Search Results (987)

Visible-infrared person re-identification (VI-ReID) is a challenging cross-modality retrieval task to match a person across different spectral camera views. Most existing works focus on learning shared feature representations from the final embedding space of advanced networks to alleviate modality differences between visible and infrared images. However, exclusively relying on high-level semantic information from the network’s final layers can restrict shared feature representations and overlook the benefits of low-level details. Different from these methods, we propose a multi-scale contrastive learning network (MCLNet) with hierarchical knowledge synergy for VI-ReID. MCLNet is a novel two-stream contrastive deep supervision framework designed to train low-level details and high-level semantic representations simultaneously. MCLNet utilizes supervised contrastive learning (SCL) at each intermediate layer to strengthen visual representations and enhance cross-modality feature learning. Furthermore, a hierarchical knowledge synergy (HKS) strategy for pairwise knowledge matching promotes explicit information interaction across multi-scale features and improves information consistency. Extensive experiments on three benchmarks demonstrate the effectiveness of MCLNet. Full article

The advancement of artificial intelligence (AI) technologies, including generative pre-trained transformers (GPTs) and generative models for text, image, audio, and video creation, has revolutionized content generation, creating unprecedented opportunities and critical challenges. This paper systematically examines the characteristics, methodologies, and challenges associated with detecting the synthetic content across multiple modalities, to safeguard digital authenticity and integrity. Key detection approaches reviewed include stylometric analysis, watermarking, pixel prediction techniques, dual-stream networks, machine learning models, blockchain, and hybrid approaches, highlighting their strengths and limitations, as well as their detection accuracy, independent accuracy of 80% for stylometric analysis and up to 92% using multiple modalities in hybrid approaches. The effectiveness of these techniques is explored in diverse contexts, from identifying deepfakes and synthetic media to detecting AI-generated scientific texts. Ethical concerns, such as privacy violations, algorithmic bias, false positives, and overreliance on automated systems, are also critically discussed. Furthermore, the paper addresses legal and regulatory frameworks, including intellectual property challenges and emerging legislation, emphasizing the need for robust governance to mitigate misuse. Real-world examples of detection systems are analyzed to provide practical insights into implementation challenges. Future directions include developing generalizable and adaptive detection models, hybrid approaches, fostering collaboration between stakeholders, and integrating ethical safeguards. By presenting a comprehensive overview of AIGC detection, this paper aims to inform stakeholders, researchers, policymakers, and practitioners on addressing the dual-edged implications of AI-driven content creation. Full article

Cistus monspeliensis L. (C. monspeliensis) is used in Italian folk medicine. This study was performed to determine genotoxic and antigenotoxic effects of C. monspeliensis leaf extract against mitomycin C (MMC) using an in vitro cytokinesis-block micronucleus assay (CBMN) in the Chinese Hamster Ovarian K1 (CHO-K1) cell line. The phytochemical composition of C. monspeliensis extract was evaluated using an untargeted metabolomic approach by employing UPLC-PDA-ESI/MS. The automated in vitro CBMN assay was carried out using image analysis systems with a widefield fluorescence microscope and the ImageStreamX imaging flow cytometer. The phytochemical profile of C. monspeliensis extract showed, as the most abundant metabolites, punicalagin, myricetin, gallocathechin, and a labdane-type diterpene. C. monspeliensis, at the tested concentrations of 50, 100, and 200 μg/mL, did not induce significant micronuclei frequency, thus indicating the absence of a genotoxic potential. When testing the C. monspeliensis extract for antigenotoxicity in the presence of MMC, we observed a hormetic concentration-dependent effect, where low concentrations resulted in a significant protective effect against MMC-induced micronuclei frequency, and higher concentrations resulted in no effect. In conclusion, our findings demonstrate that C. monspeliensis extract is not genotoxic and, at low concentration, exhibits an antigenotoxic effect. In relation to this final point, C. monspeliensis may act as a potential chemo-preventive against genotoxic agents. Full article

