can exceed the state-of-the-art method based on richer backbones, especially in instrument anticipation (1.27 v.s. 1.48 for inMAE; 1.48 v.s. 2.68 for eMAE). To the best of our knowledge, we are the first to introduce a spatial-temporal graph representation into surgical workflow anticipation.

Manli Zhu, Edmond S. L. Ho, Hubert P. H. Shum

Detecting human-object interactions is essential for comprehensive understanding of visual scenes. In particular, spatial connections between humans and objects are important cues for reasoning interactions. To this end, we propose a skeleton-aware graph convolutional network for human-object interaction detection, named SGCN4HOI. Our network exploits the spatial connections between human keypoints and object keypoints to capture their fine-grained structural interactions via graph convolutions. It fuses such geometric features with visual features and spatial configuration features obtained from human-object pairs. Furthermore, to better preserve the object structural information and facilitate human-object interaction detection, we propose a novel skeleton-based object keypoints representation. The performance of SGCN4HOI is evaluated in the public benchmark V-COCO dataset. Experimental results show that the proposed approach outperforms the state-of-the-art pose-based models and achieves competitive performance against other models.

Ruisheng Han, Kanglei Zhou, Shuang Chen et al.

Action Quality Assessment (AQA) predicts fine-grained execution scores from action videos and is widely applied in sports, rehabilitation, and skill evaluation. Long-term AQA, as in figure skating or rhythmic gymnastics, is especially challenging since it requires modeling extended temporal dynamics while remaining robust to contextual confounders. Existing approaches either depend on costly annotations or rely on unidirectional temporal modeling, making them vulnerable to spurious correlations and unstable long-term representations. To this end, we propose CaFlow, a unified framework that integrates counterfactual de-confounding with bidirectional time-conditioned flow. The Causal Counterfactual Regularization (CCR) module disentangles causal and confounding features in a self-supervised manner and enforces causal robustness through counterfactual interventions, while the BiT-Flow module models forward and backward dynamics with a cycle-consistency constraint to produce smoother and more coherent representations. Extensive experiments on multiple long-term AQA benchmarks demonstrate that CaFlow achieves state-of-the-art performance. Code is available at https://github.com/Harrison21/CaFlow

Mridula Vijendran, Frederick W. B. Li, Hubert P. H. Shum

It is difficult to train classifiers on paintings collections due to model bias from domain gaps and data bias from the uneven distribution of artistic styles. Previous techniques like data distillation, traditional data augmentation and style transfer improve classifier training using task specific training datasets or domain adaptation. 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. Our system consists of two stages which are style transfer and classification. In the style transfer stage, we generate the stylized training samples per class with uniformly sampled content and style images and train the style transformation network per domain. In the classification stage, we can interpret the effectiveness of the style and content layers at the attention layers when training on the original training dataset and the stylized images. We can tradeoff the model performance and convergence by dynamically varying the proportion of augmented samples in the majority and minority classes. We achieve comparable results to the SOTA with fewer training epochs and a classifier with fewer training parameters.

Francis Xiatian Zhang, Shuang Chen, Xianghua Xie et al.

Video inpainting fills in corrupted video content with plausible replacements. While recent advances in endoscopic video inpainting have shown potential for enhancing the quality of endoscopic videos, they mainly repair 2D visual information without effectively preserving crucial 3D spatial details for clinical reference. Depth-aware inpainting methods attempt to preserve these details by incorporating depth information. Still, in endoscopic contexts, they face challenges including reliance on pre-acquired depth maps, less effective fusion designs, and ignorance of the fidelity of 3D spatial details. To address them, we introduce a novel Depth-aware Endoscopic Video Inpainting (DAEVI) framework. It features a Spatial-Temporal Guided Depth Estimation module for direct depth estimation from visual features, a Bi-Modal Paired Channel Fusion module for effective channel-by-channel fusion of visual and depth information, and a Depth Enhanced Discriminator to assess the fidelity of the RGB-D sequence comprised of the inpainted frames and estimated depth images. Experimental evaluations on established benchmarks demonstrate our framework's superiority, achieving a 2% improvement in PSNR and a 6% reduction in MSE compared to state-of-the-art methods. Qualitative analyses further validate its enhanced ability to inpaint fine details, highlighting the benefits of integrating depth information into endoscopic inpainting.

