Full Description
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.
Contents
Contrastive Deep Supervision.- Discriminability-Transferability Trade-Off: An Information-Theoretic Perspective.- LocVTP: Video-Text Pre-training for Temporal Localization.- Few-Shot End-to-End Object Detection via Constantly Concentrated Encoding across Heads.- Implicit Neural Representations for Image Compression.- LiP-Flow: Learning Inference-Time Priors for Codec Avatars via Normalizing Flows in Latent Space.- Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining.- Learning Ego 3D Representation As Ray Tracing.- Static and Dynamic Concepts for Self-Supervised Video Representation Learning.- SphereFed: Hyperspherical Federated Learning.- Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning.- Posterior Refinement on Metric Matrix Improves Generalization Bound in Metric Learning.- Balancing Stability and Plasticity through Advanced Null Space in Continual Learning.- DisCo: Remedying Self-Supervised Learning on Lightweight Models with Distilled Contrastive Learning.- CoSCL: Cooperation of Small Continual Learners Is Stronger than a Big One.- Manifold Adversarial Learning for Cross-Domain 3D Shape Representation.- Fast-MoCo: Boost Momentum-Based Contrastive Learning with Combinatorial Patches.- LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modeling.- On the Versatile Uses of Partial Distance Correlation in Deep Learning.- Self-Regulated Feature Learning via Teacher-Free Feature Distillation.- Balancing between Forgetting and Acquisition in Incremental Subpopulation Learning.- Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification.- DAS: Densely-Anchored Sampling for Deep Metric Learning.- Learn from All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition.- A Non-Isotropic Probabilistic TakeOn Proxy-Based Deep Metric Learning.- TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers.- UFO: Unified Feature Optimization.- Sound Localization by Self-Supervised Time Delay Estimation.- X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation.- SLIP: Self-Supervision Meets Language-Image Pre-training.- Discovering Deformable Keypoint Pyramids.- Neural Video Compression Using GANs for Detail Synthesis and Propagation.- A Contrastive Objective for Learning Disentangled Representations.- PT4AL: Using Self-Supervised Pretext Tasks for Active Learning.- ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer.- DualPrompt: Complementary Prompting for Rehearsal-Free Continual Learning.- Unifying Visual Contrastive Learning for Object Recognition from a Graph Perspective.- Decoupled Contrastive Learning.- Joint Learning of Localized Representations from Medical Images and Reports.- The Challenges of Continuous Self-Supervised Learning.- Conditional Stroke Recovery for Fine-Grained Sketch-Based Image Retrieval.- Identifying Hard Noise in Long-Tailed Sample Distribution.
