Chih-Chung Hsu

Multispectral imaging based on unmanned aerial vehicle (UAV) can capture valuable spectral, thereby improving the capability of object tracking. However, most existing multispectral trackers focus on feature matching of the foreground target, leading to target loss due to sparse features and strong interference under complex backgrounds. To address this challenge, we propose the positive-negative prompt mining network (PNPM-Net), which models both background interference and target features as structured negative and positive prompts to enhance feature discriminability under complex scenarios. It mainly consists of three key components: spatial-spectral-temporal attention mining (SSTAM), positive-negative joint mining (PNJM) module and dual-incentive prompt modulation (DIPM) module. First, we propose SSTAM for adaptive spectral channel re-weighting and spatial reshaping, thereby augmenting the spatial-spectral separability between target and background signatures under complex dynamic scenarios. Second, we introduce PNJM to generate contrastive priors modeling the positive and negative prompts. Finally, we develop DIPM to employ these priors for feature enhancement and background suppression, thereby increasing the inter-class discriminativeness between target and background. Experiments show PNPM-Net achieves 71.8% AUC and 88.1% DP@20, surpassing SOTA methods by 18.5% and 9.2%, respectively, which demonstrate the strong potential in UAV-based multispectral object tracking area.

Recent advances in all-in-one (AiO) RGB image restoration have demonstrated the effectiveness of prompt learning in handling multiple degradations within a single model. However, adapting these approaches to hyperspectral image (HSI) restoration poses significant challenges due to the domain gap between RGB and HSI features, information loss in visual prompts under severe composite degradations, and difficulties in capturing HSI-specific degradation patterns via text prompts. To address these limitations, we introduce PromptHSI, the first universal AiO HSI restoration framework that is both prompt-guided and frequency-aware. By incorporating frequency-aware feature modulation, which uses frequency analysis to decouple complex composite degradations, and by employing vision–language model (VLM)–guided prompt learning, our approach decomposes text prompts into intensity and bias controllers that effectively guide the restoration process while mitigating domain discrepancies. Extensive experiments demonstrate that our unified architecture excels at both fine-grained detail recovery and global information restoration across diverse degradation scenarios, highlighting its significant potential for practical remote sensing applications.

Multi-source CT-scan classification suffers from domain shifts that impair cross-source generalization. While preprocessing pipelines combining Spatial-Slice Feature Learning (SSFL++) and Kernel-Density-based Slice Sampling (KDS) have shown empirical success, the mechanisms underlying their domain robustness remain underexplored. This study analyzes how this input-space standardization manages the trade-off between local discriminability and cross-source generalization. The SSFL++ and KDS pipeline performs spatial and temporal standardization to reduce inter-source variance, effectively mapping disparate inputs into a consistent target space. This preemptive alignment mitigates domain shift and simplifies the learning task for network optimization. Experimental validation demonstrates consistent improvements across architectures, proving the benefits stem from the preprocessing itself. The approach's effectiveness was validated by securing first place in a competitive challenge, supporting input-space standardization as a robust and practical solution for multi-institutional medical imaging.

The 3rd Workshop on Maritime Computer Vision (MaCVi) 2025 addresses maritime computer vision for Unmanned Surface Vehicles (USV) and underwater. This report offers a comprehensive overview of the findings from the challenges. We provide both statistical and qualitative analyses, evaluating trends from over 700 submissions. All datasets, evaluation code, and the leaderboard are available to the public at https://macvi.org/workshop/macvi25.

High-resolution hyperspectral imaging plays a crucial role in various remote sensing applications, yet its acquisition often faces fundamental limitations due to hardware constraints. This paper introduces S$^{3}$RNet, a novel framework for hyperspectral image pansharpening that effectively combines low-resolution hyperspectral images (LRHSI) with high-resolution multispectral images (HRMSI) through sparse spatial-spectral representation. The core of S$^{3}$RNet is the Multi-Branch Fusion Network (MBFN), which employs parallel branches to capture complementary features at different spatial and spectral scales. Unlike traditional approaches that treat all features equally, our Spatial-Spectral Attention Weight Block (SSAWB) dynamically adjusts feature weights to maintain sparse representation while suppressing noise and redundancy. To enhance feature propagation, we incorporate the Dense Feature Aggregation Block (DFAB), which efficiently aggregates inputted features through dense connectivity patterns. This integrated design enables S$^{3}$RNet to selectively emphasize the most informative features from differnt scale while maintaining computational efficiency. Comprehensive experiments demonstrate that S$^{3}$RNet achieves state-of-the-art performance across multiple evaluation metrics, showing particular strength in maintaining high reconstruction quality even under challenging noise conditions. The code will be made publicly available.

Accurate detection and segmentation of gastrointestinal bleeding are critical for diagnosing diseases such as peptic ulcers and colorectal cancer. This study proposes a two-stage framework that decouples classification and grounding to address the inherent challenges posed by traditional Multi-Task Learning models, which jointly optimizes classification and segmentation. Our approach separates these tasks to achieve targeted optimization for each. The model first classifies images as bleeding or non-bleeding, thereby isolating subsequent grounding from inter-task interference and label heterogeneity. To further enhance performance, we incorporate Stochastic Weight Averaging and Test-Time Augmentation, which improve model robustness against domain shifts and annotation inconsistencies. Our method is validated on the Auto-WCEBleedGen Challenge V2 Challenge dataset and achieving second place. Experimental results demonstrate significant improvements in classification accuracy and segmentation precision, especially on sequential datasets with consistent visual patterns. This study highlights the practical benefits of a two-stage strategy for medical image analysis and sets a new standard for GI bleeding detection and segmentation. Our code is publicly available at this GitHub repository.