Cantitate/Preț
Produs

Pattern Recognition: Lecture Notes in Computer Science, cartea 14264

Editat de Ullrich Köthe, Carsten Rother
en Limba Engleză Paperback – 8 mar 2024
This book constitutes the proceedings of the 45th Annual Conference of the German Association for Pattern Recognition, DAGM-GCPR 2023, which took place in Heidelberg, Germany, during September 19-22, 2023. 
The 40 full papers included in these proceedings were carefully reviewed and selected from 76 submissions. They were organized in topical sections as follows: Segmentation and action recognition; 3D reconstruction and neural rendering; Photogrammetry and remote sensing; Pattern recognition in the life sciences; Interpretable machine learning; Weak supervision and online learning; Robust models.
Citește tot Restrânge

Din seria Lecture Notes in Computer Science

Preț: 64231 lei

Preț vechi: 80290 lei
-20%

Puncte Express: 963

Carte tipărită la comandă

Livrare economică 09-23 iulie

Livrare prin curier în România Termenul estimat este afișat lângă disponibilitate.
Transport gratuit pentru acest produs Plată online sau ramburs, în funcție de opțiunile comenzii.
Retur gratuit în 14 zile Comandă securizată și suport în română.

Specificații

ISBN-13: 9783031546044
ISBN-10: 3031546040
Pagini: 660
Ilustrații: XV, 641 p. 206 illus., 191 illus. in color.
Dimensiuni: 155 x 235 x 36 mm
Greutate: 0.98 kg
Ediția:2024
Editura: Springer
Colecția Lecture Notes in Computer Science
Seria Lecture Notes in Computer Science

Locul publicării:Cham, Switzerland

Cuprins

Segmentation and action recognition.- Score-Based Generative Models for Medical Image Segmentation using Signed Distance Functions.- A Trimodal Dataset: RGB, Thermal, and Depth for Human Segmentation and Temporal Action Detection.- Airborne-Shadow: Towards Fine-Grained Shadow Detection in Aerial Imagery.- UGainS: Uncertainty Guided Anomaly Instance Segmentation.- Local Spherical Harmonics Improve Skeleton-Based Hand Action Recognition.- 3D reconstruction and neural rendering.- LMD: Light-weight Prediction Quality Estimation for Object Detection in Lidar Point Clouds.- A Network Analysis for Correspondence Learning via Linearly-Embedded Functions.- HiFiHR: Enhancing 3D Hand Reconstruction from a Single Image via High-Fidelity Texture.- Point2Vec for Self-Supervised Representation Learning on Point Clouds.- FullFormer: Generating Shapes Inside Shapes.- GenLayNeRF: Generalizable Layered Representations with 3D ModelAlignment for Human View Synthesis.- RC-BEVFusion: A Plug-In Module for Radar-Camera Bird's Eye View Feature Fusion.- Parallax-aware Image Stitching based on Homographic Decomposition.- 
Photogrammetry and remote sensing.- DustNet: Attention to Dust.- Leveraging Bioclimatic Context for Supervised and Self-Supervised Land Cover Classification.- Automatic Reverse Engineering: Creating computer-aided design (CAD) models from multi-view images.- Characterization of out-of-distribution samples from uncertainty maps using supervised machine learning.- Underwater multiview stereo using axial camera models.- Pattern recognition in the life sciences.- 3D Retinal Vessel Segmentation in OCTA Volumes: Annotated Dataset MORE3D and Hybrid U-Net with Flattening Transformation.- M(otion)-mode Based Prediction of Ejection Fraction using Echocardiograms.- Improving Data Efficiency for Plant Cover Prediction with Label Interpolation and Monte-Carlo Cropping.- Learning Channel Importance for High Content Imaging with Interpretable Deep Input Channel Mixing.- Self-Supervised Learning in Histopathology: New Perspectives for Prostate Cancer Grading.- Interpretable machine learning.- DeViL: Decoding Vision features into Language.- Zero-shot Translation of Attention Patterns in VQA Models to Natural Language.- Beyond Debiasing: Actively Steering Feature Selection via Loss Regularization.- Simplified Concrete Dropout - Improving the Generation of Attribution Masks for Fine-grained Classification.- Weak supervision and online learning.- Best Practices in Active Learning for Semantic Segmentation.- COOLer: Class-Incremental Learning for Appearance-Based Multiple Object Tracking.- Label Smarter, Not Harder: CleverLabel for Faster Annotation of Ambiguous Image Classification with Higher Quality.- Speeding Up Online Self-Supervised Learning by Exploiting Its Limitations.- Text-to-feature diffusion for audio-visual few-shot learning.- Correlation Clustering of Bird Sounds.- MargCTGAN: A ``Marginally'' Better CTGAN for the Low Sample Regime.- Robust models.- Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networks Adversarial Perturbations Straight on JPEG Coefficients.- Certified Robust Models with Slack Control and Large Lipschitz Constants.- Multiclass Alignment of Confidence and Certainty for Network Calibration.- Drawing the Same Bounding Box Twice? Coping Noisy Annotations in Object Detection with Repeated Labels.- An Evaluation of Zero-Cost Proxies - from Neural Architecture Performance Prediction to Model Robustness.