22 accepted papers
Real-world visual data rarely presents as isolated, static instances. Instead, it often evolves gradually over time through variations in pose, lighting, object state, or scene context. However, conventional classifiers are typically trained under the assumption of temporal independence, limiting th
Video anomaly detection (VAD) is critical for surveillance systems, but current methods prioritize accuracy while ignoring the ethical risks of encoding sensitive biometric information. This neglect poses significant privacy concerns for real-world deployment. To bridge this gap, we introduce the Gu…
Learning from structured multi-way data, represented as higher-order tensors, requires capturing complex interactions across tensor modes while remaining computationally efficient. We introduce Uncertainty-driven Kernel Tensor Learning (UKTL), a novel kernel framework for $M$-mode tensors that compa…
Laminectomy represents an effective surgical procedure for the treatment of lumbar spinal stenosis. Due to the intricate anatomical structure of the lumbar spine, meticulous surgical path planning is essential to ensure the safety of the procedure and enhance the likelihood of successful outcomes. T
We propose Graph Consistency Regularization (GCR), a novel framework that injects relational graph structures, derived from model predictions, into the learning process to promote class-aware, semantically meaningful feature representations. Functioning as a form of *self-prompting*, GCR enables the…
Continual ultra-fine-grained visual recognition (C-UFG) aims to continuously learn to categorize the increasing number of cultivates (VC-UFG) and consistently recognize crops across reproductive stages (HC-UFG), which is a fundamental goal of intelligent agriculture. Despite the progress made in gen
Over the past few years, vision transformers (ViTs) have consistently demonstrated remarkable performance across various visual recognition tasks. However, attempts to enhance their robustness have yielded limited success, mainly focusing on different training strategies, input patch augmentation, o…
Ground-to-aerial person search leverages cooperative efforts between unmanned aerial vehicles (UAV) and ground surveillance cameras to locate person individuals. Despite the progress made by recent works, the impact of the discrepancy between the two views is underestimated. This limits the overall
Preference-based optimizing methods have shown their advantages and potential in exploring individual, comfortable, and effective control strategies and assistance parameters of exoskeletons during locomotion. Research indicates that compared with naive wearers, knowledgeable wearers with abundant e…
Mechanisms that balance wide range of motion(ROM) with increased stiffness are gradually gaining attention in robotic applications. This letter proposed kinematic methods for the spatial interlocking 3-UU mechanism based on Lie Group, which consists of a fixed base and a moving platform connected by
We introduce Referring Human Pose and Mask Estimation (R-HPM) in the wild, where either a text or positional prompt specifies the person of interest in an image. This new task holds significant potential for human-centric applications such as assistive robotics and sports analysis. In contrast to pr…
Ultra-fine-grained visual classification (ultra-FGVC) targets at classifying sub-grained categories of fine-grained objects. This inevitably requires discriminative representation learning within a limited training set. Exploring intrinsic features from the object itself, e.g., predicting the rotati…
Fine-grained leaf image retrieval (FGLIR) aims to search similar leaf images in subspecies level which involves very high interclass visual similarity and accordingly poses great challenges to leaf image description. In this study, we introduce a new concept, named fan-beam binarization difference p…
Current referring video object segmentation (R-VOS) techniques extract conditional kernels from encoded (low-resolution) vision-language features to segment the decoded high-resolution features. We discovered that this causes significant feature drift, which the segmentation kernels struggle to perc…
Two-dimensional singular value decomposition (2DSVD) is an important dimensionality reduction algorithm which has inherent advantage in preserving the structure of 2D images. However, 2DSVD algorithm is based on the squared error loss, which may exaggerate the projection errors with the presence of…
Daily manipulation tasks are characterized by geometric primitives related to actions and object shapes. Such geometric descriptors are poorly represented by only using Cartesian coordinate systems. In this paper, we propose a learning approach to extract the optimal representation from a dictionary…
Ensuring the motion consistency of human and exoskeletons is the key to the research of wearable exoskeleton robots. However, as the complexity of the coupling of sliding and rolling motion in human joint tissue, it is hard to depict the dynamic states of the joint axis. Exploring the changed human
Though convolutional neural networks (CNNs) with residual and dense aggregations have obtained much attention in image denoising, they are incapable of exploiting different levels of contextual information at every convolutional unit in order to infer different levels of noise components with a sing…
Deep learning methods have achieved remarkable success in fine-grained visual categorization. Such successful categorization at sub-ordinate level, e.g., different animal or plant species, however relies heavily on the visual differences that human can observe and the ground-truths are labelled on t…
Radon transform is a popular mathematical tool for shape analysis. However, it cannot handle affine deformation. Although its extended version, trace transform, allow us to construct affine invariants, they are less informative and computational expensive due to the loss of spatial relationship betw…
Effectively describing and recognizing leaf shapes under arbitrary deformations, particularly from a large database, remains an unsolved problem. In this research, we attempted a new strategy of describing shape by walking along a bunch of chords that pass through the shape to measure the regions tr…
Pathological tremor is defined as a roughly sinusoidal movement and usually occurs in the upper limb impacting individuals activities of daily livings. Functional electrical stimulation (FES) is proposed as a potential alternative for cancelling the pathological tremor. However, the feasibility and