Computer Vision – ECCV 2024 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part XLII

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. 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; motion estimation.

Open-Set Recognition in the Age of Vision-Language Models.- Unsqueeze [CLS] Bottleneck to Learn Rich Representations.- Robust Multimodal Learning via Representation Decoupling.- Object-Conditioned Energy-Based  Attention Map Alignment in Text-to-Image Diffusion Models.- WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activity Sensing.- Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic Segmentation.- VeCLIP: Improving CLIP Training via Visual-enriched Captions.- Three Things We Need to Know About Transferring Stable Diffusion to Visual Dense Prediciton Tasks.- Learning Representations from Foundation Models for Domain Generalized Stereo Matching.- Spike-Temporal Latent Representation for Energy-Efficient Event-to-Video Reconstruction.- Effective Lymph Nodes Detection in CT Scans Using Location Debiased Query Selection and Contrastive Query Representation in Transformer.- Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts.- Event-Adapted Video Super-Resolution.- Look Hear: Gaze Prediction for Speech-directed Human Attention.- Raising the Ceiling: Conflict-Free Local Feature Matching with Dynamic View Switching.- Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World Knowledge.- Catastrophic Overfitting: A Potential Blessing in Disguise.- Long-range Turbulence Mitigation: A Large-scale Dataset and A Coarse-to-fine Framework.- SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models.- Visual Alignment Pre-training for Sign Language Translation.- Parrot Captions Teach CLIP to Spot Text.- Solving Motion Planning Tasks with a Scalable Generative Model.- Griffon: Spelling out All Object Locations at Any Granularity with Large Language Models.- Vision-Language Action Knowledge Learning for Semantic-Aware Action Quality Assessment.- Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentation.- BurstM: Deep Burst Multi-scale SR using Fourier Space with Optical Flow.- Diffusion Reward: Learning Rewards via Conditional Video Diffusion.