Hyperspectral band selection seeks to identify a compact subset of informative spectral channels that preserves task–relevant information while mitigating the storage, transmission, and computational burdens imposed by high–dimensional data. Yet prevailing techniques face two pervasive limitations: (i) scoring- or ranking-based methods assess bands independently, overlooking the joint dependency that determine their true utility; and (ii) combinatorial search approaches, though theoretically exhaustive, require prohibitive enumeration that is incompatible with the scale and end-to-end nature of modern deep-learning pipelines. We recast band selection as a combinatorial inference problem and propose a task-agnostic framework that embeds a learnable Band Selection Layer equipped with an Expectation–Maximization–driven Sparsity Loss The E-step efficiently enumerates the expected likelihood of allk-out-of-Bband subsets via dynamic programming, thereby making implicit dependencies explicit; the M-step optimises band importances toward a provablyk-sparse solution without post-hoc thresholding. Comprehensive theoretical analysis proves the absence of spurious local maxima and guarantees convergence to an exact sparse optimum. Extensive experiments on three public benchmarks (KSC, HT2013, HT2018), two auxiliary tasks (anomaly and target detection), and six classifiers demonstrate that the proposed method consistently surpasses state-of-the-art baselines. The results confirm that EM-guided sparsification not only stabilises the sparsity pattern but also yields interpretable inter-band dependency structures, making the framework a robust and broadly applicable tool for hyperspectral analysis and other sparsity-oriented vision problems.

Image understanding and analysis primarily rely on object appearances. However, when faced with challenges such as occlusion, camouflage, and small targets in surveillance scenarios, the discriminative features of objects cannot be effectively extracted. This paper proposes the utilization of hyperspectral imaging techniques as a solution to these issues, aiming to unlock new potential in the field. Hyperspectral images have the unique capability to identify a variety of materials, thereby offering a distinct advantage in surveillance. However, existing hyperspectral image datasets are not specifically tailored for image classification tasks within surveillance scenarios. To address this issue, we introduce an innovative hyperspectral image dataset designed explicitly for real-world surveillance, with the goal of setting a new benchmark for material classification. Our aspiration extends beyond merely deploying deep learning methods for hyperspectral material classification, aiming to contribute insightful understanding of spectral patterns inherent in natural surveillance scenes. The proposed dataset is currently the largest of its kind and the first one designed specifically for surveillance scenarios. It encompasses 128 spectral bands and provides annotations for 28 common material categories. Furthermore, we introduce a novel texture-metric-based spatial and spectral fusion network, meticulously crafted to accommodate our unique scenario and dataset. This model significantly outperforms existing networks in enhancing the fusion of spatial and spectral features, achieving state-of-the-art results on both our proposed dataset and existing public hyperspectral image classification datasets. For access to this unique dataset, please visithttps://github.com/robberban/HIC-for-Surveillance.git.

Domain adaptive object detection has always been a problem widely concerned by academia and industry. The variability of application scenes and the unknown target labels in the target domain make it challenging for well-trained detectors to generalize well by supervised learning. Due to the lack of instance-level information, previous approaches often tend to achieve image-level and pixel-level alignment using the model's own knowledge, but this is of finite help in separating the object to be detected from the image background, and it is difficult for the model itself to learn the foreground characteristics of the target domain. In this paper, we propose a method for domain-adaptive detection based on coarse-grained foreground guidance. Our approach uses an unsupervised foreground extraction algorithm to estimate the coarse locations of objects in the video, which can provide knowledge for instance features and progressively improve the cross-domain detection ability of the model. Experiments on the cross-domain object detection dataset confirm the effectiveness of our approach. We have also conducted experiments in real outdoor traffic scenarios, and the results indicate that our method can operate in real application scenarios.

Connectionist Temporal Classification (CTC) is an objective function for sequence learning and has shown promising results in speech and text recognition tasks. However, its inherent mechanism has not been investigated thoroughly. In this paper, we propose a theoretical explanation of CTC from the perspective of the Expectation-Maximization (EM) algorithm. Based on the EM analysis, we propose a pseudo-label-based L1 regularization and voting decoding algorithm to improve the performance of text recognition. The L1 regularization can reduce the pseudo-label estimation error, while the voting decoding algorithm modifies the built-in decoding logic of CTC and introduces a voting mechanism to the inference process. Experiments of handwritten text recognition show that the proposed method consistently improves over the CTC baseline and yields state-of-the-art results on three benchmark datasets.