The human visual system can rapidly focus on prominent objects in complex scenes, significantly enhancing information processing efficiency. Salient object detection (SOD) mimics this biological ability, aiming to identify and segment the most prominent regions or objects in images or videos. This reduces the amount of data needed to process while enhancing the accuracy and efficiency of information extraction. In recent years, SOD has made significant progress in many areas such as deep learning, multi-modal fusion, and attention mechanisms. Additionally, it has expanded in real-time detection, weakly supervised learning, and cross-domain applications. Depth images can provide three-dimensional structural information of a scene, aiding in a more accurate understanding of object shapes and distances. In SOD tasks, depth images enhance detection accuracy and robustness by providing additional geometric information. This additional information is particularly crucial in complex scenes and occlusion situations. This survey reviews the substantial advancements in the field of RGB-Depth SOD, with a focus on the critical roles played by attention mechanisms and cross-modal fusion methods. It summarizes the existing literature, provides a brief overview of mainstream datasets and evaluation metrics, and quantitatively compares the discussed models.

In complex marine environments, extracting target features from acoustic signal is very difficult, making the targets hard to be recognized. Therefore, it is necessary to perform denoising method on the acoustic signal to highlight the target features. However, training deep learning denoising models requires a large mount of acoustic data with labels and obtaining labels with real measured data is also extremely difficult. In this paper, an enhanced simulation algorithm, which considers integrating features of target line spectrum and ocean environmental noise, is proposed to construct a large-scale training sample set. Additionally, a deep convolutional denoising model is presented, which is first train on simulated data and directly applied to real measured data for denoising, enabling line spectrum to be significantly displayed in the time-frequency spectrogram. The results on simulation experiments and sea trials demonstrate that the proposed method can significantly reduce ocean noise while preserving the characteristics of target line spectrum. Furthermore, the experiments demonstrate that the proposed convolutional denoising model has transferability and generalization, making it suitable for denoising underwater acoustic signal in different marine areas.

Visual target tracking is a fundamental task in computer vision. Combining multi-modal information with tracking leverages complementary information, which improves the precision and robustness of trackers. Traditional multi-modal tracking methods typically employ a full fine-tuning scheme, i.e., fine-tuning pre-trained single-modal models to multi-modal tasks. However, this approach suffers from low transfer learning efficiency, catastrophic forgetting, and high cross-task deployment costs. To address these issues, we propose an efficient model named multi-modal prompt vision tracker (MPVT) based on an efficient prompt-tuning paradigm. Three key components are involved in the model: a decoupled input enhancement module, a dynamic adaptive prompt fusion module, and a fully connected head network module. The decoupled input enhancement module enhances input representations via positional and type embedding. The dynamic adaptive prompt fusion module achieves efficient prompt tuning and multi-modal interaction using scaled convolution and low-rank cross-modal attention mechanisms. The fully connected head network module addresses the shortcomings of traditional convolutional head networks such as inductive biases. Experimental results from RGB-T, RGB-D, and RGB-E scenarios show that MPVT outperforms state-of-the-art methods. Moreover, MPVT can save 43.8% GPU memory usage and reduce training time by 62.9% compared with a full-parameter fine-tuning model.

In Underwater Acoustic Target Recognition (UATR), accurately extracting spectral lines from time–frequency spectra in complex ocean environments faces three critical challenges: low-frequency spectral confusion, line spectrum and noise mixture, and a computational efficiency vs. performance trade-off. To address these, we propose a deep learning-integrated framework based on application-oriented integration and adaptation of established techniques tailored to the underwater acoustic domain. The framework consists of the following: (1) the Line Spectrum Separation Network (LSS-Net), which integrates a Time–Frequency Joint LSTM and a Temporal Gated Cross-Attention (TGCA) module within an encoder–decoder architecture adapted for high-resolution underwater acoustic time–frequency spectra; (2) a physics-informed signal simulation approach that realistically models Doppler frequency drift and intensity fluctuations; and (3) a Peak-Tracking Line Extractor (PTLE) algorithm that leverages underwater acoustic-specific temporal constraints. The proposed framework achieves an MOTA of 0.89 on simulated data and 0.52 on real sea trial data, outperforming existing methods by 0.06-2.14 in MOTA and significantly suppressing high-resolution background noise.