55 citations · 62 across the 5 of their papers we have counts for
5 papers
ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models
Ilker Kesen, Andrea Pedrotti, Mustafa Dogan +8
With the ever-increasing popularity of pretrained Video-Language Models (VidLMs), there is a pressing need to develop robust evaluation methodologies that delve deeper into their v…
Interpreting Vision and Language Generative Models with Semantic Visual Priors
Michele Cafagna, Lina M. Rojas-Barahona, Kees van Deemter +1
When applied to Image-to-text models, interpretability methods often provide token-by-token explanations namely, they compute a visual explanation for each token of the generated s…
HL Dataset: Visually-grounded Description of Scenes, Actions and Rationales
Michele Cafagna, Kees van Deemter, Albert Gatt
Current captioning datasets focus on object-centric captions, describing the visible objects in the image, e.g. "people eating food in a park". Although these datasets are useful t…
Understanding Cross-modal Interactions in V&L Models that Generate Scene Descriptions
Michele Cafagna, Kees van Deemter, Albert Gatt
Image captioning models tend to describe images in an object-centric way, emphasising visible objects. But image descriptions can also abstract away from objects and describe the t…
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
Letitia Parcalabescu, Michele Cafagna, Lilitta Muradjan +3
We propose VALSE (Vision And Language Structured Evaluation), a novel benchmark designed for testing general-purpose pretrained vision and language (V&L) models for their visio-lin…