Vor Ort
Merkzettel Warenkorb
  • Produktbild: Computer Vision – ECCV 2022
  • Produktbild: Computer Vision – ECCV 2022
Band 13680

Computer Vision – ECCV 2022 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XX

Aus der Reihe Lecture Notes in Computer Science

49,99 €

inkl. gesetzl. MwSt., Versandkostenfrei

Beschreibung

Produktdetails

Einband

Taschenbuch

Erscheinungsdatum

21.10.2022

Herausgeber

Shai Avidan + weitere

Verlag

Springer

Seitenzahl

759

Maße (L/B/H)

23,5/15,5/4,4 cm

Gewicht

1212 g

Auflage

1st edition 2022

Sprache

Englisch

ISBN

978-3-031-20043-4

Beschreibung

Produktdetails

Einband

Taschenbuch

Erscheinungsdatum

21.10.2022

Herausgeber

Verlag

Springer

Seitenzahl

759

Maße (L/B/H)

23,5/15,5/4,4 cm

Gewicht

1212 g

Auflage

1st edition 2022

Sprache

Englisch

ISBN

978-3-031-20043-4

Herstelleradresse

Springer-Verlag KG
Sachsenplatz 4-6
1201 Wien
AT

Email: GPSR Kontakt

Noch keine Bewertungen vorhanden

Verfassen Sie die erste Bewertung zu diesem Artikel

Helfen Sie anderen Kundinnen und Kunden durch Ihre Meinung.

Kundinnen und Kunden meinen

Bewertungen (0)
  • Produktbild: Computer Vision – ECCV 2022
  • Produktbild: Computer Vision – ECCV 2022
  • tSF: Transformer-Based Semantic Filter for Few-Shot Learning.- Adversarial Feature Augmentation for Cross-Domain Few-Shot Classification.- Constructing Balance from Imbalance for Long-Tailed Image Recognition.- On Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization and Beyond.- Few-Shot Video Object Detection.- Worst Case Matters for Few-Shot Recognition.- Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image Classification.- Doubly Deformable Aggregation of Covariance Matrices for Few-Shot Segmentation.- Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation.- Rethinking Clustering-Based Pseudo Labeling for Unsupervised Meta-Learning.- CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition.- Few-Shot Class-Incremental Learning for 3D Point Cloud Objects.- Meta-Learning with Less Forgetting on Large-Scale Non-stationary Task Distributions.- DNA: Improving Few-Shot Transfer Learning with Low-Rank Decomposition and Alignment.- Learning Instance and Task-Aware Dynamic Kernels for Few Shot Learning.- Open-World Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding.- Few-Shot Classification with Contrastive Learning.- Time-rEversed diffusioN tEnsor Transformer: A New TENET of Few-Shot Object Detection.- Self-Promoted Supervision for Few-Shot Transformer.- Few-Shot Object Counting and Detection.- Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark.- Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations.- Mutually Reinforcing Structure with Proposal Contrastive Consistency for Few-Shot Object Detection.- Dual Contrastive Learning with Anatomical Auxiliary Supervision for Few-Shot Medical Image Segmentation.- Improving Few-Shot Learning through Multi-task Representation Learning Theory.- Tree Structure-Aware Few Shot Image Classification via Hierarchical Aggregation.- Inductive and Transductive Few Shot Video Classification via Appearance and Temporal Alignments.- Temporal and Cross-Modal Attention for Audio-Visual Zero-Shot Learning.- HM: Hybrid Masking for Few-Shot Segmentation.- TransVLAD: Focusing on Locally Aggregated Descriptors for Few-ShotLearning.- Kernel Relative-Prototype Spectral Filtering for Few-Shot Learning.- “This Is My Unicorn, Fluffy”: Personalizing Frozen Vision-Language Representations.- CLOSE: Curriculum Learning on the Sharing Extent towards Better One-Shot NAS.- Streamable Neural Fields.- Gradient-Based Uncertainty for Monocular Depth Estimation.- Online Continual Learning with Contrastive Vision Transformer.- CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Execution.- EAutoDet: Efficient Architecture Search for Object Detection.- A Max-Flow Based Approach for Neural Architecture Search.- OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses.- ERA: Enhanced Rational Activations.- Convolutional Embedding Makes Hierarchical Vision Transformer Stronger.