Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                

"RaP: Redundancy-aware Video-language Pre-training for Text-Video Retrieval."

Xing Wu et al. (2022)

Details and statistics

DOI: 10.48550/ARXIV.2210.06881

access: open

type: Informal or Other Publication

metadata version: 2022-10-18