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

Few-shot Class Incremental Learning with Attention-Aware Self-Adaptive Prompt.- An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models.- Generalizable Symbolic Optimizer Learning.- Online Continuous Generalized Category Discovery.- Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation.- Tackling Structural Hallucination in Image Translation with Local Diffusion.- Hierarchical Separable Video Transformer for Snapshot Compressive Imaging.- Unified Medical Image Pre-training in Language-Guided Common Semantic Space.- On the Vulnerability of Skip Connections to Model Inversion Attacks.- Adversarial Robustification via Text-to-Image Diffusion Models.- Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection.- Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detector.- Reinforcement Learning via Auxillary Task Distillation.- DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation.- Pre-trained Visual Dynamics Representations for Efficient Policy Learning.- View-Consistent Hierarchical 3D Segmentation Using Ultrametric Feature Fields.- Plug and Play: A Representation Enhanced Domain Adapter for Collaborative Perception.- Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models.- SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation.- TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias.- Learning Quantized Adaptive Conditions for Diffusion Models.- STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay.- Remove Projective LiDAR Depthmap Artifacts via Exploiting Epipolar Geometry.- Accelerating Online Mapping and Behavior Prediction via Direct BEV Feature Attention.- High-Fidelity Modeling of Generalizable Wrinkle Deformation.- Instruction Tuning-free Visual Token Complement for Multimodal LLMs.