A Tri-Modal Dataset and a Baseline System for Tracking Unmanned Aerial Vehicles

MambaRefine-YOLO has been introduced as a dual-modality small object detector specifically designed for Unmanned Aerial Vehicle (UAV) imagery, addressing the challenges of low resolution and background clutter in small object detection. The model incorporates a Dual-Gated Complementary Mamba fusion module (DGC-MFM) and a Hierarchical Feature Aggregation Neck (HFAN), achieving a state-of-the-art mean Average Precision (mAP) of 83.2% on the DroneVehicle dataset.

A new framework called KTCAA has been introduced for few-shot cross-modal sketch person re-identification, aiming to bridge the gap between hand-drawn sketches and RGB surveillance images. This framework addresses challenges related to domain discrepancy and perturbation invariance, proposing innovative components like Alignment Augmentation and Knowledge Transfer Catalyst to enhance model robustness and alignment capabilities.

One4D has been introduced as a unified framework for 4D generation and reconstruction, capable of producing dynamic 4D content through synchronized RGB frames and pointmaps. This framework utilizes a Unified Masked Conditioning mechanism to handle varying sparsities of conditioning frames, allowing for seamless transitions between 4D generation from a single image and reconstruction from full videos or sparse frames.

Recent advancements in unmanned aerial vehicle (UAV) technology have led to the development of an optimized planning strategy for search and rescue missions in occluded environments, such as dense forests. This strategy focuses on enhancing the effectiveness of UAVs by optimizing camera positioning and perspective to capture clearer ground views during critical missions following natural disasters.

The introduction of the Promptable 3D Detector (Pro3D) marks a significant advancement in roadside monocular 3D detection, which involves identifying objects in RGB frames and predicting their 3D attributes, such as bird's-eye-view locations. This innovation leverages 2D detections as prompts to enhance the accuracy and efficiency of 3D detection processes.

A new framework for articulated object reconstruction has been proposed, utilizing planar Gaussian Splatting to reconstruct 3D objects from sparse-view RGB images captured from a single state. This method introduces a Gaussian information field to optimize viewpoint selection and employs a coarse-to-fine optimization strategy for depth estimation and part segmentation.

A new framework for autonomous UAV navigation has been proposed, focusing on meta-policy switching to enhance resilience against adversarial attacks that manipulate sensor inputs. This approach utilizes a discounted Thompson sampling mechanism to dynamically select robust policies, addressing the limitations of traditional reinforcement learning methods in adversarial airspace.