Related papers: GlobalMind: Global Multi-head Interactive Self-att…

3D point cloud segmentation has a wide range of applications in areas such as autonomous driving, augmented reality, virtual reality and digital twins. The point cloud data collected in real scenes often contain small objects and categories…

Attention-based models, exemplified by the Transformer, can effectively model long range dependency, but suffer from the quadratic complexity of self-attention operation, making them difficult to be adopted for high-resolution image…

In latest years, deep learning has gained a leading role in the pansharpening of multiresolution images. Given the lack of ground truth data, most deep learning-based methods carry out supervised training in a reduced-resolution domain.…

High-density object counting in surveillance scenes is challenging mainly due to the drastic variation of object scales. The prevalence of deep learning has largely boosted the object counting accuracy on several benchmark datasets.…

Deploying depth estimation networks in the real world requires high-level robustness against various adverse conditions to ensure safe and reliable autonomy. For this purpose, many autonomous vehicles employ multi-modal sensor systems,…

Human skin segmentation is a crucial task in computer vision and biometric systems, yet it poses several challenges such as variability in skin color, pose, and illumination. This paper presents a robust data-driven skin segmentation method…

Grouping has been commonly used in deep metric learning for computing diverse features. However, current methods are prone to overfitting and lack interpretability. In this work, we propose an improved and interpretable grouping method to…

Recently, large foundation models trained on vast datasets have demonstrated exceptional capabilities in feature extraction and general feature representation. The ongoing advancements in deep learning-driven large models have shown great…

Accurate temporal segmentation of human actions is critical for intelligent robots in collaborative settings, where a precise understanding of sub-activity labels and their temporal structure is essential. However, the inherent noise in…

Most existing salient object detection methods mostly use U-Net or feature pyramid structure, which simply aggregates feature maps of different scales, ignoring the uniqueness and interdependence of them and their respective contributions…

Semantic segmentation relying solely on RGB data often struggles in challenging conditions such as low illumination and obscured views, limiting its reliability in critical applications like autonomous driving. To address this, integrating…

An effective perception system is a fundamental component for farming robots, as it enables them to properly perceive the surrounding environment and to carry out targeted operations. The most recent methods make use of state-of-the-art…

Diffusion has shown great success in improving accuracy of unsupervised image retrieval systems by utilizing high-order structures of image manifold. However, existing diffusion methods suffer from three major limitations: 1) they usually…

This paper proposes GluMind, a transformer-based multimodal framework designed for continual and long-term blood glucose forecasting. GluMind devises two attention mechanisms, including cross-attention and multi-scale attention, which…

Deep learning has achieved remarkable success in medical image analysis, however its adoption in clinical practice is limited by a lack of interpretability. These models often make correct predictions without explaining their reasoning.…

In human-computer interaction, head pose estimation profoundly influences application functionality. Although utilizing facial landmarks is valuable for this purpose, existing landmark-based methods prioritize precision over simplicity and…

We propose a Self-supervised Anomaly Detection technique, called SeMAnD, to detect geometric anomalies in Multimodal geospatial datasets. Geospatial data comprises of acquired and derived heterogeneous data modalities that we transform to…

Accurate segmentation of multiple organs and the differentiation of pathological tissues in medical imaging are crucial but challenging, especially for nuanced classifications and ambiguous organ boundaries. To tackle these challenges, we…

Despite significant progress in 3D object detection, point clouds remain challenging due to sparse data, incomplete structures, and limited semantic information. Capturing contextual relationships between distant objects presents additional…

Recent advances in pixel-level tasks (e.g. segmentation) illustrate the benefit of of long-range interactions between aggregated region-based representations that can enhance local features. However, such aggregated representations, often…