Style-Enhanced Transformer for Image Captioning in Construction Scenes.

Image captioning is important for improving the intelligence of construction projects and assisting managers in mastering construction site activities. However, there are few image-captioning models for construction scenes at present, and the existing methods do not perform well in complex construction scenes. According to the characteristics of construction scenes, we label a text description dataset based on the MOCS dataset and propose a style-enhanced Transformer for image captioning in construction scenes, simply called SETCAP. Specifically, we extract the grid features using the Swin Transformer. Then, to enhance the style information, we not only use the grid features as the initial detail semantic features but also extract style information by style encoder. In addition, in the decoder, we integrate the style information into the text features. The interaction between the image semantic information and the text features is carried out to generate content-appropriate sentences word by word. Finally, we add the sentence style loss into the total loss function to make the style of generated sentences closer to the training set. The experimental results show that the proposed method achieves encouraging results on both the MSCOCO and the MOCS datasets. In particular, SETCAP outperforms state-of-the-art methods by 4.2% CIDEr scores on the MOCS dataset and 3.9% CIDEr scores on the MSCOCO dataset, respectively.

Endoscopic combined intrarenal surgery composed of micro-perc and retrograde intrarenal surgery in the treatment of complex kidney stones in children.

OBJECTIVE: This research aims to explore the efficiency and safety of endoscopic combined intrarenal surgery (Micro-ECIRS) composed of micro-percutaneous nephrolithotomy (Micro-perc) and retrograde intrarenal surgery (RIRS) in the Galdakao-modified supine Valdivia (GMSV) position for a single session for the treatment of complex nephrolithiasis in children. MATERIALS AND METHODS: This study retrospectively reviewed patients aged < 18 years who underwent Micro-ECIRS in the GMSV position for renal stones larger than 2 cm under ultrasound guidance between August 2020 to May 2022 at our institution. RESULTS: A total of 13 patients (8 males and 5 females) received Micro-ECIRS for renal stones under ultrasound guidancewhile adopting the GMSV position. The average stone size was 2.7 cm (range: 2.1-3.7 cm). Among them, 6 patients had left kidney stones, 5 patients had right kidney stones, and 2 patients had bilateral kidney stones. The mean operative time was 70.5 min (range: 54-93 min). The mean hospital stay was 6.4 days (range: 4-9 days). The mean hemoglobin decrease was 8.2 g/L (range: 5.1-12.4 g/L). The total number of kidneys that had complete stone clearance was 8 kidneys at 48 h postoperatively, 11 kidneys at 2 weeks postoperatively, and 14 kidneys at 1 month postoperatively. CONCLUSION: Our results demonstrate that Micro-ECIRS while patients are in the GMSV position is a safe and effective method for the treatment of complex children nephrolithiasis. However, all children made three hospital visits and received anesthesia three times. Further research is needed to confirm these findings.

Corrigendum: Accurate few-shot object counting with Hough matching feature enhancement.

[This corrects the article DOI: 10.3389/fncom.2023.1145219.].

Corrigendum: An initial prediction and fine-tuning model based on improving GCN for 3D human motion prediction.

[This corrects the article DOI: 10.3389/fncom.2023.1145209.].

Accurate few-shot object counting with Hough matching feature enhancement.

Introduction: Given some exemplars, few-shot object counting aims to count the corresponding class objects in query images. However, when there are many target objects or background interference in the query image, some target objects may have occlusion and overlap, which causes a decrease in counting accuracy. Methods: To overcome the problem, we propose a novel Hough matching feature enhancement network. First, we extract the image feature with a fixed convolutional network and refine it through local self-attention. And we design an exemplar feature aggregation module to enhance the commonality of the exemplar feature. Then, we build a Hough space to vote for candidate object regions. The Hough matching outputs reliable similarity maps between exemplars and the query image. Finally, we augment the query feature with exemplar features according to the similarity maps, and we use a cascade structure to further enhance the query feature. Results: Experiment results on FSC-147 show that our network performs best compared to the existing methods, and the mean absolute counting error on the test set improves from 14.32 to 12.74. Discussion: Ablation experiments demonstrate that Hough matching helps to achieve more accurate counting compared with previous matching methods.

Unilateral Suprainguinal Ectopic Scrotum: Case Report and Literature Review.

