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 2327, 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.
Box-Supervised Instance Segmentation with Level Set Evolution.- Point Primitive Transformer for Long-Term 4D Point Cloud Video Understanding.- Adaptive Agent Transformer for Few-Shot Segmentation.- Waymo Open Dataset: Panoramic Video Panoptic Segmentation.- TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation.- AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-Shot Interactions.- Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation.- Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications.- Perceptual Artifacts Localization for Inpainting.- 2D Amodal Instance Segmentation Guided by 3D Shape Prior.- Data Efficient 3D Learner via Knowledge Transferred from 2D Model.- Adaptive Spatial-BCE Loss for Weakly Supervised Semantic Segmentation.- Dense Gaussian Processes for Few-Shot Segmentation.- 3D Instances as 1D Kernels.- TransMatting: Enhancing Transparent Objects Matting with Transformerslc$
![Computer Vision ECCV 2022: 17th European Conference, Tel Aviv, Israel, October [Paperback]](/itemImage/2/6/2/1/2_5269221.jpg "Computer Vision ECCV 2022: 17th European Conference, Tel Aviv, Israel, October [Paperback]")