NSTL国家科技图书文献中心

1. Unsupervised, Online and On-The-Fly Anomaly Detection for Non-stationary Image Distributions NSTL国家科技图书文献中心

Declan McIntosh | Alexandra Branzan Al... - 《Computer Vision - ECCV 2024,Part LXI》 - European Conference on Computer Vision - 2025, - 428～445 - 共18页

摘要：We propose Online-InReaCh, the first fully unsupervised online method for detecting and localizing anomalies on-the-fly in image sequences while following non-stationary distributions. Previous anomal...

关键词： Anomaly detection | Unsupervised | Online

2. Attribute-based document image retrieval NSTL国家科技图书文献中心

Melissa Cote | Alexandra Branzan Al... - 《International journal on document analysis and recognition》 - 2024,27(1) - 57～71 - 共15页 - 被引量：1

摘要：This paper explores the use of attributes for document image querying and retrieval. Existing document image retrieval techniques present several drawbacks: textual searches are limited to text, query...

关键词： Document image retrieval | Document querying | Visual attributes | Convolutional neural networks | Document classification

3. Single-Class Instance Segmentation for Vectorization of Line Drawings NSTL国家科技图书文献中心

Rhythm Vohra | Amanda Dash ... - 《19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications,[v.3].VISAPP》 - International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - 2024, - 215～226 - 共12页

摘要：Images can be represented and stored either in raster or in vector formats. Raster images are most ubiquitous and are defined as matrices of pixel intensities/colours, while vector images consist of a...

关键词： Segmentation | Visual attention | Image vectorization

4. Deep Learning-Based Identification of Arctic Ocean Boundaries and Near-Surface Phenomena in Underwater Echograms NSTL国家科技图书文献中心

Femina Senjaliya | Melissa Cote ... - 《2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops》 - IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops - 2024, - 2977～2986 - 共10页

摘要：Monitoring marine environments is a crucial part of understanding the impact of oceans on global climate and their importance for biodiversity and ecological systems, particularly in the Arctic region...

关键词： Surveys | Sea surface | Analytical models | Biological system modeling | Semantic segmentation | Arctic | Surface treatment

5. Inter-Realization Channels: Unsupervised Anomaly Detection Beyond One-Class Classification NSTL国家科技图书文献中心

Declan McIntosh | Alexandra Branzan Al... - 《2023 IEEE/CVF International Conference on Computer Vision: ICCV 2023, Paris, France, 1-6 October 2023, [v.1]》 - IEEE International Conference on Computer Vision - 2023, - 6262～6272 - 共11页

摘要：Unsupervised anomaly detection and localization in images is a challenging problem, leading previous methods to attempt an easier supervised one-class classification formalization. Assuming training i...

关键词： Training | Location awareness | Computer vision | Codes | Training data | Feature extraction | Data models

6. Texture-Based Data Augmentation for Small Datasets NSTL国家科技图书文献中心

Amanda Dash | Alexandra Branzan Al... - 《Advanced Concepts for Intelligent Vision Systems: 21st International Conference, ACIVS 2023 Kumamoto, Japan, August 21-23, 2023 Proceedings》 - International Conference on Advanced Concepts for Intelligent Vision Systems - 2023, - 345～356 - 共12页

摘要：This paper proposes a texture-based domain-specific data augmentation technique applicable when training on small datasets for deep learning classification tasks. Our method focuses on label-preservat...

关键词： Data-independent augmentation | Texture

7. Unsupervised Deep-Learning Approach for Underwater Image Enhancement NSTL国家科技图书文献中心

Alejandro Rico Espin... | Declan McIntosh ... - 《Advances in Visual Computing: 18th International Symposium, ISVC 2023, Lake Tahoe, NV, USA, October 16-18, 2023, Proceedings, Part II》 - International Symposium on Visual Computing - 2023, - 233～244 - 共12页

摘要：Underwater images often contain color casting and blurriness which reduce the quality. State-of-the-art shows different deep-learning models to handle these degradations. However, they required ground...