Ectopic scrotum is an infrequent congenital scrotal anomaly. Different surgical methods of correcting ectopic scrotum have been used, but none have produced optimal cosmetic results for all types. We describe a case of left ectopic suprainguinal scrotum in a 14-month-old boy who had an undescended left testicle and a left-sided scrotal skin tag. Single-stage rotational flap scrotoplasty and unilateral orchiopexy were performed; however, we modified the surgical technique of scrotal rotation by excising the intervening longitudinal skin. Eight months after surgery, the repositioned scrotum had a better appearance, and the affected testicle was similar in size to the contralateral one. In comparison with other surgical methods, pedicle flap rotation of the ectopic scrotal skin with excision of the intervening longitudinal skin may produce a better cosmetic outcome.

An initial prediction and fine-tuning model based on improving GCN for 3D human motion prediction.

Human motion prediction is one of the fundamental studies of computer vision. Much work based on deep learning has shown impressive performance for it in recent years. However, long-term prediction and human skeletal deformation are still challenging tasks for human motion prediction. For accurate prediction, this paper proposes a GCN-based two-stage prediction method. We train a prediction model in the first stage. Using multiple cascaded spatial attention graph convolution layers (SAGCL) to extract features, the prediction model generates an initial motion sequence of future actions based on the observed pose. Since the initial pose generated in the first stage often deviates from natural human body motion, such as a motion sequence in which the length of a bone is changed. So the task of the second stage is to fine-tune the predicted pose and make it closer to natural motion. We present a fine-tuning model including multiple cascaded causally temporal-graph convolution layers (CT-GCL). We apply the spatial coordinate error of joints and bone length error as loss functions to train the fine-tuning model. We validate our model on Human3.6m and CMU-MoCap datasets. Extensive experiments show that the two-stage prediction method outperforms state-of-the-art methods. The limitations of proposed methods are discussed as well, hoping to make a breakthrough in future exploration.

Single-center experience of micro-perc in the treatment of children with 1.0-2.0 cm sized kidney stones in the Galdakao-modified supine Valdivia position.

OBJECTIVE: We aimed to explore the applicability and safety of micro-percutaneous nephrolithotomy (micro-perc) in the treatment of children with kidney stones in the Galdakao-modified supine Valdivia (GMSV) position under the guidance of whole-course ultrasound. MATERIALS AND METHODS: Patients were aged < 18 years in the GMSV position who underwent micro-perc for kidney stones under ultrasound guidance between August 2020 and May 2022 at our institution were reviewed retrospectively. RESULTS: A total of 23 patients, 15 males and 8 females, received micro-perc. The average stone size was 1.6 cm (range 1.1-2.0 cm). Among them, 12 patients had left kidney stones, 10 patients had right kidney stones, and 1 patient had bilateral kidney stones. The mean operative time was 55.3 min (range 35-86 min). The mean hospital stay was 2.9 days (range 2-4 days). The mean hemoglobin decrease was 1.7 g/L (range 0.9-3.2 g/L). A total of 17 patients had complete stone clearance at 48 h postoperatively. A total of 22 patients had complete stone clearance at 2 weeks postoperatively. CONCLUSION: Our results demonstrate that micro-perc under ultrasound guidance is a safe and effective method for the treatment of children with kidney stones in the GMSV position. Further research is warranted to confirm these results.

Structural Smoothing Low-Rank Matrix Restoration Based on Sparse Coding and Dual-Weighted Model.

Group sparse coding (GSC) uses the non-local similarity of images as constraints, which can fully exploit the structure and group sparse features of images. However, it only imposes the sparsity on the group coefficients, which limits the effectiveness of reconstructing real images. Low-rank regularized group sparse coding (LR-GSC) reduces this gap by imposing low-rankness on the group sparse coefficients. However, due to the use of non-local similarity, the edges and details of the images are over-smoothed, resulting in the blocking artifact of the images. In this paper, we propose a low-rank matrix restoration model based on sparse coding and dual weighting. In addition, total variation (TV) regularization is integrated into the proposed model to maintain local structure smoothness and edge features. Finally, to solve the problem of the proposed optimization, an optimization method is developed based on the alternating direction method. Extensive experimental results show that the proposed SDWLR-GSC algorithm outperforms state-of-the-art algorithms for image restoration when the images have large and sparse noise, such as salt and pepper noise.

Deep Matrix Factorization Based on Convolutional Neural Networks for Image Inpainting.