The nociceptin receptor (NOP) and nociceptin are involved in the pathways of pain and inflammation. The potent role of nuclear factor-κB (NFκB) in the modulation of tumor necrosis factor-α (TNF-α) and interleukin (IL)-1β on the nociceptin system in human THP-1 cells under inflammatory conditions were investigated. Cells were stimulated without/with phorbol-myristate-acetate (PMA), TNF-α, IL-1β, or PMA combined with individual cytokines. To examine NFκB’s contribution to the regulation of the nociceptin system, PMA-stimulated cells were treated with NFκB inhibitor BAY 11-7082, JSH-23, or anacardic acid before culturing with TNF-α or IL-1β. NOP and prepronociceptin (ppNOC) mRNA were quantified by RT-qPCR; cell membrane NOP and intracellular nociceptin protein levels were measured by flow cytometry. Phosphorylation and localization of NFκB/p65 were determined using ImageStream. PMA + TNF-α decreased NOP mRNA compared to stimulation with PMA alone, while PMA + IL-1β did not. BAY 11-7082 and JSH-23 reversed the repression of NOP by PMA + TNF-α. TNF-α and IL-1β attenuated PMA’s upregulating effects on ppNOC. None of the inhibitors preserved the upregulation of ppNOC in PMA + TNF-α and PMA + IL-1β cultures. TNF-α strongly mediated the nuclear translocation of NFκB/p65 in PMA-treated cells, while IL-1β did not. Proinflammatory cytokines suppressed NOP and ppNOC mRNA in PMA-induced human THP-1 cells. NFκB signaling seems to be an important regulator controlling the transcription of NOP. These findings suggest that the nociceptin system may play an anti-inflammatory role during immune responses. Full article

Integrating infrared and visible-light images facilitates a more comprehensive understanding of scenes by amalgamating dual-sensor data derived from identical environments. Traditional CNN-based fusion techniques are predominantly confined to local feature emphasis due to their inherently limited receptive fields. Conversely, Transformer-based models tend to prioritize global information, which can lead to a deficiency in feature diversity and detail retention. Furthermore, methods reliant on single-scale feature extraction are inadequate for capturing extensive scene information. To address these limitations, this study presents GLMAFuse, an innovative dual-stream encoder–decoder network, which utilizes a multi-scale attention mechanism to harmoniously integrate global and local features. This framework is designed to maximize the extraction of multi-scale features from source images while effectively synthesizing local and global information across all layers. We introduce the global-aware and local embedding (GALE) module to adeptly capture and merge global structural attributes and localized details from infrared and visible imagery via a parallel dual-branch architecture. Additionally, the multi-scale attention fusion (MSAF) module is engineered to optimize attention weights at the channel level, facilitating an enhanced synergy between high-frequency edge details and global backgrounds. This promotes effective interaction and fusion of dual-modal features. Extensive evaluations using standard datasets demonstrate that GLMAFuse surpasses the existing leading methods in both qualitative and quantitative assessments, highlighting its superior capability in infrared and visible image fusion. On the TNO and MSRS datasets, our method achieves outstanding performance across multiple metrics, including EN (7.15, 6.75), SD (46.72, 47.55), SF (12.79, 12.56), MI (2.21, 3.22), SCD (1.75, 1.80), VIF (0.79, 1.08), Qbaf (0.58, 0.71), and SSIM (0.99, 1.00). These results underscore its exceptional proficiency in infrared and visible image fusion. Full article

In tasks such as wood defect repair and the production of high-end wooden furniture, ensuring the consistency of the texture in repaired or jointed areas is crucial. This paper proposes the WTSM-SiameseNet model for wood-texture-similarity matching and introduces several improvements to address the issues present in traditional methods. First, to address the issue that fixed receptive fields cannot adapt to textures of different sizes, a multi-receptive field fusion feature extraction network was designed. This allows the model to autonomously select the optimal receptive field, enhancing its flexibility and accuracy when handling wood textures at different scales. Secondly, the interdependencies between layers in traditional serial attention mechanisms limit performance. To address this, a concurrent attention mechanism was designed, which reduces interlayer interference by using a dual-stream parallel structure that enhances the ability to capture features. Furthermore, to overcome the issues of existing feature fusion methods that disrupt spatial structure and lack interpretability, this study proposes a feature fusion method based on feature correlation. This approach not only preserves the spatial structure of texture features but also improves the interpretability and stability of the fused features and the model. Finally, by introducing depthwise separable convolutions, the issue of a large number of model parameters is addressed, significantly improving training efficiency while maintaining model performance. Experiments were conducted using a wood texture similarity dataset consisting of 7588 image pairs. The results show that WTSM-SiameseNet achieved an accuracy of 96.67% on the test set, representing a 12.91% improvement in accuracy and a 14.21% improvement in precision compared to the pre-improved SiameseNet. Compared to CS-SiameseNet, accuracy increased by 2.86%, and precision improved by 6.58%. Full article

