Related papers: Wavelet-Decoupling Contrastive Enhancement Network…
Long-term vertebral fractures severely affect the life quality of patients, causing kyphotic, lumbar deformity and even paralysis. Computed tomography (CT) is a common clinical examination to screen for this disease at early stages.…
Real-life applications of action recognition often require a fine-grained understanding of subtle movements, e.g., in sports analytics, user interactions in AR/VR, and surgical videos. Although fine-grained actions are more costly to…
Spatial-temporal graphs have been widely used by skeleton-based action recognition algorithms to model human action dynamics. To capture robust movement patterns from these graphs, long-range and multi-scale context aggregation and…
Advanced deep Convolutional Neural Networks (CNNs) have shown great success in video-based person Re-Identification (Re-ID). However, they usually focus on the most obvious regions of persons with a limited global representation ability.…
Facial action unit (AU) detection remains a challenging task, due to the subtlety, dynamics, and diversity of AUs. Recently, the prevailing techniques of self-attention and causal inference have been introduced to AU detection. However,…
Human action recognition is one of the challenging tasks in computer vision. The current action recognition methods use computationally expensive models for learning spatio-temporal dependencies of the action. Models utilizing RGB channels…
Action recognition technology plays a vital role in enhancing security through surveillance systems, enabling better patient monitoring in healthcare, providing in-depth performance analysis in sports, and facilitating seamless human-AI…
Deepfakes have emerged as a significant threat to digital media authenticity, increasing the need for advanced detection techniques that can identify subtle and time-dependent manipulations. CNNs are effective at capturing spatial artifacts…
Fine-grained visual recognition typically depends on modeling subtle difference from object parts. However, these parts often exhibit dramatic visual variations such as occlusions, viewpoints, and spatial transformations, making it hard to…
Concealed object detection (COD) in cluttered scenes is significant for various image processing applications. However, due to that concealed objects are always similar to their background, it is extremely hard to distinguish them. Here,…
Video temporal action detection aims to temporally localize and recognize the action in untrimmed videos. Existing one-stage approaches mostly focus on unifying two subtasks, i.e., localization of action proposals and classification of each…
Clothing segmentation and fine-grained attribute recognition are challenging tasks at the crossing of computer vision and fashion, which segment the entire ensemble clothing instances as well as recognize detailed attributes of the clothing…
Automatic recognition of affective state from wearable physiology has clear societal impact for public health, preventive care, and stress-aware interventions, but real deployments require robustness to non-stationary dynamics, artefacts,…
Few-shot Open-set Object Detection (FOOD) poses a challenge in many open-world scenarios. It aims to train an open-set detector to detect known objects while rejecting unknowns with scarce training samples. Existing FOOD methods are subject…
As an important research topic in computer vision, fine-grained classification which aims to recognition subordinate-level categories has attracted significant attention. We propose a novel region based ensemble learning network for…
Weakly supervised methods, such as class activation maps (CAM) based, have been applied to achieve bleeding segmentation with low annotation efforts in Wireless Capsule Endoscopy (WCE) images. However, the CAM labels tend to be extremely…
With the powerful learning ability of deep convolutional networks, deep clustering methods can extract the most discriminative information from individual data and produce more satisfactory clustering results. However, existing deep…
We consider the problem of fine-grained classification on an edge camera device that has limited power. The edge device must sparingly interact with the cloud to minimize communication bits to conserve power, and the cloud upon receiving…
Skeleton-based action recognition receives increasing attention because the skeleton representations reduce the amount of training data by eliminating visual information irrelevant to actions. To further improve the sample efficiency,…
The HGR is a quite challenging task as its performance is influenced by various aspects such as illumination variations, cluttered backgrounds, spontaneous capture, etc. The conventional CNN networks for HGR are following two stage pipeline…