NSTL国家科技图书文献中心

1. Computer graphics and image processing techniques based on visual communication design NSTL国家科技图书文献中心

Zhaoguo Chen - 《Fourth International Conference on Computer Vision,Application,and Algorithm (CVAA 2024)》 - International Conference on Computer Vision,Application,and Algorithm - 2025, - 134860F.1～134860F.5 - 共5页

摘要： graphics and image* processing technologies and elevate* | , the implementation of advanced design image | of visual communication image* representation. The* | feasibility, effectively boosting image* recognition accuracy* | across four distinct image* categories with varying*

关键词： Visual communication design | Computer | Graphic image processing

2. Optimizing Image Quality and Reliability Through Chunking Fusion and Wavelet Transform NSTL国家科技图书文献中心

Hu, Jiachong - 《Mapan》 - 2025,40(1) - 43～58 - 共16页

摘要： modern graphic* image processing techniques have the* | proposed image* processing system has been widely adopted* | and image* technology on the development of visual* | critical role of computer graphics and image* technology* | The study of visual communication and its role

关键词： Communication process | Computer graphics | Graphic design | Image processing | Internet of things | Communication design

3. Low-light few-shot object detection via curve contrast enhancement and flow-encoder-based variational autoencoder NSTL国家科技图书文献中心

Zetao,Jiang | Xin,Jin ... - 《Neural computing & applications》 - 2025,37(10) - 7261～7278 - 共18页

摘要： the enhanced image* and the low-light image through* | pixel values of the enhanced image. Moreover, we | Aiming at the problem of insufficient samples | in low-light object detection in some environments | , a low-light few-shot object detection method based

关键词： Low-light environment | Few-shot object detection | Curve contrast enhancement | Flow-encoder-based variational autoencoder

4. Deepfake Video Detection Using Facial Feature Points and Ch-Transformer NSTL国家科技图书文献中心

RUI YANG | RUSHI LAN ... - 《ACM transactions on multimedia computing communications and applications》 - 2025,21(2) - 49.1～49.22 - 共22页

摘要：With the development of Metaverse technology | , the avatar in Metaverse has faced serious security | and privacy concerns. Analyzing facial features to | distinguish between genuine and manipulated facial videos | holds significant research importance for ensuring the

关键词： Transformer | deepfake detection | facial feature | FFP-ChT | facial feature points

5. Perceptual Information Fidelity for Quality Estimation of Industrial Images NSTL国家科技图书文献中心

Ke Gu | Hongyan Liu ... - 《IEEE Transactions on Circuits and Systems for Video Technology》 - 2025,35(1) - 477～491 - 共15页

摘要：., causing existing image* processing methods for quality* | processing and assembly automation, which play a highly | , more regular shapes, massive graphic* elements, etc* | an industrial image, so in the researches of image | based image* quality estimation model, abbreviated as*

关键词： Image quality | Estimation | Optical imaging | Optical distortion | Optical noise | Brain modeling | Noise

6. Enhanced Spatial Adaptive Fusion Network For Video Super-Resolution NSTL国家科技图书文献中心

Boyue Li | Xin Zhao ... - 《Pattern Recognition and Computer Vision,Part VI》 - Chinese Conference on Pattern Recognition and Computer Vision - 2025, - 491～505 - 共15页

摘要：In the field of Video Super-Resolution (VSR | ), recurrent structures are frequently used in the designed | network architectures, yet they face significant | challenges in effective information transmission and | accurate alignment. To address this issue, this study

关键词： Recurrent structures | Spatially adaptive | Implicit alignment

7. Residual Hybrid Attention Enhanced Video Super-Resolution with Cross Convolution NSTL国家科技图书文献中心

Shiqian Yuan | Boyue Li ... - 《Pattern Recognition and Computer Vision,Part VI》 - Chinese Conference on Pattern Recognition and Computer Vision - 2025, - 535～549 - 共15页

摘要： processing of vertical and horizontal gradient information | In video super-resolution reconstruction | , traditional methods often fall short in capturing details | , particularly in edges and occluded areas, which affects the | realism and clarity of the images. To address this issue