In this work, we formulate the image in-painting as a matrix completion problem. Traditional matrix completion methods are generally based on linear models, assuming that the matrix is low rank. When the original matrix is large scale and the observed elements are few, they will easily lead to over-fitting and their performance will also decrease significantly. Recently, researchers have tried to apply deep learning and nonlinear techniques to solve matrix completion. However, most of the existing deep learning-based methods restore each column or row of the matrix independently, which loses the global structure information of the matrix and therefore does not achieve the expected results in the image in-painting. In this paper, we propose a deep matrix factorization completion network (DMFCNet) for image in-painting by combining deep learning and a traditional matrix completion model. The main idea of DMFCNet is to map iterative updates of variables from a traditional matrix completion model into a fixed depth neural network. The potential relationships between observed matrix data are learned in a trainable end-to-end manner, which leads to a high-performance and easy-to-deploy nonlinear solution. Experimental results show that DMFCNet can provide higher matrix completion accuracy than the state-of-the-art matrix completion methods in a shorter running time.

Removing Adversarial Noise via Low-Rank Completion of High-Sensitivity Points.

Deep neural networks are fragile under adversarial attacks. In this work, we propose to develop a new defense method based on image restoration to remove adversarial attack noise. Using the gradient information back-propagated over the network to the input image, we identify high-sensitivity keypoints which have significant contributions to the image classification performance. We then partition the image pixels into the two groups: high-sensitivity and low-sensitivity points. For low-sensitivity pixels, we use a total variation (TV) norm-based image smoothing method to remove adversarial attack noise. For those high-sensitivity keypoints, we develop a structure-preserving low-rank image completion method. Based on matrix analysis and optimization, we derive an iterative solution for this optimization problem. Our extensive experimental results on the CIFAR-10, SVHN, and Tiny-ImageNet datasets have demonstrated that our method significantly outperforms other defense methods which are based on image de-noising or restoration, especially under powerful adversarial attacks.

Renal malignant tumor with the loss of INI1 expression and WT1 positive in a 3-year-old boy: a case report.

Wilms' tumor is the most common primary renal malignancy in children (80%) and the less common tumors include renal cell carcinoma, rhabdoid tumor, clear cell sarcoma, cellular congenital mesoblastic nephroma and medullary carcinoma, all of which originate from renal parenchyma. The tumors originating from renal pelvis are rare. The immunohistochemistry (IHC) showed INI1 deletion with the WT1 positive which has not been reported as we know. A 3-year-old boy was admitted to hospital for vomiting. An ultrasonography examination revealed a mass in the right kidney, medium echo, as well as hydronephrosis with collecting system separation of 3.5 cm. The computed tomography and the magnetic resonance (MR) radical showed that the tumor occupied the right renal pelvis and extended into the ureter. A radical nephroureterectomy was accomplished through a transabdominal approach. The pathologic diagnosis was malignant renal tumor with INI1 deficiency which was atypical in morphology and immunophenotype, but according to immunophenotype renal rhabdomyoid tumor could not be excluded. The patient was treated with carboplatin, etoposide and cyclophosphamide chemotherapy for 6 months. Follow-up studies of the patient showed no indication of recurrence or metastasis 22 months after nephrectomy. The novel findings may expand the spectrum of pediatric renal tumors to include the special malignancy.

Reweighted Low-Rank Matrix Analysis With Structural Smoothness for Image Denoising.

In this paper, we develop a new low-rank matrix recovery algorithm for image denoising. We incorporate the total variation (TV) norm and the pixel range constraint into the existing reweighted low-rank matrix analysis to achieve structural smoothness and to significantly improve quality in the recovered image. Our proposed mathematical formulation of the low-rank matrix recovery problem combines the nuclear norm, TV norm, and norm, thereby allowing us to exploit the low-rank property of natural images, enhance the structural smoothness, and detect and remove large sparse noise. Using the iterative alternating direction and fast gradient projection methods, we develop an algorithm to solve the proposed challenging non-convex optimization problem. We conduct extensive performance evaluations on single-image denoising, hyper-spectral image denoising, and video background modeling from corrupted images. Our experimental results demonstrate that the proposed method outperforms the state-of-the-art low-rank matrix recovery methods, particularly for large random noise. For example, when the density of random sparse noise is 30%, for single-image denoising, our proposed method is able to improve the quality of the restored image by up to 4.21 dB over existing methods.