Grounding Everything: Emerging Localization Properties in Vision-Language TransformersWalid Bousselham, Hilde Kuehne, Felix Petersen et al.|Unknown|2024Cited by 38
MaskInversion: Localized Embeddings via Optimization of Explainability MapsWalid Bousselham, Hilde Kuehne, Christian Rupprecht et al.|arXiv (Cornell University)|2024Cited by 1
Grounding Everything: Emerging Localization Properties in Vision-Language TransformersWalid Bousselham, Hilde Kuehne, Felix Petersen et al.|arXiv (Cornell University)|2023Cited by 0