Cite
Notes
Only stored in your browser.
Attribution
OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection
arXiv 2025
β-CLIP: Text-Conditioned Contrastive Learning for Multi-Granular Vision-Language Alignment
from 2 papers
Bernard Ghanem
Chen Zhao
Alejandro Pardo
Anthony Cioppa
Carlos Hinojosa
Hani Itani
Juan León Alcázar
Lama Alssum
Mattia Soldan
Mengmeng Xu