Computer Vision - ECCV 2024

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 29October 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.

Inhalt

OvSW: Overcoming Silent Weights for Accurate Binary Neural Networks.- Multistain Pretraining for Slide Representation Learning in Pathology.- T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy.- Harmonizing knowledge Transfer in Neural Network with Unified Distillation.- Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data.- Click Prompt Learning with Optimal Transport for Interactive Segmentation.- 3D Human Pose Estimation via Non-Causal Retentive Networks.- OMR: Occlusion-Aware Memory-Based Refinement for Video Lane Detection.- 6DoF Head Pose Estimation through Explicit Bidirectional Interaction with Face Geometry.- Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging.- Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition.- Enhancing Tampered Text Detection through Frequency Feature Fusion and Decomposition.- Modeling Label Correlations with Latent Context for Multi-Label Recognition.- LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model.- Finding a needle in a haystack: A Black-Box Approach to Invisible Watermark Detection.- DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstruction.- MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos.- ARoFace: Alignment Robustness to Improve Low-quality Face Recognition.- Learning Diffusion Models for Multi-View Anomaly Detection.- Clearer Frames, Anytime: Resolving Velocity Ambiguity in Video Frame Interpolation.- Multi-modal Relation Distillation for Unified 3D Representation Learning.- Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization.- Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation.- Distributionally Robust Loss for Long-Tailed Multi-Label Image Classification.- MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation.- LongVLM: Efficient Long Video Understanding via Large Language Models.- The All-Seeing Project V2: Towards General Relation Comprehension of the Open World.