Abstract Domain adaptive object detection (DAOD) aims to alleviate transfer performance
degradation caused by the cross-domain discrepancy. However, most existing DAOD …

Satellite videos capture the dynamic changes in a large observed sense, which provides an
opportunity to track the object trajectories. However, existing multiple object tracking (MOT) …

Unsupervised domain adaptive object detection (UDA-OD) is a challenging problem since it
needs to locate and recognize objects while maintaining the generalization ability across …

To enhance the transferability of object detection models in real-world scenarios where data
is sampled from disparate distributions, considerable attention has been devoted to domain …

Obeject detection as a fundamental task of environmental perception systems in
autonomous vehicles (AVs), is significant for intelligent driving safety that precise detection …

Domain adaptive object detection (DAOD) aims to generalize detectors trained on an
annotated source domain to an unlabelled target domain. As the visual-language models …

With the emergence of foundation models, deep learning-based object detectors have
shown practical usability in closed set scenarios. However, for real-world tasks, object …

Object detection with the capacity to incrementally adapt to new domains is a crucial yet
relatively under-explored research topic. The catastrophic forgetting problem presents a …

Object detection using LiDAR point clouds relies on a large amount of human-annotated
samples when training the underlying detectors' deep neural networks. However, generating …

Data augmentation is widely used in computer vision tasks for enhancing the diversity of
training data. However, due to sample redundancy and lack of object background, it is …