LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 14

Search options

  1. Article ; Online: Style-Enhanced Transformer for Image Captioning in Construction Scenes.

    Song, Kani / Chen, Linlin / Wang, Hengyou

    Entropy (Basel, Switzerland)

    2024  Volume 26, Issue 3

    Abstract: 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 ... ...

    Abstract 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.
    Language English
    Publishing date 2024-03-01
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2014734-X
    ISSN 1099-4300 ; 1099-4300
    ISSN (online) 1099-4300
    ISSN 1099-4300
    DOI 10.3390/e26030224
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  2. Article ; Online: Structural Smoothing Low-Rank Matrix Restoration Based on Sparse Coding and Dual-Weighted Model.

    Wu, Jiawei / Wang, Hengyou

    Entropy (Basel, Switzerland)

    2022  Volume 24, Issue 7

    Abstract: 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 ... ...

    Abstract 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.
    Language English
    Publishing date 2022-07-07
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2014734-X
    ISSN 1099-4300 ; 1099-4300
    ISSN (online) 1099-4300
    ISSN 1099-4300
    DOI 10.3390/e24070946
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

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

    He, Zhiquan / Zheng, Donghong / Wang, Hengyou

    Frontiers in computational neuroscience

    2023  Volume 17, Page(s) 1145219

    Abstract: 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 ...

    Abstract 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.
    Language English
    Publishing date 2023-03-30
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2452964-3
    ISSN 1662-5188
    ISSN 1662-5188
    DOI 10.3389/fncom.2023.1145219
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

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

    He, Zhiquan / Zhang, Lujun / Wang, Hengyou

    Frontiers in computational neuroscience

    2023  Volume 17, Page(s) 1232765

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

    Abstract [This corrects the article DOI: 10.3389/fncom.2023.1145209.].
    Language English
    Publishing date 2023-06-13
    Publishing country Switzerland
    Document type Published Erratum
    ZDB-ID 2452964-3
    ISSN 1662-5188
    ISSN 1662-5188
    DOI 10.3389/fncom.2023.1232765
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

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

    He, Zhiquan / Zheng, Donghong / Wang, Hengyou

    Frontiers in computational neuroscience

    2023  Volume 17, Page(s) 1232762

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

    Abstract [This corrects the article DOI: 10.3389/fncom.2023.1145219.].
    Language English
    Publishing date 2023-06-20
    Publishing country Switzerland
    Document type Published Erratum
    ZDB-ID 2452964-3
    ISSN 1662-5188
    ISSN 1662-5188
    DOI 10.3389/fncom.2023.1232762
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

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

    He, Zhiquan / Zhang, Lujun / Wang, Hengyou

    Frontiers in computational neuroscience

    2023  Volume 17, Page(s) 1145209

    Abstract: 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 ... ...

    Abstract 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.
    Language English
    Publishing date 2023-04-05
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2452964-3
    ISSN 1662-5188
    ISSN 1662-5188
    DOI 10.3389/fncom.2023.1145209
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  7. Article ; Online: Unilateral Suprainguinal Ectopic Scrotum: Case Report and Literature Review.

    Wang, Hengyou / Tang, Daxing / Yan, Xiang

    Urologia internationalis

    2023  Volume 107, Issue 5, Page(s) 539–542

    Abstract: 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 ... ...

    Abstract 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.
    MeSH term(s) Male ; Humans ; Infant ; Scrotum/surgery ; Scrotum/abnormalities ; Plastic Surgery Procedures ; Surgical Flaps ; Cryptorchidism/surgery
    Language English
    Publishing date 2023-04-04
    Publishing country Switzerland
    Document type Review ; Case Reports
    ZDB-ID 204045-1
    ISSN 1423-0399 ; 0042-1138
    ISSN (online) 1423-0399
    ISSN 0042-1138
    DOI 10.1159/000529809
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  8. Article ; Online: Deep Matrix Factorization Based on Convolutional Neural Networks for Image Inpainting.

    Ma, Xiaoxuan / Li, Zhiwen / Wang, Hengyou

    Entropy (Basel, Switzerland)

    2022  Volume 24, Issue 10

    Abstract: 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 ... ...

    Abstract 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.
    Language English
    Publishing date 2022-10-20
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2014734-X
    ISSN 1099-4300 ; 1099-4300
    ISSN (online) 1099-4300
    ISSN 1099-4300
    DOI 10.3390/e24101500
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  9. Article ; Online: Endoscopic combined intrarenal surgery composed of micro-perc and retrograde intrarenal surgery in the treatment of complex kidney stones in children.

    Xu, Zi-Hao / Du, Geng-Yu / Zhao, Yi-Jun / Wang, Heng-You / Chen, Guang-Jie / Tao, Chang / Yan, Xiang

    World journal of urology

    2024  Volume 42, Issue 1, Page(s) 21

    Abstract: 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 ... ...

    Abstract 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.
    MeSH term(s) Child ; Female ; Male ; Humans ; Retrospective Studies ; Kidney Calculi/diagnostic imaging ; Kidney Calculi/surgery ; Kidney/diagnostic imaging ; Kidney/surgery ; Nephrolithotomy, Percutaneous ; Anesthesiology
    Language English
    Publishing date 2024-01-10
    Publishing country Germany
    Document type Journal Article
    ZDB-ID 380333-8
    ISSN 1433-8726 ; 0724-4983
    ISSN (online) 1433-8726
    ISSN 0724-4983
    DOI 10.1007/s00345-023-04695-3
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  10. Article ; Online: 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.

    Xu, Zi-Hao / Du, Geng-Yu / Zhao, Yi-Jun / Wang, Heng-You / Chen, Guang-Jie / Tao, Chang / Yan, Xiang

    World journal of urology

    2023  Volume 41, Issue 3, Page(s) 837–841

    Abstract: 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 ... ...

    Abstract 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.
    MeSH term(s) Male ; Female ; Humans ; Child ; Retrospective Studies ; Nephrostomy, Percutaneous/methods ; Kidney Calculi/diagnostic imaging ; Kidney Calculi/surgery ; Kidney/surgery ; Nephrolithotomy, Percutaneous/methods ; Supine Position ; Treatment Outcome
    Language English
    Publishing date 2023-02-07
    Publishing country Germany
    Document type Journal Article
    ZDB-ID 380333-8
    ISSN 1433-8726 ; 0724-4983
    ISSN (online) 1433-8726
    ISSN 0724-4983
    DOI 10.1007/s00345-023-04289-z
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

To top