关键词： Video super-resolution | Hybrid attention | Cross convolution

8. Real-Time Detection Transformer with Bi-Level Routing Attention NSTL国家科技图书文献中心

Xin Zhao | Shiqian Yuan ... - 《Pattern Recognition and Computer Vision,Part IV》 - Chinese Conference on Pattern Recognition and Computer Vision - 2025, - 312～325 - 共14页

摘要：In recent years, DEtection TRansformer (DETR | ) has achieved remarkable performance for traffic | monitoring. However, due to the typically high | computational complexity of transformers, DETR encounters | performance bottlenecks in resource-constrained scenarios

关键词： Road traffic | End-to-End object detect | Transformer

9. Enhancing small parcel sorting accuracy: Robot machine vision in stacking target image experiment NSTL国家科技图书文献中心

Mu, Longtao | Quan, Chao ... - 《Journal of computational methods in sciences and engineering》 - 2025,25(1) - 146～159 - 共14页

摘要： processing time of 0.12 seconds per image. The successful | completes sorting actions through parcel graphic | As robots are increasingly being used in | various fields of production and daily life, research in | this area has become a hot topic among researchers

关键词： robotic | artificial intelligence | object recognition | deep learning | automation

10. Improved Faster Region-based Convolutional Neural Network in graphic recognition and retrieval NSTL国家科技图书文献中心

Song, Xu | Zhou, Hongyu - 《Journal of computational methods in sciences and engineering》 - 2025,25(2) - 1341～1353 - 共13页

摘要： image processing tasks. | image in the complex environment and to improve the | accuracy of the model. Finally, the object in the image | in the model, and the graphic* recognition and* | development of the image* retrieval module enables semantic*

摘要： graphics and image* processing technologies and elevate* | , the implementation of advanced design image | of visual communication image* representation. The* | feasibility, effectively boosting image* recognition accuracy* | across four distinct image* categories with varying*

关键词： Visual communication design | Computer | Graphic image processing

摘要： modern graphic* image processing techniques have the* | proposed image* processing system has been widely adopted* | and image* technology on the development of visual* | critical role of computer graphics and image* technology* | The study of visual communication and its role

关键词： Communication process | Computer graphics | Graphic design | Image processing | Internet of things | Communication design

摘要： the enhanced image* and the low-light image through* | pixel values of the enhanced image. Moreover, we | Aiming at the problem of insufficient samples | in low-light object detection in some environments | , a low-light few-shot object detection method based

关键词： Low-light environment | Few-shot object detection | Curve contrast enhancement | Flow-encoder-based variational autoencoder

摘要：With the development of Metaverse technology | , the avatar in Metaverse has faced serious security | and privacy concerns. Analyzing facial features to | distinguish between genuine and manipulated facial videos | holds significant research importance for ensuring the

关键词： Transformer | deepfake detection | facial feature | FFP-ChT | facial feature points

摘要：., causing existing image* processing methods for quality* | processing and assembly automation, which play a highly | , more regular shapes, massive graphic* elements, etc* | an industrial image, so in the researches of image | based image* quality estimation model, abbreviated as*

关键词： Image quality | Estimation | Optical imaging | Optical distortion | Optical noise | Brain modeling | Noise

摘要：In the field of Video Super-Resolution (VSR | ), recurrent structures are frequently used in the designed | network architectures, yet they face significant | challenges in effective information transmission and | accurate alignment. To address this issue, this study

关键词： Recurrent structures | Spatially adaptive | Implicit alignment

摘要： processing of vertical and horizontal gradient information | In video super-resolution reconstruction | , traditional methods often fall short in capturing details | , particularly in edges and occluded areas, which affects the | realism and clarity of the images. To address this issue

关键词： Video super-resolution | Hybrid attention | Cross convolution

摘要：In recent years, DEtection TRansformer (DETR | ) has achieved remarkable performance for traffic | monitoring. However, due to the typically high | computational complexity of transformers, DETR encounters | performance bottlenecks in resource-constrained scenarios

关键词： Road traffic | End-to-End object detect | Transformer

摘要： processing time of 0.12 seconds per image. The successful | completes sorting actions through parcel graphic | As robots are increasingly being used in | various fields of production and daily life, research in | this area has become a hot topic among researchers

关键词： robotic | artificial intelligence | object recognition | deep learning | automation