Tanqiu Qiao, Ruochen Li, Frederick W. B. Li et al.

Video-based Human-Object Interaction (HOI) recognition explores the intricate dynamics between humans and objects, which are essential for a comprehensive understanding of human behavior and intentions. While previous work has made significant strides, effectively integrating geometric and visual features to model dynamic relationships between humans and objects in a graph framework remains a challenge. In this work, we propose a novel end-to-end category to scenery framework, CATS, starting by generating geometric features for various categories through graphs respectively, then fusing them with corresponding visual features. Subsequently, we construct a scenery interactive graph with these enhanced geometric-visual features as nodes to learn the relationships among human and object categories. This methodological advance facilitates a deeper, more structured comprehension of interactions, bridging category-specific insights with broad scenery dynamics. Our method demonstrates state-of-the-art performance on two pivotal HOI benchmarks, including the MPHOI-72 dataset for multi-person HOIs and the single-person HOI CAD-120 dataset.

Ziyi Chang, George Alex Koulieris, Hubert P. H. Shum

Acquiring the virtual equivalent of exhibits, such as sculptures, in virtual reality (VR) museums, can be labour-intensive and sometimes infeasible. Deep learning based 3D reconstruction approaches allow us to recover 3D shapes from 2D observations, among which single-view-based approaches can reduce the need for human intervention and specialised equipment in acquiring 3D sculptures for VR museums. However, there exist two challenges when attempting to use the well-researched human reconstruction methods: limited data availability and domain shift. Considering sculptures are usually related to humans, we propose our unsupervised 3D domain adaptation method for adapting a single-view 3D implicit reconstruction model from the source (real-world humans) to the target (sculptures) domain. We have compared the generated shapes with other methods and conducted ablation studies as well as a user study to demonstrate the effectiveness of our adaptation method. We also deploy our results in a VR application.

Haiju Fan, Xiaona Qin, Shuang Chen et al.

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 other compression techniques. Despite this, existing adversarial attack methods on image classification are mostly performed in the pixel domain with few exceptions in the compressed domain, making them less applicable in real-world scenarios. In this paper, we propose a novel one-index attack method in the VQ domain to generate adversarial images by a differential evolution algorithm, successfully resulting in image misclassification in victim models. The one-index attack method modifies a single index in the compressed data stream so that the decompressed image is misclassified. It only needs to modify a single VQ index to realize an attack, which limits the number of perturbed indexes. The proposed method belongs to a semi-black-box attack, which is more in line with the actual attack scenario. We apply our method to attack three popular image classification models, i.e., Resnet, NIN, and VGG16. On average, 55.9% and 77.4% of the images in CIFAR-10 and Fashion MNIST, respectively, are successfully attacked, with a high level of misclassification confidence and a low level of image perturbation.

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 in egocentric virtual environments can significantly affect distance perception and immersion. However, the influence of eye height in pre-captured real environments has received less attention due to the difficulty of altering the perspective after finishing the capture process. 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. If a significant influence is confirmed, an effective image-based approach to adapt pre-captured real-world environments to the user's eye height would be desirable. Motivated by the study, we propose a learning-based approach for synthesizing novel views for omnidirectional images with altered eye heights. This approach employs a multitask architecture that learns depth and semantic segmentation in two formats, and generates high-quality depth and semantic segmentation to facilitate the inpainting stage. With the improved omnidirectional-aware layered depth image, our approach synthesizes natural and realistic visuals for eye height adaptation. Quantitative and qualitative evaluation shows favorable results against state-of-the-art methods, and an extensive user study verifies improved perception and immersion for pre-captured real-world environments.

Manli Zhu, Qianhui Men, Edmond S. L. Ho et al.

Musculoskeletal and neurological disorders are the most common causes of walking problems among older people, and they often lead to diminished quality of life. Analyzing walking motion data manually requires trained professionals and the evaluations may not always be objective. To facilitate early diagnosis, recent deep learning-based methods have shown promising results for automated analysis, which can discover patterns that have not been found in traditional machine learning methods. We observe that existing work mostly applies deep learning on individual joint features such as the time series of joint positions. Due to the challenge of discovering inter-joint features such as the distance between feet (i.e. the stride width) from generally smaller-scale medical datasets, these methods usually perform sub-optimally. 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. Due to the distinctive nature of the two types of features, we introduce a two-stream framework, with one stream learning from the time series of joint position and the other from the time series of relative joint displacement. We further develop a mid-layer fusion module to combine the discovered patterns in these two streams for diagnosis, which results in a complementary representation of the data for better prediction performance. We validate our system with a benchmark dataset of 3D skeleton motion that involves 45 patients with musculoskeletal and neurological disorders, and achieve a prediction accuracy of 95.56%, outperforming state-of-the-art methods.

