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

Upper-body Hierarchical Graph for Skeleton Based Emotion Recognition in Assistive Driving.- Fine-Grained Scene Graph Generation via Sample-Level Bias Prediction.- Exploring Guided Sampling of Conditional GANs.- MotionChain: Conversational Motion Controllers via Multimodal Prompts.- Idempotent Unsupervised Representation Learning for Skeleton-Based Action Recognition.- Latent Guard: a Safety Framework for Text-to-image Generation.- MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion.- TCC-Det: Temporarily consistent cues for weakly-supervised 3D detection.- OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection.- FoundPose: Unseen Object Pose Estimation with Foundation Features.- Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation.- Kalman-Inspired Feature Propagation for Video Face Super-Resolution.- Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models.- VideoMamba: State Space Model for Efficient Video Understanding.- SAFNet: Selective Alignment Fusion Network for Efficient HDR Imaging.- Heterogeneous Graph Learning for Scene Graph Prediction in 3D Point Clouds.- Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving.- Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models.- Deep Cost Ray Fusion for Sparse Depth Video Completion.- GraphBEV: Towards Robust BEV Feature Alignment for Multi-Modal 3D Object Detection.- DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video.- GraspXL: Generating Grasping Motions for Diverse Objects at Scale.- Source Prompt Disentangled Inversion for Boosting Image Editability with Diffusion Models.- Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models.- JointDreamer: Ensuring Geometry Consistency and Text Congruence in Text-to-3D Generation via Joint Score Distillation.- Brain Netflix: Scaling Data to Reconstruct Videos from Brain Signals.- Equivariant Spatio-Temporal Self-Supervision for LiDAR Object Detection.