Computer Vision - ECCV 2024 Workshops

The multi-volume set LNCS 15623 until LNCS 15646 constitutes the proceedings of the workshops that were held in conjunction with the 18th European Conference on Computer Vision, ECCV 2024, which took place in Milan, Italy, during September 29October 4, 2024.

These LNCS volumes contain 574 accepted papers from 53 of the 73 workshops. The list of workshops and distribution of the workshop papers in the LNCS volumes can be found in the preface that is freely accessible online.

Inhalt

.- Revisiting Relevance Feedback for CLIP-based Interactive Image Retrieval.
.- Rethinking Sparse Lexical Representations for Image Retrieval in the Age
of Rising Multi-Modal Large Language Models.
.- Boundary Attention: Learning curves, corners, junctions and grouping.
.- Deep Learning Meets Satellite Images - An Evaluation on Handcrafted and
Learning-based Features for Multi-date Satellite Stereo Images.
.- Image Color Consistency in Datasets: The Smooth-TPS3D Method.
.- Unsupervised Video Summarization: A Reconstruction Model with Proximal
Gradient Methods.
.- TF-OCM: Training Free Optimal Community Matching for Domain Generalized Few Shot Learning.
.- Perspective-Equivariance for Unsupervised Imaging with Camera Geometry.
.- Reliable Probabilistic Human Trajectory Prediction for Autonomous Applications.
.- Calibration of Network Confidence for Unsupervised Domain Adaptation
Using Estimated Accuracy.
.- Logit disagreement: OoD Detection with Bayesian Neural Networks.
.- Can Your Generative Model Detect Out-of-Distribution Covariate Shift?.
.- Multi-label out-of-distribution detection via evidential learning.
.- UTrack: Multi-Object Tracking with Uncertain Detections.
.- TAG: Text Prompt Augmentation for Zero-Shot Out-of-Distribution Detection.
.- Sanity Checks for Explanation Uncertainty.
.- Sources of Uncertainty in 3D Scene Reconstruction.
.- The BRAVO Semantic Segmentation Challenge Results in UNCV2024.
.- Maximally Separated Active Learning.
.- Hyperbolic Metric Learning for Visual Outlier Detection.
.- A Bottom-Up Approach to Class-Agnostic Image Segmentation.
.- Adversarial Attacks on Hyperbolic Networks.
.- Hyperbolic Learning with Multimodal Large Language Models.
.- Embedding Geometries of Contrastive Language-Image Pre-Training.
.- Learning Multi-Manifold Embedding for Out-Of-Distribution Detection
.- ProxyDR: Deep Hyperspherical Metric Learning with Distance Ratio-Based
Formulation.
.- Backward-Compatible Aligned Representations via Orthogonal Transformation Layer.