Xiatian Zhang, Sisi Zheng, Hubert P. H. Shum et al.

Resting-state fMRI (rs-fMRI) functional connectivity (FC) analysis provides valuable insights into the relationships between different brain regions and their potential implications for neurological or psychiatric disorders. However, specific design efforts to predict treatment response from rs-fMRI remain limited due to difficulties in understanding the current brain state and the underlying mechanisms driving the observed patterns, which limited the clinical application of 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. This approach results in a more expressive framework that captures brain dynamic features at different scales and enables more accurate prediction of treatment response. Our experiments on the chronic pain and depersonalization disorder datasets demonstrate that our proposed method outperforms current methods in different scenarios. To the best of our knowledge, we are the first to explore the integration of distance-based and correlation-based neural similarity into graph learning for treatment response prediction.

Ruochen Li, Zhanxing Zhu, Tanqiu Qiao et al.

Pedestrian trajectory prediction is critical for ensuring safety in autonomous driving, surveillance systems, and urban planning applications. While early approaches primarily focus on one-hop pairwise relationships, recent studies attempt to capture high-order interactions by stacking multiple Graph Neural Network (GNN) layers. However, these approaches face a fundamental trade-off: insufficient layers may lead to under-reaching problems that limit the model's receptive field, while excessive depth can result in prohibitive computational costs. We argue that an effective model should be capable of adaptively modeling both explicit one-hop interactions and implicit high-order dependencies, rather than relying solely on architectural depth. To this end, we propose ViTE (Virtual graph Trajectory Expert router), a novel framework for pedestrian trajectory prediction. ViTE consists of two key modules: a Virtual Graph that introduces dynamic virtual nodes to model long-range and high-order interactions without deep GNN stacks, and an Expert Router that adaptively selects interaction experts based on social context using a Mixture-of-Experts design. This combination enables flexible and scalable reasoning across varying interaction patterns. Experiments on three benchmarks (ETH/UCY, NBA, and SDD) demonstrate that our method consistently achieves state-of-the-art performance, validating both its effectiveness and practical efficiency.

Ruochen Li, Ziyi Chang, Junyan Hu et al.

Accurate prediction of real-world pedestrian trajectories is crucial for a wide range of robot-related applications. Recent approaches typically adopt graph-based or transformer-based frameworks to model interactions. Despite their effectiveness, these methods either introduce unnecessary computational overhead or struggle to represent the diverse and time-varying characteristics of human interactions. In this work, we present an Adaptive Relational Transformer (ART), which introduces a Temporal-Aware Relation Graph (TARG) to explicitly capture the evolution of pairwise interactions and an Adaptive Interaction Pruning (AIP) mechanism to reduce redundant computations efficiently. Extensive evaluations on ETH/UCY and NBA benchmarks show that ART delivers state-of-the-art accuracy with high computational efficiency.

Xiaotang Zhang, Ziyi Chang, Qianhui Men et al.

Motion tracking has been an important technique for imitating human-like movement from large-scale datasets in physics-based motion synthesis. However, existing approaches focus on tracking either single character or a particular type of interaction, limiting their ability to handle contact-rich interactions. Extending single-character tracking approaches suffers from the instability due to the challenge of forces transferred through contacts. Contact-rich interactions requires levels of control, which places much greater demands on model capacity. To this end, we propose a robust tracking method based on progressive neural network (PNN) where multiple experts are specialized in learning skills of various difficulties. Our method learns to assign training samples to experts automatically without requiring manually scheduling. Both qualitative and quantitative results show that our method delivers more stable motion tracking in densely interactive movements while enabling more efficient model training.

Kanglei Zhou, Liyuan Wang, Xingxing Zhang et al.

