Unmanned Aerial Vehicles (UAVs) are widely adopted across various fields, yet they raise significant privacy and safety concerns, demanding robust monitoring solutions. Existing anti-UAV methods primarily focus on position tracking but fail to capture UAV behavior and intent. To address this, we introduce a novel task—UAV Tracking and Intent Understanding (UTIU)—which aims to track UAVs while inferring and describing their motion states and intent for a more comprehensive monitoring approach. To tackle the task, we propose JTD-UAV, the first joint tracking, and intent description framework based on large language models. Our dual-branch architecture integrates UAV tracking with Visual Question Answering (VQA), allowing simultaneous localization and behavior description. To benchmark this task, we introduce the TDUAV dataset, the largest dataset for joint UAV tracking and intent understanding, featuring 1,328 challenging video sequences, over 163K annotated thermal frames, and 3K VQA pairs. Our benchmark demonstrates the effectiveness of JTD-UAV.

High resolution range profile (HRRP) plays a crucial role in radar target recognition. In real-world applications, variations in operational conditions during testing, such as changes in depression angles, result in unsatisfactory performance for HRRP target recognition methods. One way to alleviate this issue is to augment training data with samples that embody the testing domain style. Therefore, we propose a domain-adaptive HRRP generation approach based on a two-stage denoising diffusion probability model (DDPM). In the first stage, we leverage the category labels as conditioning factors, ensuring precise category control over the pre-generated contents. In the second stage, we harness style information from reference samples to steer the pre-generated content closer to the testing domain. By augmenting training data with the generated samples, the disparity between two domains is bridged. Results on the moving and stationary target acquisition and recognition (MSTAR) dataset show that the proposed method improves the recognition rate by 2.01% and 4.93% for the data of 15° and 17° depression angle, respectively.

Continual learning strives to acquire knowledge across sequential tasks without forgetting previously assimilated knowledge. Current state-of-the-art methodologies utilize dynamic architectural strategies to increase the network capacity for new tasks. However, these approaches often suffer from a rapid growth in the number of parameters. While some methods introduce an additional network compression stage to address this, they tend to construct complex and hyperparameter-sensitive systems. In this work, we introduce a novel solution to this challenge by proposing Memory-Boosted transformer (MoBoo), instead of conventional architecture expansion and compression. Specifically, we design a memory-augmented attention mechanism by establishing a memory bank where the “key” and “value” linear projections are stored. This memory integration prompts the model to leverage previously learned knowledge, thereby enhancing stability during training at a marginal cost. The memory bank is lightweight and can be easily managed with a straightforward queue. Moreover, to increase the model’s plasticity, we design a memory-attentive aggregator, which leverages the cross-attention mechanism to adaptively summarize the image representation from the encoder output that has historical knowledge involved. Extensive experiments on challenging benchmarks demonstrate the effectiveness of our method. For example, on ImageNet-100 under 10 tasks, our method outperforms the current state-of-the-art methods by +3.74% in average accuracy and using fewer parameters.

The detection performance in crowd scenes is limited by recalling hard objects (e.g., occluded objects). It requires that this kind of objects can be successfully detected and retained by the non-maximum suppression (NMS) while controlling false positives. The existing dynamic label assignment algorithms can help recall these objects by adaptively allocating appropriate positive samples, however, they ignore the alignment with the selecting rules of NMS. This leads to the fact that detecting objects in crowd scenes are still very sensitive to the NMS threshold setting. As a result, the existing methods can only set a low NMS threshold to avoid the excessive false positives, causing some objects failed to be recalled. And these methods also generally lack more excitation for positive samples, which hinders further facilitating the recall of hard instances in crowd scenes. This article proposes a novel dynamic label assignment strategy for object detection in crowd scenes, callednon-maximum suppression guided label assignment(NGLA), which aligns the assignment strategy with NMS process and learns more prominent positive samples. Following NMS, NGLA introduces the IoU between samples with their corresponding best samples to define positive and negative samples. To cooperate with NGLA, anNMS-aware lossis proposed to dynamically assign sample weights when supervising sample predictions, which also considers the IoU with the best sample. In addition, for better classification prediction, aregression assisted classification branchis designed to help detectors perceive the relation between the regression predictions of each sample and the corresponding best sample. Experiments demonstrate that NGLA outperforms other label assignment methods on CrowdHuman and Citypersons, and is less sensitive to the NMS threshold in crowd scenes.

High resolution range profile (HRRP) is essential for high-throughput radar automatic target recognition. Due to the aspect sensitivity of HRRP, the recognition performance degrades when the training dataset misses some aspects. Inspired by disentangled representation learning (DRL), this letter proposes a type-aspect disentanglement network to alleviate the above aspects missing problem. The proposed method disentangles HRRP into uncorrelated type and aspect representations, so that the type representation can be used to accurately recognize target without being affected by target aspects. Specifically, the proposed network acquires initial type and aspect representations by residual factorization. On this basis, mutual information (MI) minimization is used to constrain the independence of two representations from each other, and a reconstruction loss is employed to avoid information reduction during the decorrelation process. Additionally, target type and aspect labels are exploited to constrain their semantic meanings. Experimental results demonstrate that the proposed method achieves improved robustness in varying degrees of aspects missing cases.

Semantic segmentation plays an important role in very high resolution (VHR) image understanding. Despite the potentials of the deep convolutional network in improving performance by end-to-end feature learning, each model has its limitations, and it is hard to discriminate complex features purely by a single model. Ensemble learning is promising for integrating the strengths of different models, however, the ensemble of deep models is challenging due to the huge amount of parameters and computation of the deep model itself as well as the difficulty in capturing complementarity between different models. To tackle these problems, a head-level ensemble network (HENet) is proposed in this letter, which reduces model complexity by sharing feature extraction networks and improves complementarity between models by novel cooperative learning (CL). Experiments on ISPRS 2-D semantic labeling benchmark demonstrate the effectiveness and advantage of the proposed method.

Detecting ships from synthetic aperture radar (SAR) images is inherently subject to its imaging mechanism. With the development of deep learning, advanced learning-based techniques have been migrated from optical images to SAR images. However, the default hyperparameters (e.g., learning rate, size of the anchor box) predefined by a heuristic strategy on optical images might be suboptimal for SAR datasets. In addition, the low-quality imaging in SAR images further reduces the portability of hyperparameters. To solve this problem, a new optimization method, named reinforcement learning and hyperband (RLH), is proposed to dynamically learn hyperparameter configurations by deep reinforcement learning (DRL), where a neural network is adopted to capture the relationship between different configurations and predict new configurations to further improve the performance. Hyperparameter configuration is able to be automatically learned to accommodate various SAR image datasets, and experiments on two SAR image datasets demonstrate the effectiveness and advantage of the proposed approach.

Object monitoring can be performed by change detection algorithms. However, for the image pair with a large perspective difference, the change detection performance is usually impacted by inaccurate image registration. To address the above difficulties, a novel object-specific change detection approach is proposed for object monitoring in this paper. In contrast to traditional approaches, the proposed approach is robust to view angle variation and does not require explicit image registration. Experiments demonstrate the effectiveness and advantages of the proposed approach.