The field of aerial surveillance and object detection is rapidly advancing with the development of new technologies and techniques. Researchers are exploring new approaches to improve the accuracy and efficiency of object detection in aerial images and videos, including the use of deep learning methods, multi-modal fusion, and meta-learning. One of the key challenges in this field is the ability to detect and track small objects in complex environments, such as low-altitude aircraft or maritime objects. To address this challenge, researchers are proposing new datasets and benchmarking protocols to evaluate the performance of object detection algorithms in these scenarios. Noteworthy papers in this area include SatSAM2, which proposes a zero-shot satellite video tracker that outperforms state-of-the-art methods, and LAA3D, which introduces a large-scale dataset for 3D detection and tracking of low-altitude aerial vehicles. Additionally, papers like MambaRefine-YOLO and IrisNet are proposing new methods for small object detection in UAV imagery, leveraging techniques such as dual-modality fusion and meta-learning. Overall, the field of aerial surveillance and object detection is seeing significant advancements, with a focus on improving the accuracy and efficiency of object detection algorithms in complex environments.