Action Quality Assessment (AQA) evaluates diverse skills but models struggle with non-stationary data. We propose Continual AQA (CAQA) to refine models using sparse new data. Feature replay preserves memory without storing raw inputs. However, the misalignment between static old features and the dynamically changing feature manifold causes severe catastrophic forgetting. To address this novel problem, we propose Manifold-Aligned Graph Regularization (MAGR), which first aligns deviated old features to the current feature manifold, ensuring representation consistency. It then constructs a graph jointly arranging old and new features aligned with quality scores. Experiments show MAGR outperforms recent strong baselines with up to 6.56%, 5.66%, 15.64%, and 9.05% correlation gains on the MTL-AQA, FineDiving, UNLV-Dive, and JDM-MSA split datasets, respectively. This validates MAGR for continual assessment challenges arising from non-stationary skill variations. Code is available at https://github.com/ZhouKanglei/MAGR_CAQA}{https://github.com/ZhouKanglei/MAGR_CAQA.

Jamie S. J. Stirling, Noura Al-Moubayed, Hubert P. H. Shum

Vector quantization approaches (VQ-VAE, VQ-GAN) learn discrete neural representations of images, but these representations are inherently position-dependent: codes are spatially arranged and contextually entangled, requiring autoregressive or diffusion-based priors to model their dependencies at sample time. In this work, we ask whether positional information is necessary for discrete representations of spatially aligned data. We propose the permutation-invariant vector-quantized autoencoder (PI-VQ), in which latent codes are constrained to carry no positional information. We find that this constraint encourages codes to capture global, semantic features, and enables direct interpolation between images without a learned prior. To address the reduced information capacity of permutation-invariant representations, we introduce matching quantization, a vector quantization algorithm based on optimal bipartite matching that increases effective bottleneck capacity by $3.5\times$ relative to naive nearest-neighbour quantization. The compositional structure of the learned codes further enables interpolation-based sampling, allowing synthesis of novel images in a single forward pass. We evaluate PI-VQ on CelebA, CelebA-HQ and FFHQ, obtaining competitive precision, density and coverage metrics for images synthesised with our approach. We discuss the trade-offs inherent to position-free representations, including separability and interpretability of the latent codes, pointing to numerous directions for future work.

Wenke E, Yixin Sun, Jiaxu Liu et al.

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 LiDAR image representation fused from range, intensity and ambient channels, together with a voxel-aligned view transformer that preserves spatial fidelity while enabling efficient BEV processing. During training, a high-capacity LiDAR and camera fusion Teacher network extracts both rich spatial and semantic features for cross-modality knowledge distillation into a lightweight Student network that relies solely on a single 360-degree panoramic camera image. Extensive experiments on the Dur360BEV dataset demonstrate that our teacher model significantly outperforms existing camera-based BEV segmentation methods, achieving a 25.6\% IoU improvement. Meanwhile, the distilled Student network attains competitive performance with an 8.5\% IoU gain and state-of-the-art inference speed of 31.2 FPS. Moreover, evaluations on KITTI-360 (two fisheye cameras) confirm that our distillation framework generalises to diverse camera setups, underscoring its feasibility and robustness. This approach reduces sensor complexity and deployment costs while providing a practical solution for efficient, low-cost BEV segmentation in real-world autonomous driving.

Shuang Chen, Haozheng Zhang, Amir Atapour-Abarghouei et al.

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 particularly challenging because it requires the reconstructed regions to exhibit similar patterns to the semanticly consistent regions}. This requires a model with a strong capacity to capture long-range dependencies. Existing models struggle in this regard due to the slow growth of receptive field for Convolutional Neural Networks (CNNs) based methods and patch-level interactions in Transformer-based methods, which are ineffective for capturing long-range dependencies. Motivated by this, we propose SEM-Net, a novel visual State Space model (SSM) vision network, modelling corrupted images at the pixel level while capturing long-range dependencies (LRDs) in state space, achieving a linear computational complexity. To address the inherent lack of spatial awareness in SSM, we introduce the Snake Mamba Block (SMB) and Spatially-Enhanced Feedforward Network. These innovations enable SEM-Net to outperform state-of-the-art inpainting methods on two distinct datasets, showing significant improvements in capturing LRDs and enhancement in spatial consistency. Additionally, SEM-Net achieves state-of-the-art performance on motion deblurring, demonstrating its generalizability. Our source code will be released in https://github.com/ChrisChen1023/SEM-Net.