In computer vision, accurately estimating a 3D human skeleton from a single RGB image remains a challenging task. Inspired by the advantages of multi-view approaches, we propose a method of predicting enhanced 2D skeletons (specifically, predicting the joints’ relative depths) from multiple virtual viewpoints based on a single real-view image. By fusing these virtual-viewpoint skeletons, we can then estimate the final 3D human skeleton more accurately. Our network consists of two stages. The first stage is composed of a two-stream network: the Real-Net stream predicts 2D image coordinates and the relative depth for each joint from the real viewpoint, while the Virtual-Net stream estimates the relative depths in virtual viewpoints for the same joints. Our network’s second stage consists of a depth-denoising module, a cropped-to-original coordinate transform (COCT) module, and a fusion module. The goal of the fusion module is to fuse skeleton information from the real and virtual viewpoints so that it can undergo feature embedding, 2D-to-3D lifting, and regression to an accurate 3D skeleton. The experimental results demonstrate that our single-view method can achieve a performance of 45.7 mm on average per-joint position error, which is superior to that achieved in several other prior studies of the same kind and is comparable to that of other sequence-based methods that accept tens of consecutive frames as the input. Full article

Recently, AI systems such as autonomous driving and smart homes have become integral to daily life. Intelligent multi-sensors, once limited to single data types, now process complex text and image data, demanding faster and more accurate processing. While integrating NPUs and sensors has improved processing speed and accuracy, challenges like low resource utilization and long memory latency remain. This study proposes a method to reduce processing time and improve resource utilization by virtualizing NPUs to simultaneously handle multiple deep-learning models, leveraging a hardware scheduler and data prefetching techniques. Experiments with 30,000 SA resources showed that the hardware scheduler reduced memory cycles by over 10% across all models, with reductions of 30% for NCF and 70% for DLRM. The hardware scheduler effectively minimized memory latency and idle NPU resources in resource-constrained environments with frequent context switching. This approach is particularly valuable for real-time applications like autonomous driving, enabling smooth transitions between tasks such as object detection and route planning. It also enhances multitasking in smart homes by reducing latency when managing diverse data streams. The proposed system is well suited for resource-constrained environments that demand efficient multitasking and low-latency processing. Full article

Generating accurate and contextually rich captions for images and videos is essential for various applications, from assistive technology to content recommendation. However, challenges such as maintaining temporal coherence in videos, reducing noise in large-scale datasets, and enabling real-time captioning remain significant. We introduce MIRA-CAP (Memory-Integrated Retrieval-Augmented Captioning), a novel framework designed to address these issues through three core innovations: a cross-modal memory bank, adaptive dataset pruning, and a streaming decoder. The cross-modal memory bank retrieves relevant context from prior frames, enhancing temporal consistency and narrative flow. The adaptive pruning mechanism filters noisy data, which improves alignment and generalization. The streaming decoder allows for real-time captioning by generating captions incrementally, without requiring access to the full video sequence. Evaluated across standard datasets like MS COCO, YouCook2, ActivityNet, and Flickr30k, MIRA-CAP achieves state-of-the-art results, with high scores on CIDEr, SPICE, and Polos metrics, underscoring its alignment with human judgment and its effectiveness in handling complex visual and temporal structures. This work demonstrates that MIRA-CAP offers a robust, scalable solution for both static and dynamic captioning tasks, advancing the capabilities of vision–language models in real-world applications. Full article

