Plastic bottles are widely used in various aspects of daily life, commonly for the storage of liquids in food and beverage packaging, pharmaceutical products, cosmetics, and personal care items. This widespread use places higher demands on the production quality of plastic bottles. Effective defect detection technologies are needed to optimize the plastic bottle manufacturing process, but the development of such technologies has been hindered by the lack of publicly available datasets. To address this issue, we propose two dedicated datasets for detecting defects in plastic bottles: one for bottle bodies and the other for shoulders. The plastic bottle body dataset consists of 500 images, captured from a professional workstation, containing four types of defects. The plastic bottle shoulder dataset consists of 3,463 images of shoulders with various types and colors, captured under the same conditions, and includes two types of defects as well as neck positioning marks. All data were collected using professional imaging equipment. In addition, we conducted benchmark experiments using common object detection models on the proposed datasets to demonstrate their usability in the field of defect detection. The datasets and related code will be made publicly available at https://github.com/lzy-coder/PBD.

Recently, cluster-based methods have achieved significant success in unsupervised re-ID tasks. The hierarchical clustering algorithm, exemplified by SpCL, has been widely adopted in unsupervised cross-domain adaptation and unsupervised learning. The momentum-based feature update mechanism in SpCL has been integrated into various algorithms, achieving notable results in subsequent studies. In this paper, we propose a multi-queue feature updating algorithm that stores feature vectors corresponding to person IDs in multiple queues. Random sampling is then applied to construct the negative sample matrix for contrastive loss, addressing the limitations of momentum-based updating methods. Additionally, we replace the static temperature coefficient in contrastive loss with a trainable temperature coefficient, enabling the model to automatically balance sensitivity between easy and hard samples. The code is available at https://github.com/bmfarer/multi-queue.git.

In this paper, we propose a novel task of 3D Human Motion Moment Retrieval (HMMR), which aims to find the motion segments from a large motion corpus that semantically correspond to a given linguistic query. To better understand this goal, we treat this unexplored task as a combination of motion retrieval (MR) and moment localization (ML) subtasks. However, most existing retrieval methods directly align text and motion through contrastive learning (for MR), often overlooking the contextual richness and semantic overlap between different moments (for ML). Inspired by this, we propose a Multi-Granularity Semantic-aware Network (MGSNet) to perceive the target moment from multiple atomic motions with intricate semantics. Specifically, (1) a query-aligned attention module is constructed to learn the semantic representations of different modalities; (2) a moment match module is then introduced to comprehensively align text and motion sequence by decomposing the motion into three granularities: frame-, segment- and event-wise levels. Extensive experiments on HumanML3D-Aug and BABEL datasets demonstrate the potential of our framework in corpus-level HMMR.

Coded Aperture Snapshot Spectral Imaging (CASSI) multiplexes 3D Hyperspectral Images (HSIs) into a 2D sensor to capture dynamic spectral scenes, which, however, sacrifices the spatial information. Dual-Camera Compressive Hyperspectral Imaging (DCCHI) enhances CASSI by incorporating a Panchromatic (PAN) camera to compensate for the loss of spatial information in CASSI. However, the dual-camera structure of DCCHI disrupts the diagonal property of the product of the sensing matrix and its transpose, making it difficult to efficiently and accurately solve the data subproblem in closed-form and thereby hindering the application of model-based methods and Deep Unfolding Networks (DUNs) that rely on such a closed-form solution. To address this issue, we propose an Alternating Direction DUN, named ADRNN, which decouples the imaging model of DCCHI into a CASSI subproblem and a PAN subproblem. The ADRNN alternately solves data terms analytically and a joint prior term in these subproblems. Additionally, we propose a Cross Spectral Transformer (XST) to exploit the joint prior. The XST utilizes cross spectral attention to exploit the correlation between the compressed HSI and the PAN image, and incorporates Grouped-Query Attention (GQA) to alleviate the burden of parameters and computational cost brought by impartially treating the compressed HSI and the PAN image. Furthermore, we built a real DCCHI system and captured large-scale indoor and outdoor scenes for future academic research. Extensive experiments on both simulation and real datasets demonstrate that the proposed method achieves state-of-the-art (SOTA) performance. The code and datasets have been open-sourced at: https://github.com/ShawnDong98/ADRNN-XST.