摘要： image processing tasks. | image in the complex environment and to improve the | accuracy of the model. Finally, the object in the image | in the model, and the graphic* recognition and* | development of the image* retrieval module enables semantic*

关键词： Faster R-CNN | region of interest pooling layer | Softmax classifier | gradient descent algorithm | R-CNN | IDENTIFICATION

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： graphics and image processing technologies and elevate | , the implementation of advanced design image | of visual communication image representation. The | feasibility, effectively boosting image recognition accuracy | across four distinct image categories with varying

关键词： Visual communication design | Computer | Graphic image processing

摘要： modern graphic image processing techniques have the | proposed image processing system has been widely adopted | and image technology on the development of visual | critical role of computer graphics and image technology | The study of visual communication and its role

关键词： Communication process | Computer graphics | Graphic design | Image processing | Internet of things | Communication design

摘要： the enhanced image and the low-light image through | pixel values of the enhanced image. Moreover, we | Aiming at the problem of insufficient samples | in low-light object detection in some environments | , a low-light few-shot object detection method based

关键词： Low-light environment | Few-shot object detection | Curve contrast enhancement | Flow-encoder-based variational autoencoder

摘要：With the development of Metaverse technology | , the avatar in Metaverse has faced serious security | and privacy concerns. Analyzing facial features to | distinguish between genuine and manipulated facial videos | holds significant research importance for ensuring the

关键词： Transformer | deepfake detection | facial feature | FFP-ChT | facial feature points

摘要：., causing existing image processing methods for quality | processing and assembly automation, which play a highly | , more regular shapes, massive graphic elements, etc | an industrial image, so in the researches of image | based image quality estimation model, abbreviated as

关键词： Image quality | Estimation | Optical imaging | Optical distortion | Optical noise | Brain modeling | Noise

摘要：In the field of Video Super-Resolution (VSR | ), recurrent structures are frequently used in the designed | network architectures, yet they face significant | challenges in effective information transmission and | accurate alignment. To address this issue, this study

关键词： Recurrent structures | Spatially adaptive | Implicit alignment

摘要： processing of vertical and horizontal gradient information | In video super-resolution reconstruction | , traditional methods often fall short in capturing details | , particularly in edges and occluded areas, which affects the | realism and clarity of the images. To address this issue

关键词： Video super-resolution | Hybrid attention | Cross convolution

摘要：In recent years, DEtection TRansformer (DETR | ) has achieved remarkable performance for traffic | monitoring. However, due to the typically high | computational complexity of transformers, DETR encounters | performance bottlenecks in resource-constrained scenarios

关键词： Road traffic | End-to-End object detect | Transformer

摘要： processing time of 0.12 seconds per image. The successful | completes sorting actions through parcel graphic | As robots are increasingly being used in | various fields of production and daily life, research in | this area has become a hot topic among researchers

关键词： robotic | artificial intelligence | object recognition | deep learning | automation

摘要： image processing tasks. | image in the complex environment and to improve the | accuracy of the model. Finally, the object in the image | in the model, and the graphic recognition and | development of the image retrieval module enables semantic

关键词： Faster R-CNN | region of interest pooling layer | Softmax classifier | gradient descent algorithm | R-CNN | IDENTIFICATION

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： graphics and image* processing technologies and elevate* | , the implementation of advanced design image | of visual communication image* representation. The* | feasibility, effectively boosting image* recognition accuracy* | across four distinct image* categories with varying*

摘要： modern graphic* image processing techniques have the* | proposed image* processing system has been widely adopted* | and image* technology on the development of visual* | critical role of computer graphics and image* technology* | The study of visual communication and its role

摘要： the enhanced image* and the low-light image through* | pixel values of the enhanced image. Moreover, we | Aiming at the problem of insufficient samples | in low-light object detection in some environments | , a low-light few-shot object detection method based

摘要：., causing existing image* processing methods for quality* | processing and assembly automation, which play a highly | , more regular shapes, massive graphic* elements, etc* | an industrial image, so in the researches of image | based image* quality estimation model, abbreviated as*

摘要： image processing tasks. | image in the complex environment and to improve the | accuracy of the model. Finally, the object in the image | in the model, and the graphic* recognition and* | development of the image* retrieval module enables semantic*