ExoViP: Step-by-step Verification and Exploration with Exoskeleton Modules for Compositional Visual Reasoning

Y Wang, A Yuille, Z Li, Z Zheng - arXiv preprint arXiv:2408.02210, 2024 - arxiv.org
Compositional visual reasoning methods, which translate a complex query into a structured
composition of feasible visual tasks, have exhibited a strong potential in complicated multi …

On the Diagnosis and Generalization of Compositional Visual Reasoning

Z Li - 2024 - jscholarship.library.jhu.edu
Computer vision is not only about recognizing visual signals, but also rea-soning over
perceived visual elements. This ability, termed visual reasoning, is typically studied by …