Learning to Segment Referred Objects from Narrated Egocentric Videos

Yuhan Shen,Huiyu Wang,Xitong Yang,Matt Feiszli,Ehsan Elhamifar,Lorenzo Torresani,Effrosyni Mavroudi

CVPR 2024（2024）

引用 5|浏览43

关键词

Egocentric Videos,Bounding Box,Video Clips,Multiple Objects,Object Segmentation,Contrastive Loss,Ground Objects,Video Dataset,Benchmark Evaluation,Negative Samples,Intersection Over Union,Object Classification,Manual Annotation,Self-supervised Learning,Class Instances,Masked Images,Noun Phrase,Dynamic Adjustment,Rest Of The Region,Global Objective,Affinity Score,Vision Transformer,Image Encoder,Text Encoder,Weak Supervision,Pixel-level Annotations,Transformer Layers,Matching Regions,Video Object,End Of The Text

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要