TJUMMG
TJUMMG
Home
News
Publications
People
Teaching
Services
Awards
Research
Resources
Contact
Light
Dark
Automatic
Referring video segmentation
Sequence as A Whole: A Unified Framework for Video Action Localization with Long-Range Text Query
Comprehensive understanding of video content requires both spatial and temporal localization. However, there lacks a unified video action localization framework, which hinders the coordinated development of this field. Existing 3D CNN methods take …
Cite
×