Related papers: DIS-Mine: Instance Segmentation for Disaster-Aware…

Line segments are ubiquitous in our human-made world and are increasingly used in vision tasks. They are complementary to feature points thanks to their spatial extent and the structural information they provide. Traditional line detectors…

Pixel-level annotation demands expensive human efforts and limits the performance of deep networks that usually benefits from more such training data. In this work we aim to achieve high quality instance and semantic segmentation results…

Scene understanding of high resolution aerial images is of great importance for the task of automated monitoring in various remote sensing applications. Due to the large within-class and small between-class variance in pixel values of…

Systematic failures of computer vision models on subsets with coherent visual patterns, known as error slices, pose a critical challenge for robust model evaluation. Existing slice discovery methods are primarily developed for image…

At the heart of all automated driving systems is the ability to sense the surroundings, e.g., through semantic segmentation of LiDAR sequences, which experienced a remarkable progress due to the release of large datasets such as…

Automated surface-anomaly detection using machine learning has become an interesting and promising area of research, with a very high and direct impact on the application domain of visual inspection. Deep-learning methods have become the…

Object detection is a fundamental problem in computer vision, aiming at locating and classifying objects in image. Although current devices can easily take very high-resolution images, current approaches of object detection seldom consider…

Instance segmentation of remote sensing images (RSIs) is an essential task for a wide range of applications such as land planning and intelligent transport. Instance segmentation of RSIs is constantly plagued by the unbalanced ratio of…

Low-resolution image segmentation is crucial in real-world applications such as robotics, augmented reality, and large-scale scene understanding, where high-resolution data is often unavailable due to computational constraints. To address…

The instance segmentation can be considered an extension of the object detection problem where bounding boxes are replaced by object contours. Strictly speaking the problem requires to identify each pixel instance and class independently of…

As the global population ages, the number of fall-related incidents is on the rise. Effective fall detection systems, specifically in healthcare sector, are crucial to mitigate the risks associated with such events. This study evaluates the…

Transformer-based real-time object detectors achieve strong accuracy-latency trade-offs, and D-FINE is among the top-performing recent architectures. However, real-time instance segmentation with transformers is still less common. We…

End-to-end paradigms significantly improve the accuracy of various deep-learning-based computer vision models. To this end, tasks like object detection have been upgraded by replacing non-end-to-end components, such as removing non-maximum…

Face detection in unrestricted conditions has been a trouble for years due to various expressions, brightness, and coloration fringing. Recent studies show that deep learning knowledge of strategies can acquire spectacular performance…

Semi-Supervised Instance Segmentation (SSIS) aims to leverage an amount of unlabeled data during training. Previous frameworks primarily utilized the RGB information of unlabeled images to generate pseudo-labels. However, such a mechanism…

This paper addresses the critical need for improved explainability in text-based depression detection. While offering predictive outcomes, current solutions often overlook the understanding of model predictions which can hinder trust in the…

Can our video understanding systems perceive objects when a heavy occlusion exists in a scene? To answer this question, we collect a large-scale dataset called OVIS for occluded video instance segmentation, that is, to simultaneously…

Existing 3D instance segmentation methods frequently encounter issues with over-segmentation, leading to redundant and inaccurate 3D proposals that complicate downstream tasks. This challenge arises from their unsupervised merging approach,…

The accurate detection and segmentation of pavement distresses, particularly tiny and small cracks, are critical for early intervention and preventive maintenance in transportation infrastructure. Traditional manual inspection methods are…

Intrusion detection systems (IDSs) have become a widely used measure for security systems. The main problem for those systems results is the irrelevant alerts on those results. We will propose a data mining based method for classification…