conftrace_

video object grounding

1 paper

Explore in graph

Also known as

VOG

Co-occurring keywords · papers mentioning both

multi-modal relation (1) relative position encoding (1) semantic role (1) object relation (1) natural language description (1) language description (1) multimodal learning (1)

Papers

Video Object Grounding Using Semantic Roles in Language Description CVPR 2020