关键词： Underwater | Unsupervised | Enhancement

8. An Efficient Approach for Underwater Image Improvement: Deblurring, Dehazing, and Color Correction NSTL国家科技图书文献中心

Alejandro Rico Espin... | Declan McIntosh ... - 《2023 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops: IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW), 3-7 January 2023, Waikoloa, HI, USA》 - IEEE/CVF Conference on Applications of Computer Vision Workshops - 2023, - 206～215 - 共10页

摘要：As remotely operated underwater vehicles (ROV) and static underwater video and image collection platforms become more prevalent, there is a significant need for effective ways to increase the quality ...

关键词： Training | Degradation | Visualization | Image color analysis | Real-time systems | Data models | Discrete wavelet transforms

9. U-MSAA-Net: A Multiscale Additive Attention-Based Network for Pixel-Level Identification of Finfish and Krill in Echograms NSTL国家科技图书文献中心

Tunai Porto Marques | Melissa Cote ... - 《IEEE Journal of Oceanic Engineering: A Journal Devoted to the Application of Electrical and Electronics Engineering to the Oceanic Environment》 - 2023,48(3) - 853～873 - 共21页 - 被引量：1

摘要：This paper addresses the detection of finfish and krill in echograms. Finfish, in particular Pacific hake, are used both as human food and fish meal. Krill, harvested for aquaculture and aquariums, ar...

关键词： Acoustics | Backscatter | Feature extraction | Oceans | Aquaculture | Additives | Task analysis

10. Classification of Herring, Salmon, and Bubbles in Multifrequency Echograms Using U-Net Neural Networks NSTL国家科技图书文献中心

Alex L. Slonimer | Stan E. Dosso ... - 《IEEE Journal of Oceanic Engineering: A Journal Devoted to the Application of Electrical and Electronics Engineering to the Oceanic Environment》 - 2023,48(4) - 1236～1254 - 共19页 - 被引量：2

摘要：Echosounders are used by fisheries and ocean observatories, but significant manual effort is required to classify species of interest within multifrequency echograms. This article investigates the use...

摘要：We propose Online-InReaCh, the first fully unsupervised online method for detecting and localizing anomalies on-the-fly in image sequences while following non-stationary distributions. Previous anomal...

关键词： Anomaly detection | Unsupervised | Online

摘要：This paper explores the use of attributes for document image querying and retrieval. Existing document image retrieval techniques present several drawbacks: textual searches are limited to text, query...

关键词： Document image retrieval | Document querying | Visual attributes | Convolutional neural networks | Document classification

摘要：Images can be represented and stored either in raster or in vector formats. Raster images are most ubiquitous and are defined as matrices of pixel intensities/colours, while vector images consist of a...

关键词： Segmentation | Visual attention | Image vectorization

摘要：Monitoring marine environments is a crucial part of understanding the impact of oceans on global climate and their importance for biodiversity and ecological systems, particularly in the Arctic region...

关键词： Surveys | Sea surface | Analytical models | Biological system modeling | Semantic segmentation | Arctic | Surface treatment

摘要：Unsupervised anomaly detection and localization in images is a challenging problem, leading previous methods to attempt an easier supervised one-class classification formalization. Assuming training i...

关键词： Training | Location awareness | Computer vision | Codes | Training data | Feature extraction | Data models

摘要：This paper proposes a texture-based domain-specific data augmentation technique applicable when training on small datasets for deep learning classification tasks. Our method focuses on label-preservat...

关键词： Data-independent augmentation | Texture

摘要：Underwater images often contain color casting and blurriness which reduce the quality. State-of-the-art shows different deep-learning models to handle these degradations. However, they required ground...

关键词： Underwater | Unsupervised | Enhancement

摘要：As remotely operated underwater vehicles (ROV) and static underwater video and image collection platforms become more prevalent, there is a significant need for effective ways to increase the quality ...

关键词： Training | Degradation | Visualization | Image color analysis | Real-time systems | Data models | Discrete wavelet transforms

摘要：This paper addresses the detection of finfish and krill in echograms. Finfish, in particular Pacific hake, are used both as human food and fish meal. Krill, harvested for aquaculture and aquariums, ar...

关键词： Acoustics | Backscatter | Feature extraction | Oceans | Aquaculture | Additives | Task analysis

摘要：Echosounders are used by fisheries and ocean observatories, but significant manual effort is required to classify species of interest within multifrequency echograms. This article investigates the use...

关键词： Deep learning | Aquaculture | Oceans | Semantic segmentation | Underwater acoustics

4008-161-200 800-990-8900

国家科技图书文献中心