Aude Oliva

ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs

arXiv 2024

Going Beyond Nouns With Vision & Language Models Using Synthetic Data

ICCV 2023 1

Ego4D: Around the World in 3,000 Hours of Egocentric Video

CVPR 2022 1

Network Dissection: Quantifying Interpretability of Deep Visual Representations

network-dissection-quantifying-1

Antonio Torralba

professor

Leonid Karlinsky

Rogerio Feris

Sivan Doveh

Abrham Gebreselasie

Aditya Khosla

Adriano Fragomeni

Akshay Erapalli

Andrew Westbury

Antonino Furnari