6 papers · 1 filter
RelateAnything: Real-Time Open-Vocabulary Relation Prediction From Any Inputs
Maëlic Neau
Open-vocabulary detection accepts any class list at inference, and promptable segmentation returns regions without class names: the taxonomy has left the model and become an input.…
Visual Commonsense Driven Knowledge Refinements for Scene Graph Generation
Maëlic Neau, Salim Baloch, Jakob Suchan +2
Learning-driven Scene Graph Generation (SGG) models excel on frequent relation types but degrade sharply under annotation sparsity, failing to capture reliable visual commonsense k…
REACT++: Efficient Cross-Attention for Real-Time Scene Graph Generation
Maëlic Neau, Zoe Falomir
Scene Graph Generation (SGG) is a task that encodes visual relationships between objects in images as graph structures. SGG shows significant promise as a foundational component fo…
Measuring Image-Relation Alignment: Reference-Free Evaluation of VLMs and Synthetic Pre-training for Open-Vocabulary Scene Graph Generation
Maëlic Neau, Zoe Falomir, Cédric Buche +1
Scene Graph Generation (SGG) encodes visual relationships between objects in images as graph structures. Thanks to the advances of Vision-Language Models (VLMs), the task of Open-V…
REACT: Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generation
Maëlic Neau, Paulo E. Santos, Anne-Gwenn Bosser +2
Scene Graph Generation (SGG) is a task that encodes visual relationships between objects in images as graph structures. SGG shows significant promise as a foundational component fo…
Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph Generation
Neau Maëlic, Paulo E. Santos, Anne-Gwenn Bosser +1
Learning to compose visual relationships from raw images in the form of scene graphs is a highly challenging task due to contextual dependencies, but it is essential in computer vi…