conftrace_

narration grounding

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

pixel-level grounding (1) zero-shot grounding (1) weakly supervised segmentation (1) video object segmentation (1) egocentric video (1) vision-language model (1) vision-language alignment (1) weakly supervised learning (1)

Papers

Learning to Segment Referred Objects from Narrated Egocentric Videos CVPR 2024