Mridula Vijendran, Frederick W. B. Li, Jingjing Deng et al.

Painting classification plays a vital role in organizing, finding, and suggesting artwork for digital and classic art galleries. Existing methods struggle with adapting knowledge from the real world to artistic images during training, leading to poor performance when dealing with different datasets. Our innovation lies in addressing these challenges through a two-step process. First, we generate more data using Style Transfer with Adaptive Instance Normalization (AdaIN), bridging the gap between diverse styles. Then, our classifier gains a boost with feature-map adaptive spatial attention modules, improving its understanding of artistic details. Moreover, we tackle the problem of imbalanced class representation by dynamically adjusting augmented samples. Through a dual-stage process involving careful hyperparameter search and model fine-tuning, we achieve an impressive 87.24\% accuracy using the ResNet-50 backbone over 40 training epochs. Our study explores quantitative analyses that compare different pretrained backbones, investigates model optimization through ablation studies, and examines how varying augmentation levels affect model performance. Complementing this, our qualitative experiments offer valuable insights into the model's decision-making process using spatial attention and its ability to differentiate between easy and challenging samples based on confidence ranking.

Ruisheng Han, Kanglei Zhou, Amir Atapour-Abarghouei et al.

Action quality assessment (AQA) is critical for evaluating athletic performance, informing training strategies, and ensuring safety in competitive sports. However, existing deep learning approaches often operate as black boxes and are vulnerable to spurious correlations, limiting both their reliability and interpretability. In this paper, we introduce FineCausal, a novel causal-based framework that achieves state-of-the-art performance on the FineDiving-HM dataset. Our approach leverages a Graph Attention Network-based causal intervention module to disentangle human-centric foreground cues from background confounders, and incorporates a temporal causal attention module to capture fine-grained temporal dependencies across action stages. This dual-module strategy enables FineCausal to generate detailed spatio-temporal representations that not only achieve state-of-the-art scoring performance but also provide transparent, interpretable feedback on which features drive the assessment. Despite its strong performance, FineCausal requires extensive expert knowledge to define causal structures and depends on high-quality annotations, challenges that we discuss and address as future research directions. Code is available at https://github.com/Harrison21/FineCausal.

Ziyu Wang, Hongrui Kou, Cheng Wang et al.

The Operational Design Domain (ODD) of urbanoriented Level 4 (L4) autonomous driving, especially for autonomous robotaxis, confronts formidable challenges in complex urban mixed traffic environments. These challenges stem mainly from the high density of Vulnerable Road Users (VRUs) and their highly uncertain and unpredictable interaction behaviors. However, existing open-source datasets predominantly focus on structured scenarios such as highways or regulated intersections, leaving a critical gap in data representing chaotic, unstructured urban environments. To address this, this paper proposes an efficient, high-precision method for constructing drone-based datasets and establishes the Vehicle-Vulnerable Road User Interaction Dataset (VRUD), as illustrated in Figure 1. Distinct from prior works, VRUD is collected from typical "Urban Villages" in Shenzhen, characterized by loose traffic supervision and extreme occlusion. The dataset comprises 4 hours of 4K/30Hz recording, containing 11,479 VRU trajectories and 1,939 vehicle trajectories. A key characteristic of VRUD is its composition: VRUs account for about 87% of all traffic participants, significantly exceeding the proportions in existing benchmarks. Furthermore, unlike datasets that only provide raw trajectories, we extracted 4,002 multi-agent interaction scenarios based on a novel Vector Time to Collision (VTTC) threshold, supported by standard OpenDRIVE HD maps. This study provides valuable, rare edge-case resources for enhancing the safety performance of ADS in complex, unstructured urban environments. To facilitate further research, we have made the VRUD dataset open-source at: https://zzi4.github.io/VRUD/.

Kanglei Zhou, Qingyi Pan, Xingxing Zhang et al.

Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation. A major challenge lies in the non-stationary nature of quality distributions in real-world scenarios, which limits the generalization ability of conventional methods. We introduce Continual AQA (CAQA), which equips AQA with Continual Learning (CL) capabilities to handle evolving distributions while mitigating catastrophic forgetting. Although parameter-efficient fine-tuning of pretrained models has shown promise in CL for image classification, we find it insufficient for CAQA. Our empirical and theoretical analyses reveal two insights: (i) Full-Parameter Fine-Tuning (FPFT) is necessary for effective representation learning; yet (ii) uncontrolled FPFT induces overfitting and feature manifold shift, thereby aggravating forgetting. To address this, we propose Adaptive Manifold-Aligned Graph Regularization (MAGR++), which couples backbone fine-tuning that stabilizes shallow layers while adapting deeper ones with a two-step feature rectification pipeline: a manifold projector to translate deviated historical features into the current representation space, and a graph regularizer to align local and global distributions. We construct four CAQA benchmarks from three datasets with tailored evaluation protocols and strong baselines, enabling systematic cross-dataset comparison. Extensive experiments show that MAGR++ achieves state-of-the-art performance, with average correlation gains of 3.6% offline and 12.2% online over the strongest baseline, confirming its robustness and effectiveness. Our code is available at https://github.com/ZhouKanglei/MAGRPP.

Jiaxu Liu, Li Li, Hubert P. H. Shum et al.

Diffusion models currently demonstrate impressive performance over various generative tasks. Recent work on image diffusion highlights the strong capabilities of Mamba (state space models) due to its efficient handling of long-range dependencies and sequential data modeling. Unfortunately, joint consideration of state space models with 3D point cloud generation remains limited. To harness the powerful capabilities of the Mamba model for 3D point cloud generation, we propose a novel diffusion framework containing dual latent Mamba block (DM-Block) and a time-variant frequency encoder (TF-Encoder). The DM-Block apply a space-filling curve to reorder points into sequences suitable for Mamba state-space modeling, while operating in a latent space to mitigate the computational overhead that arises from direct 3D data processing. Meanwhile, the TF-Encoder takes advantage of the ability of the diffusion model to refine fine details in later recovery stages by prioritizing key points within the U-Net architecture. This frequency-based mechanism ensures enhanced detail quality in the final stages of generation. Experimental results on the ShapeNet-v2 dataset demonstrate that our method achieves state-of-the-art performance (ShapeNet-v2: 0.14\% on 1-NNA-Abs50 EMD and 57.90\% on COV EMD) on certain metrics for specific categories while reducing computational parameters and inference time by up to 10$\times$ and 9$\times$, respectively. Source code is available in Supplementary Materials and will be released upon accpetance.

Abril Corona-Figueroa, Jonathan Frawley, Sam Bond-Taylor et al.

Computed tomography (CT) is an effective medical imaging modality, widely used in the field of clinical medicine for the diagnosis of various pathologies. Advances in Multidetector CT imaging technology have enabled additional functionalities, including generation of thin slice multiplanar cross-sectional body imaging and 3D reconstructions. However, this involves patients being exposed to a considerable dose of ionising radiation. Excessive ionising radiation can lead to deterministic and harmful effects on the body. This paper proposes a Deep Learning model that learns to reconstruct CT projections from a few or even a single-view X-ray. This is based on a novel architecture that builds from neural radiance fields, which learns a continuous representation of CT scans by disentangling the shape and volumetric depth of surface and internal anatomical structures from 2D images. Our model is trained on chest and knee datasets, and we demonstrate qualitative and quantitative high-fidelity renderings and compare our approach to other recent radiance field-based methods. Our code and link to our datasets are available at https://github.com/abrilcf/mednerf

Dimitrios Sakkos, Hubert P. H. Shum, Edmond S. L. Ho

A core challenge in background subtraction (BGS) is handling videos with sudden illumination changes in consecutive frames. In this paper, we tackle the problem from a data point-of-view using data augmentation. Our method performs data augmentation that not only creates endless data on the fly, but also features semantic transformations of illumination which enhance the generalisation of the model. It successfully simulates flashes and shadows by applying the Euclidean distance transform over a binary mask that is randomly generated. Such data allows us to effectively train an illumination-invariant deep learning model for BGS. Experimental results demonstrate the contribution of the synthetics in the ability of the models to perform BGS even when significant illumination changes take place. The source code of the project is made publicly available at https://github.com/dksakkos/illumination_augmentation.

