Related papers: FocusTune: Tuning Visual Localization through Focu…

The splendid success of convolutional neural networks (CNNs) in computer vision is largely attributable to the availability of massive annotated datasets, such as ImageNet and Places. However, in medical imaging, it is challenging to create…

Current works focus on addressing the remote sensing change detection task using bi-temporal images. Although good performance can be achieved, however, seldom of they consider the motion cues which may also be vital. In this work, we…

Camera pose estimation is an important problem in computer vision. Common techniques either match the current image against keyframes with known poses, directly regress the pose, or establish correspondences between keypoints in the image…

The widespread use of large language models has resulted in a multitude of tokenizers and embedding spaces, making knowledge transfer in prompt discovery tasks difficult. In this work, we propose FUSE (Flexible Unification of Semantic…

Object counting and localization are key steps for quantitative analysis in large-scale microscopy applications. This procedure becomes challenging when target objects are overlapping, are densely clustered, and/or present fuzzy boundaries.…

Segmentation is a fundamental problem in surgical scene analysis using artificial intelligence. However, the inherent data scarcity in this domain makes it challenging to adapt traditional segmentation techniques for this task. To tackle…

Line features are valid complements for point features in man-made environments. 3D-2D constraints provided by line features have been widely used in Visual Odometry (VO) and Structure-from-Motion (SfM) systems. However, how to accurately…

This study proposes a 3D semantic segmentation method for the spine based on the improved SwinUNETR to improve segmentation accuracy and robustness. Aiming at the complex anatomical structure of spinal images, this paper introduces a…

Deep convolutional neural networks (DCNNs) based remote sensing (RS) image semantic segmentation technology has achieved great success used in many real-world applications such as geographic element analysis. However, strong dependency on…

Neural machine translation often adopts the fine-tuning approach to adapt to specific domains. However, nonrestricted fine-tuning can easily degrade on the general domain and over-fit to the target domain. To mitigate the issue, we propose…

Cross-View Geo-Localisation is still a challenging task where additional modules, specific pre-processing or zooming strategies are necessary to determine accurate positions of images. Since different views have different geometries,…

Robot navigation systems are critical for various real-world applications such as delivery services, hospital logistics, and warehouse management. Although classical navigation methods provide interpretability, they rely heavily on expert…

3D point cloud segmentation has made tremendous progress in recent years. Most current methods focus on aggregating local features, but fail to directly model long-range dependencies. In this paper, we propose Stratified Transformer that is…

Hierarchical visual localization methods achieve state-of-the-art accuracy but require substantial memory as they need to store all database images. Direct 2D-3D matching requires significantly less memory but suffers from lower accuracy…

For several emerging technologies such as augmented reality, autonomous driving and robotics, visual localization is a critical component. Directly regressing camera pose/3D scene coordinates from the input image using deep neural networks…

Technology mapping involves mapping logical circuits to a library of cells. Traditionally, the full technology library is used, leading to a large search space and potential overhead. Motivated by randomly sampled technology mapping case…

Keypoint detection and description is fundamental yet important in many vision applications. Most existing methods use detect-then-describe or detect-and-describe strategy to learn local features without considering their context…

The complexity of scene parsing grows with the number of object and scene classes, which is higher in unrestricted open scenes. The biggest challenge is to model the spatial relation between scene elements while succeeding in identifying…

Class-agnostic 3D instance segmentation tackles the challenging task of segmenting all object instances, including previously unseen ones, without semantic class reliance. Current methods struggle with generalization due to the scarce…

This work proposes a new end-to-end DCNN based approach for motion segmentation, especially for video sequences captured with such non-static cameras, called MOSNET. While other approaches focus on spatial or temporal context only, the…