6 citations · 15 across the 12 of their papers we have counts for
13 papers
Fast and Efficient Approximate Nearest Neighbor Search for High-Dimensional LLM Embeddings
Nico Hezel, Kai Uwe Barthel, Bruno Schilling +3
The annual SISAP Indexing Challenge benchmarks Approximate Nearest Neighbor Search (ANNS) algorithms under rigorous constraints. This paper presents our submissions for the 2026 ed…
Dynamic Exploration Graph: A Novel Approach for Efficient Nearest Neighbor Search in Evolving Multimedia Datasets
Nico Hezel, Kai Uwe Barthel, Bruno Schilling +2
Approximate Nearest Neighbor Search (ANNS) represents a fundamental problem in various applications (image-search, recommendation systems). While graph-based algorithms have demons…
An Exploration Graph with Continuous Refinement for Efficient Multimedia Retrieval
Nico Hezel, Kai Uwe Barthel, Konstantin Schall +1
As datasets and the dimensionality of feature vectors continue to grow, Approximate Nearest Neighbor Search (ANNS) in large multimedia databases becomes increasingly relevant. Grap…
Creating Sorted Grid Layouts with Gradient-based Optimization
Kai Uwe Barthel, Florian Tim Barthel, Peter Eisert +2
Visually sorted grid layouts provide an efficient method for organizing high-dimensional vectors in two-dimensional space by aligning spatial proximity with similarity relationship…
Permutation Learning with Only N Parameters: From SoftSort to Self-Organizing Gaussians
Kai Uwe Barthel, Florian Barthel, Peter Eisert
Sorting and permutation learning are key concepts in optimization and machine learning, especially when organizing high-dimensional data into meaningful spatial layouts. The Gumbel…
Optimizing CLIP Models for Image Retrieval with Maintained Joint-Embedding Alignment
Konstantin Schall, Kai Uwe Barthel, Nico Hezel +1
Contrastive Language and Image Pairing (CLIP), a transformative method in multimedia retrieval, typically trains two neural networks concurrently to generate joint embeddings for t…
Fast Approximate Nearest Neighbor Search with a Dynamic Exploration Graph using Continuous Refinement
Nico Hezel, Kai Uwe Barthel, Konstantin Schall +1
For approximate nearest neighbor search, graph-based algorithms have shown to offer the best trade-off between accuracy and search time. We propose the Dynamic Exploration Graph (D…
Improved Evaluation and Generation of Grid Layouts using Distance Preservation Quality and Linear Assignment Sorting
Kai Uwe Barthel, Nico Hezel, Klaus Jung +1
Images sorted by similarity enables more images to be viewed simultaneously, and can be very useful for stock photo agencies or e-commerce applications. Visually sorted grid layout…
PicArrange -- Visually Sort, Search, and Explore Private Images on a Mac Computer
Klaus Jung, Kai Uwe Barthel, Nico Hezel +1
The native macOS application PicArrange integrates state-of-the-art image sorting and similarity search to enable users to get a better overview of their images. Many file and imag…
GPR1200: A Benchmark for General-Purpose Content-Based Image Retrieval
Konstantin Schall, Kai Uwe Barthel, Nico Hezel +1
Even though it has extensively been shown that retrieval specific training of deep neural networks is beneficial for nearest neighbor image search quality, most of these models are…
Real-Time Visual Navigation in Huge Image Sets Using Similarity Graphs
Kai Uwe Barthel, Nico Hezel, Konstantin Schall +1
Nowadays stock photo agencies often have millions of images. Non-stop viewing of 20 million images at a speed of 10 images per second would take more than three weeks. This demonst…
Deep Metric Learning using Similarities from Nonlinear Rank Approximations
Konstantin Schall, Kai Uwe Barthel, Nico Hezel +1
In recent years, deep metric learning has achieved promising results in learning high dimensional semantic feature embeddings where the spatial relationships of the feature vectors…
Deep Aggregation of Regional Convolutional Activations for Content Based Image Retrieval
Konstantin Schall, Kai Uwe Barthel, Nico Hezel +1
One of the key challenges of deep learning based image retrieval remains in aggregating convolutional activations into one highly representative feature vector. Ideally, this descr…