12 papers
Composed Historical Image Retrieval by Modeling Temporal Representations
Adrià Molina Rodríguez, Oriol Ramos Terrades, Josep Lladós Canet
While time evolves linearly, the geometry of neural embedding spaces is inherently multi-dimensional, often chaotic, and difficult to interpret. In principle, one could constrain a…
Robust Interpretation of Historical Documents in Knowledge Graphs Through Query Inference and Execution
Sebastià Nicolau, Adrià Molina, Oriol Ramos Terrades +1
The emergence of Large Language Models (LLMs) has redefined how users interact with information in digital environments. However, their widespread and often indiscriminate integrat…
Temporal Modeling of Optically Variable Devices in Identity Documents
Glen Pouliquen, Joseph Chazalon, Guillaume Chiron +3
Robust remote verification of identity documents relies on analyzing faint, transparent security features like Optically Variable Devices (OVDs), or "holograms", within user-captur…
Visual Model Checking: Graph-Based Inference of Visual Routines for Image Retrieval
Adrià Molina, Oriol Ramos Terrades, Josep Lladós
Information retrieval lies at the foundation of the modern digital industry. While natural language search has seen dramatic progress in recent years largely driven by embedding-ba…
ODE-ViT: Plug & Play Attention Layer from the Generalization of the ViT as an Ordinary Differential Equation
Carlos Boned Riera, David Romero Sanchez, Oriol Ramos Terrades
In recent years, increasingly large models have achieved outstanding performance across CV tasks. However, these models demand substantial computational resources and storage, and…
LLM-Driven Medical Document Analysis: Enhancing Trustworthy Pathology and Differential Diagnosis
Lei Kang, Xuanshuo Fu, Oriol Ramos Terrades +3
Medical document analysis plays a crucial role in extracting essential clinical insights from unstructured healthcare records, supporting critical tasks such as differential diagno…