Full Description
The multi-volume set of LNCS books with volume numbers 15059 up to 15147 constitutes the refereed proceedings of the 18th European Conference on Computer Vision, ECCV 2024, held in Milan, Italy, during September 29-October 4, 2024.
The 2387 papers presented in these proceedings were carefully reviewed and selected from a total of 8585 submissions. They 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; motion estimation.
Contents
Spline-based Transformers.- Learning Pseudo 3D Guidance for View-consistent Texturing with 2D Diffusion.- TreeSBA: Tree-Transformer for Self-Supervised Sequential Brick Assembly.- SparseRadNet: Sparse Perception Neural Network on Subsampled Radar Data.- Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models.- Adversarial Diffusion Distillation.- Fake It till You Make It: Curricular Dynamic Forgery Augmentations towards General Deepfake Detection.- Explain via Any Concept: Concept Bottleneck Model with Open Vocabulary Concepts.- Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation.- A Multimodal Benchmark Dataset and Model for Crop Disease Diagnosis.- Missing Modality Prediction for Unpaired Multimodal Learning via Joint Embedding of Unimodal Models.- Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization using Geometrical Information.- Improving Diffusion Models for Authentic Virtual Try-on in the Wild.- Exploiting Semantic Reconstruction to Mitigate Hallucinations in Vision-Language Models.- LISO: Lidar-only Self-Supervised 3D Object Detection.- Text-Conditioned Resampler For Long Form Video Understanding.- Implicit Steganography Beyond the Constraints of Modality.- Using My Artistic Style? You Must Obtain My Authorization.- LookupViT: Compressing visual information to a limited number of tokens.- Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation.- UMERegRobust - Universal Manifold Embedding Compatible Features for Robust Point Cloud Registration.- Non-transferable Pruning.- A Compact Dynamic 3D Gaussian Representation for Real-Time Dynamic View Synthesis.- Fast Context-Based Low-Light Image Enhancement via Neural Implicit Representations.- Toward Open Vocabulary Aerial Object Detection with CLIP-Activated Student-Teacher Learning.- Affine steerers for structured keypoint description.
