Bousselham, Walid

4 publications

ICCV 2025 LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity Walid Bousselham, Angie Boggust, Sofian Chaybouti, Hendrik Strobelt, Hilde Kuehne

CVPR 2025 VideoGEM: Training-Free Action Grounding in Videos Felix Vogel, Walid Bousselham, Anna Kukleva, Nina Shvetsova, Hilde Kuehne

CVPR 2024 Grounding Everything: Emerging Localization Properties in Vision-Language Transformers Walid Bousselham, Felix Petersen, Vittorio Ferrari, Hilde Kuehne

CVPR 2023 Learning Situation Hyper-Graphs for Video Question Answering Aisha Urooj, Hilde Kuehne, Bo Wu, Kim Chheu, Walid Bousselham, Chuang Gan, Niels Lobo, Mubarak Shah