Chyulu Hills, Kenya, serves as one of the region’s water towers by supplying groundwater to surrounding streams and springs in southern Kenya. In a semiarid region, this water is crucial to the survival of local people, farms, and wildlife. The Chyulu Hills is also very prone to fires, and large areas of the range burn each year during the dry season. Currently, there are no detailed fire records or burn scar maps to track the burn history. Mapping burn scars using remote sensing is a cost-effective approach to monitor fire activity over time. However, it is not clear whether spectral burn indices developed elsewhere can be directly applied here when Chyulu Hills contains mostly grassland and bushland vegetation. Additionally, burn scars are usually no longer detectable after an intervening rainy season. In this study, we calculated the Differenced Normalized Burn Ratio (dNBR) and two versions of the Relative Differenced Normalized Burn Ratio (RdNBR) using Landsat Operational Land Imager (OLI) and Sentinel-2 MultiSpectral Instrument (MSI) data to determine which index, threshold values, instrument, and Sentinel near-infrared (NIR) band work best to map burn scars in Chyulu Hills, Kenya. The results indicate that the Relative Differenced Normalized Burn Ratio from Landsat OLI had the highest accuracy for mapping burn scars while also minimizing false positives (commission error). While mapping burn scars, it became clear that adjusting the threshold value for an index resulted in tradeoffs between false positives and false negatives. While none were perfect, this is an important consideration going forward. Given the length of the Landsat archive, there is potential to expand this work to additional years. Full article

This study aimed to develop an alternative surface hardening technique for low-carbon steel alloy type 20Ch using plasma electrolytic oxidation (PEO). The surface hardening of 20Ch alloy steel samples was achieved through PEO in a Na₂CO₃ electrolyte solution. Optimal processing parameters were determined experimentally by measuring voltage and applied current. Quenching was performed in the electrolyte stream, and plasma was ionised through excitation. A mathematical model based on thermal conductivity equations and regression analysis was developed to relate the key parameters of the hardening process. The results from both the experimental and mathematical models demonstrated that PEO significantly reduces hardening time compared to traditional methods. The microstructural images revealed the transformation of the coarse-grained pearlite–ferrite structure into quenched martensite. Vickers microhardness tests indicated a substantial increase in surface hardness after PEO treatment, compared to the untreated samples. The major advantages of PEO include lower energy consumption, high quenching rates, and the ability to perform localised surface treatments. These benefits contribute to overall cost reduction, making PEO a promising surface hardening method for various industrial applications. Full article

The concept of auditory scene analysis, popularized in scientific experiments by A. S. Bregman, the primary architect of the perceptual streaming theory, and his research team, along with more recent analyses by subsequent researchers, highlights a specific scientific gap that has not been thoroughly explored in previous studies. This article seeks to expand on this concept by introducing the author’s observation of the multivariant nature of auditory perception. This notion suggests that listeners focusing on different components of an auditory image (such as a musical piece) may perceive the same sounds but interpret them as distinct sound structures. Notably, even the same listener may perceive various structures (different mental figures) when re-listening to the same piece, depending on which musical elements they focus on. The thesis of multivariantism was examined and confirmed through the analysis of selected classical music pieces, providing concrete evidence of different interpretations of the same sound stimuli. To enhance clarity and understanding, the introduction to multivariantism was supplemented with graphic examples from the visual arts, which were then related to musical art through score excerpts from the works of composers such as C. Saint-Saëns, F. Liszt, and F. Mendelssohn Bartholdy. Full article

