Computer Vision - ECCV 2022 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part IV / [electronic resource] :
edited by Shai Avidan, Gabriel Brostow, Moustapha Cissé, Giovanni Maria Farinella, Tal Hassner.
- 1st ed. 2022.
- LVI, 745 p. 204 illus., 198 illus. in color. online resource.
- Lecture Notes in Computer Science, 13664 1611-3349 ; .
- Lecture Notes in Computer Science, 13664 .
Expanding Language-Image Pretrained Models for General Video Recognition -- Hunting Group Clues with Transformers for Social Group Activity Recognition -- Contrastive Positive Mining for Unsupervised 3D Action Representation Learning -- Target-Absent Human Attention -- Uncertainty-Based Spatial-Temporal Attention for Online Action Detection -- Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows -- Rethinking Zero-Shot Action Recognition: Learning from Latent Atomic Actions -- Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection -- Collaborating Domain-Shared and Target-Specific Feature Clustering for Cross-Domain 3D Action Recognition -- Is Appearance Free Action Recognition Possible? -- Learning Spatial-Preserved Skeleton Representations for Few-Shot Action Recognition -- Dual-Evidential Learning for Weakly-Supervised Temporal Action Localization -- Global-Local Motion Transformer for Unsupervised Skeleton-Based Action Learning -- AdaFocusV3: On Unified Spatial-Temporal Dynamic Video Recognition -- Panoramic Human Activity Recognition -- Delving into Details: Synopsis-to-Detail Networks for Video Recognition -- A Generalized & Robust Framework for Timestamp Supervision in Temporal Action Segmentation -- Few-Shot Action Recognition with Hierarchical Matching and Contrastive Learning -- PrivHAR: Recognizing Human Actions from Privacy-Preserving Lens -- Scale-Aware Spatio-Temporal Relation Learning for Video Anomaly Detection -- Compound Prototype Matching for Few-Shot Action Recognition -- Continual 3D Convolutional Neural Networks for Real-Time Processing of Videos -- Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition -- Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection -- Action Quality Assessment with Temporal Parsing Transformer -- Entry-Flipped Transformer for Inference and Prediction of Participant Behavior -- Pairwise Contrastive Learning Network for Action Quality Assessment -- Geometric Features Informed Multi-Person Human-Object Interaction Recognition in Videos -- ActionFormer: Localizing Moments of Actions with Transformers -- SocialVAE: Human Trajectory Prediction Using Timewise Latents -- Shape Matters: Deformable Patch Attack -- Frequency Domain Model Augmentation for Adversarial Attack -- Prior-Guided Adversarial Initialization for Fast Adversarial Training -- Enhanced Accuracy and Robustness via Multi-Teacher Adversarial Distillation -- LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity -- A Large-Scale Multiple-Objective Method for Black-Box Attack against Object Detection -- GradAuto: Energy-Oriented Attack on Dynamic Neural Networks -- A Spectral View of Randomized Smoothing under Common Corruptions: Benchmarking and Improving Certified Robustness -- Improving Adversarial Robustness of 3D Point Cloud Classification Models -- Learning Extremely Lightweight and Robust Model with Differentiable Constraints on Sparsity and Condition Number -- RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN -- Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks.
The 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.
9783031197727
10.1007/978-3-031-19772-7 doi
Computer vision.
Application software.
User interfaces (Computer systems).
Human-computer interaction.
Machine learning.
Pattern recognition systems.
Computer Vision.
Computer and Information Systems Applications.
User Interfaces and Human Computer Interaction.
Machine Learning.
Automated Pattern Recognition.
TA1634
006.37
Expanding Language-Image Pretrained Models for General Video Recognition -- Hunting Group Clues with Transformers for Social Group Activity Recognition -- Contrastive Positive Mining for Unsupervised 3D Action Representation Learning -- Target-Absent Human Attention -- Uncertainty-Based Spatial-Temporal Attention for Online Action Detection -- Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows -- Rethinking Zero-Shot Action Recognition: Learning from Latent Atomic Actions -- Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection -- Collaborating Domain-Shared and Target-Specific Feature Clustering for Cross-Domain 3D Action Recognition -- Is Appearance Free Action Recognition Possible? -- Learning Spatial-Preserved Skeleton Representations for Few-Shot Action Recognition -- Dual-Evidential Learning for Weakly-Supervised Temporal Action Localization -- Global-Local Motion Transformer for Unsupervised Skeleton-Based Action Learning -- AdaFocusV3: On Unified Spatial-Temporal Dynamic Video Recognition -- Panoramic Human Activity Recognition -- Delving into Details: Synopsis-to-Detail Networks for Video Recognition -- A Generalized & Robust Framework for Timestamp Supervision in Temporal Action Segmentation -- Few-Shot Action Recognition with Hierarchical Matching and Contrastive Learning -- PrivHAR: Recognizing Human Actions from Privacy-Preserving Lens -- Scale-Aware Spatio-Temporal Relation Learning for Video Anomaly Detection -- Compound Prototype Matching for Few-Shot Action Recognition -- Continual 3D Convolutional Neural Networks for Real-Time Processing of Videos -- Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition -- Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection -- Action Quality Assessment with Temporal Parsing Transformer -- Entry-Flipped Transformer for Inference and Prediction of Participant Behavior -- Pairwise Contrastive Learning Network for Action Quality Assessment -- Geometric Features Informed Multi-Person Human-Object Interaction Recognition in Videos -- ActionFormer: Localizing Moments of Actions with Transformers -- SocialVAE: Human Trajectory Prediction Using Timewise Latents -- Shape Matters: Deformable Patch Attack -- Frequency Domain Model Augmentation for Adversarial Attack -- Prior-Guided Adversarial Initialization for Fast Adversarial Training -- Enhanced Accuracy and Robustness via Multi-Teacher Adversarial Distillation -- LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity -- A Large-Scale Multiple-Objective Method for Black-Box Attack against Object Detection -- GradAuto: Energy-Oriented Attack on Dynamic Neural Networks -- A Spectral View of Randomized Smoothing under Common Corruptions: Benchmarking and Improving Certified Robustness -- Improving Adversarial Robustness of 3D Point Cloud Classification Models -- Learning Extremely Lightweight and Robust Model with Differentiable Constraints on Sparsity and Condition Number -- RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN -- Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks.
The 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.
9783031197727
10.1007/978-3-031-19772-7 doi
Computer vision.
Application software.
User interfaces (Computer systems).
Human-computer interaction.
Machine learning.
Pattern recognition systems.
Computer Vision.
Computer and Information Systems Applications.
User Interfaces and Human Computer Interaction.
Machine Learning.
Automated Pattern Recognition.
TA1634
006.37