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 the available information is inherently sparse, especially for the scenario of large missing regions. Recent advances in self-attention mechanisms within transformers have led to significant improvements in many computer vision tasks including inpainting. However, limited by the computational costs, existing methods cannot fully exploit the efficacy of long-range modelling capabilities of such models. 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. Moreover, we propose a Spatially-activated Channel Attention Layer (SCAL), an efficient self-attention mechanism interpreting spatial awareness to model the corrupted image at multiple scales. To further enhance the effectiveness of SCAL, motivated by recent advanced in speech recognition, we introduce a sandwich structure that places feed-forward networks before and after the SCAL module. We demonstrate the superior performance of HINT compared to contemporary state-of-the-art models on four datasets, CelebA, CelebA-HQ, Places2, and Dunhuang.

Kanglei Zhou, Ruizhi Cai, Liyuan Wang et al.

Action Quality Assessment (AQA) quantitatively evaluates the quality of human actions, providing automated assessments that reduce biases in human judgment. Its applications span domains such as sports analysis, skill assessment, and medical care. Recent advances in AQA have introduced innovative methodologies, but similar methods often intertwine across different domains, highlighting the fragmented nature that hinders systematic reviews. In addition, the lack of a unified benchmark and limited computational comparisons hinder consistent evaluation and fair assessment of AQA approaches. In this work, we address these gaps by systematically analyzing over 150 AQA-related papers to develop a hierarchical taxonomy, construct a unified benchmark, and provide an in-depth analysis of current trends, challenges, and future directions. Our hierarchical taxonomy categorizes AQA methods based on input modalities (video, skeleton, multi-modal) and their specific characteristics, highlighting the evolution and interrelations across various approaches. To promote standardization, we present a unified benchmark, integrating diverse datasets to evaluate the assessment precision and computational efficiency. Finally, we review emerging task-specific applications and identify under-explored challenges in AQA, providing actionable insights into future research directions. This survey aims to deepen understanding of AQA progress, facilitate method comparison, and guide future innovations. The project web page can be found at https://ZhouKanglei.github.io/AQA-Survey.

Ruochen Li, Stamos Katsigiannis, Tae-Kyun Kim et al.

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 classified into pedestrian or heterogeneous trajectory prediction. The former exploits the relatively consistent behavior of pedestrians, but is limited in real-world scenarios with heterogeneous traffic agents such as cyclists and vehicles. The latter typically relies on extra class label information to distinguish the heterogeneous agents, but such labels are costly to annotate and cannot be generalized to represent different behaviors within the same class of agents. In this work, we introduce the behavioral pseudo-labels that effectively capture the behavior distributions of pedestrians and heterogeneous agents solely based on their motion features, significantly improving the accuracy of trajectory prediction. To implement the framework, we propose the Behavioral Pseudo-Label Informed Sparse Graph Convolution Network (BP-SGCN) that learns pseudo-labels and informs to a trajectory predictor. For optimization, we propose a cascaded training scheme, in which we first learn the pseudo-labels in an unsupervised manner, and then perform end-to-end fine-tuning on the labels in the direction of increasing the trajectory prediction accuracy. Experiments show that our pseudo-labels effectively model different behavior clusters and improve trajectory prediction. Our proposed BP-SGCN outperforms existing methods using both pedestrian (ETH/UCY, pedestrian-only SDD) and heterogeneous agent datasets (SDD, Argoverse 1).

Ruochen Li, Tanqiu Qiao, Stamos Katsigiannis et al.

Pedestrian trajectory prediction aims to forecast future movements based on historical paths. Spatial-temporal (ST) methods often separately model spatial interactions among pedestrians and temporal dependencies of individuals. They overlook the direct impacts of interactions among different pedestrians across various time steps (i.e., high-order cross-time interactions). This limits their ability to capture ST inter-dependencies and hinders prediction performance. To address these limitations, we propose UniEdge with three major designs. Firstly, we introduce a unified ST graph data structure that simplifies high-order cross-time interactions into first-order relationships, enabling the learning of ST inter-dependencies in a single step. This avoids the information loss caused by multi-step aggregation. Secondly, traditional GNNs focus on aggregating pedestrian node features, neglecting the propagation of implicit interaction patterns encoded in edge features. We propose the Edge-to-Edge-Node-to-Node Graph Convolution (E2E-N2N-GCN), a novel dual-graph network that jointly models explicit N2N social interactions among pedestrians and implicit E2E influence propagation across these interaction patterns. Finally, to overcome the limited receptive fields and challenges in capturing long-range dependencies of auto-regressive architectures, we introduce a transformer encoder-based predictor that enables global modeling of temporal correlation. UniEdge outperforms state-of-the-arts on multiple datasets, including ETH, UCY, and SDD.