In the coded aperture snapshot spectral imaging (CASSI) system, deep unfolding networks (DUNs) have demonstrated excellent performance in recovering 3-D hyperspectral images (HSIs) from 2-D measurements. However, some noticeable gaps exist between the imaging model used in DUNs and the real CASSI imaging process, such as the sensing error as well as photon and dark current noise, compromising the accuracy of solving the data subproblem and the prior subproblem in DUNs. To address this issue, we propose a degradation estimation network (DEN) to correct the imaging model used in DUNs by simultaneously estimating the sensing error and the noise level, thereby improving the performance of DUNs. Additionally, we propose an efficient local and non-local transformer (LNLT) to solve the prior subproblem, which not only effectively models local and non-local similarities but also reduces the computational cost of the window-based global multihead self-attention (MSA). Furthermore, we transform the DUN into a recurrent neural network (RNN) by sharing parameters of DNNs across stages, which not only allows DNN to be trained more adequately but also significantly reduces the number of parameters. The proposed DERNN-LNLT achieves state-of-the-art (SOTA) performance with fewer parameters on both simulation and real datasets (code:https://github.com/ShawnDong98/DERNN-LNLT).

In hyperspectral image (HSI) classification, it is a great challenge on how to extract key informative spectral–spatial features efficiently and suppress useless features from abundant spectral–spatial information. In this article, inspired by the attention mechanism of the human visual system, we propose a novel spectral–spatial–semantic network (S3Net) with the multiway attention mechanism for HSI classification. The S3Net consists of a spectral branch, a spatial branch, and a multiscale semantic module. The spectral branch extracts the multiway spectral features with a dense spectral block and a multiway spectral attention module. The spatial branch extracts the multiway spatial features with a multiscale spatial block and a multiway spatial attention module. The multiscale semantic module extracts spectral–spatial–semantic features that are used for classification. In the proposed S3Net, the multiway attention modules in spectral and spatial branches are built to enhance the extraction ability of the key informative spectral–spatial features. The multiscale spatial block in the spatial branch is designed to learn strong complementary and related information. The Res2Net in the multiscale semantic module is used to learn multiscale semantic features at a granular level. A large number of experimental results demonstrate that, on the University of Pavia, Kennedy Space Center, and Pavia Center data sets, the proposed S3Net achieves higher classification accuracy than state-of-the-art methods on the limited training samples. Remarkably, our S3Net also achieves the best performance on the mineral exploration HSI data set, called Huoshaoyun, which is collected by the GaoFen-5 (GF-5) satellite.

In this correspondence, we introduce a new imaging method to obtain high-resolution (HR) images. The image acquisition is performed in two stages, compressive measurement and optimization reconstruction. In order to reconstruct HR images by a small number of sensors, compressive measurements are made. Specifically, compressive measurements are made by a low-resolution (LR) camera with randomly fluttering shutter, which can be viewed as a moving random exposure pattern. In the optimization reconstruction stage, the HR image is computed by different models according to the prior knowledge of scenes. The proposed imaging method offers a new way of acquiring HR images of essentially static scenes when the camera resolution is limited by severe constraints such as cost, battery capacity, memory space, transmission bandwidth, etc. and when the prior knowledge of scenes is available. The simulation results demonstrate the effectiveness of the proposed imaging method.

Color demosaicking is an ill-posed inverse problem of image restoration. The performance of a color demosaicking algorithm depends on how thoroughly it can exploit domain knowledge to confine the solution space for the underlying true color image. We propose a sparsity-based ℓ1minimization technique for color demosaicking that exploits both interband and intra-band sparse representations of natural images. In some of most challenging cases of color demosaicking, the proposed technique outperforms those published in the literature by a significant margin in both PSNR and visual quality.

Recently compressive sensor developed as an imager for capturing images effectively has been studied extensively. In this paper, we design a new imager to reconstruct high resolution image from a low resolution blurred image obtained by the intended movable random exposure. This imager grabs an image by moving a camera with a randomly fluttering shutter along a certain motion route. By analyzing this kind of movable random exposure process, we find it can be considered as compressive sampling described in the compressive sensing (CS) theory. Then according to the CS theory, the exposure result of this imager can be used to recover a high resolution image. Since this imager consists only a movable camera and a fluttered shutter, it is relatively simple and easy to implement. The simulation results show that the proposed imager can recover high even ultra-high resolution images with good reconstruction performance.