1 code implementation • 15 Sep 2023 • Amir Rahimi, Vanessa D'Amario, Moyuru Yamada, Kentaro Takemoto, Tomotake Sasaki, Xavier Boix
We demonstrate that this result is independent of the similarity between the training and testing data and applies to well-known families of neural network architectures for VQA (i. e. monolithic architectures and neural module networks).
1 code implementation • 17 May 2023 • Kentaro Takemoto, Moyuru Yamada, Tomotake Sasaki, Hisanao Akima
Human-Object Interaction (HOI) detection is a task to localize humans and objects in an image and predict the interactions in human-object pairs.
Human-Object Interaction Detection Systematic Generalization
1 code implementation • 27 Jan 2022 • Moyuru Yamada, Vanessa D'Amario, Kentaro Takemoto, Xavier Boix, Tomotake Sasaki
We reveal that Neural Module Networks (NMNs), i. e., question-specific compositions of modules that tackle a sub-task, achieve better or similar systematic generalization performance than the conventional Transformers, even though NMNs' modules are CNN-based.
no code implementations • CVPR 2019 • Atsushi Kanehira, Kentaro Takemoto, Sho Inayoshi, Tatsuya Harada
This study addresses generating counterfactual explanations with multimodal information.