Background: Corn is the main grain crop grown in China, and the ear shape index of corn is an important parameter for breeding new varieties, including ear length, diameter, row number of ears, row number of grains per ear, and so on. Objective: In order to solve the problem of limited field of view associated with computer detection of the corn ear shape index against a complex background, this paper proposes a panoramic splicing method for corn ears against a complex background, which can splice 10 corn ear panoramic images at the same time, to improve information collection efficiency, display comprehensive information, and support data analysis, so as to realize automatic corn seed examination. Methods: A summary of corn ear panoramic stitching methods under complex backgrounds is presented as follows: 1. a perceptual hash algorithm and histogram equalization were used to extract video frames; 2. the U-Net image segmentation model based on transfer learning was used to predict corn labels; 3. a mask preprocessing algorithm was designed; 4. a corn ear splicing positioning algorithm was designed; 5. an algorithm for irregular surface expansion was designed; 6. an image stitching method based on template matching was adopted to assemble the video frames. Results: The experimental results showed that the proposed corn ear panoramic stitching method could effectively solve the problems of virtual stitching, obvious stitching seams, and too-high similarity between multiple images. The success rate of stitching was as high as 100%, and the speed of single-corn-ear panoramic stitching was about 9.4 s, indicating important reference value for corn breeding and disease and insect detection. Discussions: Although the experimental results demonstrated the significant advantages of the panoramic splicing method for corn ear images proposed in this paper in terms of improving information collection efficiency and automating corn assessment, the method still faces certain challenges. Future research will focus on the following points: 1. addressing the issue of environmental interference caused by diseases, pests, and plant nutritional status on the measurement of corn ear parameters in order to enhance the stability and accuracy of the algorithm; 2. expanding the dataset for the U-Net model to include a wider range of corn ears with complex backgrounds, different growth stages, and various environmental conditions to improve the model’s segmentation recognition rate and precision. Recently, our panoramic splicing algorithm has been deployed in practical applications with satisfactory results. We plan to continue optimizing the algorithm and more broadly promote its use in fields such as corn breeding and pest and disease detection in an effort to advance the development of agricultural automation technology. Full article

Advancements in deep learning and infrared sensors have facilitated the integration of RGB-thermal (RGBT) tracking technology in computer vision. However, contemporary RGBT tracking methods handle complex image data, resulting in inference procedures with a large number of floating-point operations and parameters, which limits their performance on general-purpose processors. We present a lightweight Siamese dual-stream infrared-enhanced RGBT tracking algorithm, called DuSiamIE.It is implemented on the low-power NVIDIA Jetson Nano to assess its practicality for edge-device applications in resource-limited settings. Our algorithm replaces the conventional backbone network with a modified MobileNetV3 and incorporates light-aware and infrared feature enhancement modules to extract and integrate multimodal information. Finally, NVIDIA TensorRT is used to improve the inference speed of the algorithm on edge devices. We validated our algorithm on two public RGBT tracking datasets. On the GTOT dataset, DuSiamIE achieved a precision (PR) of 83.4% and a success rate (SR) of 66.8%, with a tracking speed of 40.3 frames per second (FPS). On the RGBT234 dataset, the algorithm achieved a PR of 75.3% and an SR of 52.6%, with a tracking speed of 34.7 FPS. Compared with other algorithms, DuSiamIE exhibits a slight loss in accuracy but significantly outperforms them in speed on resource-constrained edge devices. It is the only algorithm among those tested that can perform real-time tracking on such devices. Full article

To address the vulnerability of existing hiding algorithms to differential attacks and the limitations of single chaotic systems, such as small key space and low security, a novel algorithm combining audio encryption with information hiding is proposed. First, the original audio is divided into blocks to enhance efficiency. A “one-time pad” mechanism is achieved by associating the key with the plaintext, and a new multidimensional sine-coupled chaotic map is designed, which, in conjunction with multiple chaotic systems, generates the key stream. Next, the block-processed audio signals are matrix-converted and then encrypted using cyclic remainder scrambling, an improved Josephus scrambling, XOR diffusion, and bit diffusion. This results in an encrypted audio information matrix. Finally, the GHM multiwavelet transform is used to select embedding channels, and the least significant bit (LSB) method is employed to hide the information within the carrier image. The algorithm is symmetric, and decryption involves simply reversing the encryption process on the stego image. Experimental results demonstrate that the Structural Similarity Index (SSIM) between the carrier image and the stego image is 0.992540, the Peak Signal-to-Noise Ratio (PSNR) is 49.659404 dB, and the Mean Squared Error (MSE) is 0.708044. These metrics indicate high statistical similarity and indistinguishability in visual appearance. The key space of the encryption algorithm is approximately 2⁸⁵⁰, which effectively resists brute-force attacks. The energy distribution of the encrypted audio approximates noise, with information entropy close to 8, uniform histograms, high scrambling degree, strong resistance to differential attacks, and robustness against noise and cropping attacks. Full article