7 papers · 1 filter
FlowID : Enhancing Forensic Identification with Latent Flow-Matching Models
Jules Ripoll, David Bertoin, Alasdair Newson +2
Every day, many people die under violent circumstances, whether from crimes, war, migration, or climate disasters. Medico-legal and law enforcement institutions document many portr…
Diff-CA: Separating Common and Salient Factors with Diffusion Models
Michaël Soumm, Alexandre Fournier Montgieux, Yunlong He +2
Contrastive Analysis aims to separate factors that are common between two data distributions from those that are salient to only one of them. Existing contrastive methods are based…
When Prompts Override Vision: Prompt-Induced Hallucinations in LVLMs
Pegah Khayatan, Jayneel Parekh, Arnaud Dapogny +3
Despite impressive progress in capabilities of large vision-language models (LVLMs), these systems remain vulnerable to hallucinations, i.e., outputs that are not grounded in the v…
Infusion: internal diffusion for inpainting of dynamic textures and complex motion
Nicolas Cherel, Andrés Almansa, Yann Gousseau +1
Video inpainting is the task of filling a region in a video in a visually convincing manner. It is very challenging due to the high dimensionality of the data and the temporal cons…
Restyling Unsupervised Concept Based Interpretable Networks with Generative Models
Jayneel Parekh, Quentin Bouniot, Pavlo Mozharovskyi +2
Developing inherently interpretable models for prediction has gained prominence in recent years. A subclass of these models, wherein the interpretable network relies on learning hi…
SINETRA: a Versatile Framework for Evaluating Single Neuron Tracking in Behaving Animals
Raphael Reme, Alasdair Newson, Elsa Angelini +2
Accurately tracking neuronal activity in behaving animals presents significant challenges due to complex motions and background noise. The lack of annotated datasets limits the eva…