LEADER 05479nam 22005535 450 001 9910629291203321 005 20251225202157.0 010 $a9783031200533 010 $a3031200535 024 7 $a10.1007/978-3-031-20053-3 035 $a(MiAaPQ)EBC7132893 035 $a(Au-PeEL)EBL7132893 035 $a(CKB)25289753400041 035 $a(BIP)085784299 035 $a(PPN)266348378 035 $a(DE-He213)978-3-031-20053-3 035 $a(EXLCZ)9925289753400041 100 $a20221105d2022 u| 0 101 0 $aeng 135 $aurcnu|||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aComputer Vision ? ECCV 2022 $e17th European Conference, Tel Aviv, Israel, October 23?27, 2022, Proceedings, Part XXIV /$fedited by Shai Avidan, Gabriel Brostow, Moustapha Cissé, Giovanni Maria Farinella, Tal Hassner 205 $a1st ed. 2022. 210 1$aCham :$cSpringer Nature Switzerland :$cImprint: Springer,$d2022. 215 $a1 online resource (803 pages) 225 1 $aLecture Notes in Computer Science,$x1611-3349 ;$v13684 311 08$aPrint version: Avidan, Shai Computer Vision - ECCV 2022 Cham : Springer,c2022 9783031200526 327 $aImproving Vision Transformers by Revisiting High-Frequency Components -- Recurrent Bilinear Optimization for Binary Neural Networks -- Neural Architecture Search for Spiking Neural Networks -- Where to Focus: Investigating Hierarchical Attention Relationship for Fine-Grained Visual Classification -- DaViT: Dual Attention Vision Transformers -- Optimal Transport for Label-Efficient Visible-Infrared Person Re-identification -- Locality Guidance for Improving Vision Transformers on Tiny Datasets -- Neighborhood Collective Estimation for Noisy Label Identification and Correction -- Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay -- Anti-Retroactive Interference for Lifelong Learning -- Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-Tailed Learning -- Dynamic Metric Learning with Cross-Level Concept Distillation -- MENet: A Memory-Based Network with Dual-Branch for Efficient Event Stream Processing -- Out-of-Distribution Detection with Boundary Aware Learning -- Learning Hierarchy Aware Features for Reducing Mistake Severity -- Learning to Detect Every Thing in an Open World -- KVT: k-NN Attention for Boosting Vision Transformers -- Registration Based Few-Shot Anomaly Detection -- Improving Robustness by Enhancing Weak Subnets -- Learning Invariant Visual Representations for Compositional Zero-Shot Learning -- Improving Covariance Conditioning of the SVD Meta-Layer by Orthogonality -- Out-of-Distribution Detection with Semantic Mismatch under Masking -- Data-Free Neural Architecture Search via Recursive Label Calibration -- Learning from Multiple Annotator Noisy Labels via Sample-Wise Label Fusion -- Acknowledging the Unknown for Multi-Label Learning with Single Positive Labels -- AutoMix: Unveiling the Power of Mixup for Stronger Classifiers -- MaxViT: Multi-axis Vision Transformer -- ScalableViT: Rethinking the Context-Oriented Generalization of Vision Transformer -- Three Things Everyone Should Know about Vision Transformers -- DeiT III: Revenge of the ViT -- MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition -- Self-Feature Distillation with Uncertainty Modeling for Degraded Image Recognition -- Novel Class Discovery without Forgetting -- SAFA: Sample-Adaptive Feature Augmentation for Long-Tailed Image Classification -- Negative Samples Are at Large: Leveraging Hard-Distance Elastic Loss for Re-identification -- Discrete-Constrained Regression for Local Counting Models -- Breadcrumbs: Adversarial Class-Balanced Sampling for Long-Tailed Recognition -- Chairs Can Be Stood On: Overcoming Object Bias in Human-Object Interaction Detection -- A Fast Knowledge Distillation Framework for Visual Recognition -- DICE: Leveraging Sparsification for Out-of-Distribution Detection -- Invariant Feature Learning forGeneralized Long-Tailed Classification -- Sliced Recursive Transformer. 330 $aThe 39-volume set, comprising the LNCS books 13661 until 13699, constitutes the refereed proceedings of the 17th European Conference on Computer Vision, ECCV 2022, held in Tel Aviv, Israel, during October 23?27, 2022. The 1645 papers presented in these proceedings were carefully reviewed and selected from a total of 5804 submissions. The papers deal with topics such as computer vision; machine learning; deep neural networks; reinforcement learning; object recognition; image classification; image processing; object detection; semantic segmentation; human pose estimation; 3d reconstruction; stereo vision; computational photography; neural networks; image coding; image reconstruction; object recognition; motion estimation. 410 0$aLecture Notes in Computer Science,$x1611-3349 ;$v13684 606 $aComputer vision 606 $aComputer Vision 615 0$aComputer vision. 615 14$aComputer Vision. 676 $a006.37 676 $a006.37 700 $aAvidan$b Shai$01262565 701 $aBrostow$b Gabriel$01262566 701 $aCisse?$b Moustapha$00 701 $aFarinella$b Giovanni Maria$01262568 701 $aHassner$b Tal$01262569 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910629291203321 997 $aUNINA