Related papers: SGDViT: Saliency-Guided Dynamic Vision Transformer…
A tracking controller for unmanned aerial vehicles (UAVs) is developed to track moving targets undergoing unknown translational and rotational motions. The main challenges are to control both the relative positions and angles between the…
Vision Transformers (ViTs) have achieved remarkable success over various vision tasks, yet their robustness against data distribution shifts and inherent inductive biases remain underexplored. To enhance the robustness of ViT models for…
Visual saliency, which predicts regions in the field of view that draw the most visual attention, has attracted a lot of interest from researchers. It has already been used in several vision tasks, e.g., image classification, object…
We introduce a transformer-based neural network to generate high-resolution (3km) synthetic radar reflectivity fields at scale from geostationary satellite imagery. This work aims to enhance short-term convective-scale forecasts of…
Understanding semantic scene segmentation of urban scenes captured from the Unmanned Aerial Vehicles (UAV) perspective plays a vital role in building a perception model for UAV. With the limitations of large-scale densely labeled data,…
With the advantage of high mobility, Unmanned Aerial Vehicles (UAVs) are used to fuel numerous important applications in computer vision, delivering more efficiency and convenience than surveillance cameras with fixed camera angle, scale…
In this paper, we present a new tracking architecture with an encoder-decoder transformer as the key component. The encoder models the global spatio-temporal feature dependencies between target objects and search regions, while the decoder…
Recent advances in cross-view geo-localization (CVGL) methods have shown strong potential for supporting unmanned aerial vehicle (UAV) navigation in GNSS-denied environments. However, existing work predominantly focuses on matching UAV…
Drones or general Unmanned Aerial Vehicles (UAVs), endowed with computer vision function by on-board cameras and embedded systems, have become popular in a wide range of applications. However, real-time scene parsing through object…
Object detection from Unmanned Aerial Vehicles (UAVs) is of great importance in many aerial vision-based applications. Despite the great success of generic object detection methods, a significant performance drop is observed when applied to…
The visual world can be parsimoniously characterized in terms of distinct entities with sparse interactions. Discovering this compositional structure in dynamic visual scenes has proven challenging for end-to-end computer vision approaches…
Although vision Transformers have achieved excellent performance as backbone models in many vision tasks, most of them intend to capture global relations of all tokens in an image or a window, which disrupts the inherent spatial and local…
Deep learning based salient object detection has recently achieved great success with its performance greatly outperforms any other unsupervised methods. However, annotating per-pixel saliency masks is a tedious and inefficient procedure.…
The spatial attention mechanism has been widely used to improve object detection performance. However, its operation is currently limited to static convolutions lacking content-adaptive features. This paper innovatively approaches from the…
Unmanned Aerial Vehicles (UAVs) are crucial in Search and Rescue (SAR) missions due to their ability to monitor vast maritime areas. However, small objects often remain difficult to detect from high altitudes due to low object-to-background…
Goal-conditioned navigation models for ground robots trained using supervised learning show promising zero-shot transfer, but their collision-avoidance capability nevertheless degrades under distribution shift, i.e. environmental, robot or…
Achieving reliable and safe autonomous driving in off-road environments requires accurate and efficient terrain traversability analysis. However, this task faces several challenges, including the scarcity of large-scale datasets tailored…
Skeleton-based action recognition receives the attention of many researchers as it is robust to viewpoint and illumination changes, and its processing is much more efficient than the processing of video frames. With the emergence of deep…
Recent works have demonstrated that transformer can achieve promising performance in computer vision, by exploiting the relationship among image patches with self-attention. While they only consider the attention in a single feature layer,…
Industrial vision anomaly detection plays a critical role in the advanced intelligent manufacturing process, while some limitations still need to be addressed under such a context. First, existing reconstruction-based methods struggle with…