Merryn D. Constable, Hubert P. H. Shum, Stephen Clark

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. This narrative review synthesises work on technical and non-technical surgical skills, collaborative task performance, and pose estimation to illustrate new opportunities to advance cardiothoracic surgical performance with innovations from computer vision and artificial intelligence. These technological innovations are critically evaluated in terms of the benefits they could offer the cardiothoracic surgical community, and any barriers to the uptake of the technology are elaborated upon. Like some other specialities, cardiothoracic surgery has relatively few opportunities to benefit from tools with data capture technology embedded within them (as with robotic-assisted laparoscopic surgery, for example). In such cases, pose estimation techniques that allow for movement tracking across a conventional operating field without using specialist equipment or markers offer considerable potential. With video data from either simulated or real surgical procedures, these tools can (1) provide insight into the development of expertise and surgical performance over a surgeon's career, (2) provide feedback to trainee surgeons regarding areas for improvement, (3) provide the opportunity to investigate what aspects of skill may be linked to patient outcomes which can (4) inform the aspects of surgical skill which should be focused on within training or mentoring programmes. Classifier or assessment algorithms that use artificial intelligence to 'learn' what expertise is from expert surgical evaluators could further assist educators in determining if trainees meet competency thresholds.

Baiyi Li, Edmond S. L. Ho, Hubert P. H. Shum et al.

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. However, acquiring such skeletal motion is challenging. While direct motion capture is expensive and slow, motion editing/generation is also non-trivial, as complex contact patterns with topological and geometric constraints have to be retained. To this end, we propose a new deep learning method for two-body skeletal interaction motion augmentation, which can generate variations of contact-rich interactions with varying body sizes and proportions while retaining the key geometric/topological relations between two bodies. Our system can learn effectively from a relatively small amount of data and generalize to drastically different skeleton sizes. Through exhaustive evaluation and comparison, we show it can generate high-quality motions, has strong generalizability and outperforms traditional optimization-based methods and alternative deep learning solutions.

Mridula Vijendran, Jingjing Deng, Shuang Chen et al.

Artificial Intelligence significantly enhances the visual art industry by analyzing, identifying and generating digitized artistic images. This review highlights the substantial benefits of integrating geometric data into AI models, addressing challenges such as high inter-class variations, domain gaps, and the separation of style from content by incorporating geometric information. Models not only improve AI-generated graphics synthesis quality, but also effectively distinguish between style and content, utilizing inherent model biases and shared data traits. We explore methods like geometric data extraction from artistic images, the impact on human perception, and its use in discriminative tasks. The review also discusses the potential for improving data quality through innovative annotation techniques and the use of geometric data to enhance model adaptability and output refinement. Overall, incorporating geometric guidance boosts model performance in classification and synthesis tasks, providing crucial insights for future AI applications in the visual arts domain.

Ziyi Chang, He Wang, George Alex Koulieris et al.

Generating large-scale multi-character interactions is a challenging and important task in character animation. Multi-character interactions involve not only natural interactive motions but also characters coordinated with each other for transition. For example, a dance scenario involves characters dancing with partners and also characters coordinated to new partners based on spatial and temporal observations. We term such transitions as coordinated interactions and decompose them into interaction synthesis and transition planning. Previous methods of single-character animation do not consider interactions that are critical for multiple characters. Deep-learning-based interaction synthesis usually focuses on two characters and does not consider transition planning. Optimization-based interaction synthesis relies on manually designing objective functions that may not generalize well. While crowd simulation involves more characters, their interactions are sparse and passive. We identify two challenges to multi-character interaction synthesis, including the lack of data and the planning of transitions among close and dense interactions. Existing datasets either do not have multiple characters or do not have close and dense interactions. The planning of transitions for multi-character close and dense interactions needs both spatial and temporal considerations. We propose a conditional generative pipeline comprising a coordinatable multi-character interaction space for interaction synthesis and a transition planning network for coordinations. Our experiments demonstrate the effectiveness of our proposed pipeline for multicharacter interaction synthesis and the applications facilitated by our method show the scalability and transferability.