Related papers: SpaceNet MVOI: a Multi-View Overhead Imagery Datas…
Identification of road networks and optimal routes directly from remote sensing is of critical importance to a broad array of humanitarian and commercial applications. Yet while identification of road pixels has been attempted before,…
360{\deg} images can provide an omnidirectional field of view which is important for stable and long-term scene perception. In this paper, we explore 360{\deg} images for visual object tracking and perceive new challenges caused by large…
Intrinsic image decomposition (IID) of outdoor scenes is crucial for relighting, editing, and understanding large-scale environments, but progress has been limited by the lack of real-world datasets with reliable albedo and shading…
Open Set Object Detection has seen rapid development recently, but it continues to pose significant challenges. Language-based methods, grappling with the substantial modal disparity between textual and visual modalities, require extensive…
Deep neural networks (DNNs) have shown exceptional performance when trained on well-illuminated images captured by Electro-Optical (EO) cameras, which provide rich texture details. However, in critical applications like aerial perception,…
Trans-Neptunian Objects (TNOs) provide a window into the history of the Solar System, but they can be challenging to observe due to their distance from the Sun and relatively low brightness. Here we report the detection of 75 moving objects…
Although state-of-the-art object detection methods have shown compelling performance, models often are not robust to adversarial attacks and out-of-distribution data. We introduce a new dataset, Natural Adversarial Objects (NAO), to…
Video object segmentation aims at accurately segmenting the target object regions across consecutive frames. It is technically challenging for coping with complicated factors (e.g., shape deformations, occlusion and out of the lens). Recent…
As the volume of image data grows, data-oriented cloud computing in Internet of Video Things (IoVT) systems encounters latency issues. Task-oriented edge computing addresses this by shifting data analysis to the edge. However, limited…
Detection of artificial objects from underwater imagery gathered by Autonomous Underwater Vehicles (AUVs) is a key requirement for many subsea applications. Real-world AUV image datasets tend to be very large and unlabelled. Furthermore,…
Visual Anomaly Detection (VAD) is a critical task for many applications including industrial inspection and healthcare. While VAD has been extensively studied, two key challenges remain largely unaddressed in conjunction: edge deployment,…
Object detection, instance segmentation, and pose estimation are popular visual recognition tasks which require localizing the object by internal or boundary landmarks. This paper summarizes these tasks as location-sensitive visual…
Multi-View Stereo~(MVS) is a fundamental problem in geometric computer vision which aims to reconstruct a scene using multi-view images with known camera parameters. However, the mainstream approaches represent the scene with a fixed…
Most contributions on Few-Shot Object Detection (FSOD) evaluate their methods on natural images only, yet the transferability of the announced performance is not guaranteed for applications on other kinds of images. We demonstrate this with…
As the roadside perception plays an increasingly significant role in the Connected Automated Vehicle Highway(CAVH) technologies, there are immediate needs of challenging real-world roadside datasets for bench marking and training various…
Semantic segmentation stands as a pivotal research focus in computer vision. In the context of industrial image inspection, conventional semantic segmentation models fail to maintain the segmentation consistency of fixed components across…
Vehicles, pedestrians, and riders are the most important and interesting objects for the perception modules of self-driving vehicles and video surveillance. However, the state-of-the-art performance of detecting such important objects (esp.…
Existing view-based methods excel at recognizing 3D objects from predefined viewpoints, but their exploration of recognition under arbitrary views is limited. This is a challenging and realistic setting because each object has different…
Object recognition in unseen indoor environments remains a challenging problem for visual perception of mobile robots. In this letter, we propose the use of topologically persistent features, which rely on the objects' shape information, to…
Real-world applications of computer vision in the humanities require algorithms to be robust against artistic abstraction, peripheral objects, and subtle differences between fine-grained target classes. Existing datasets provide…