Cite
Notes
Only stored in your browser.
Attribution
FLAIR: VLM with Fine-grained Language-informed Image Representations
CVPR 2025 1
EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval
arXiv 2024
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
from 3 papers
Zeynep Akata
Rui Xiao
Sanghwan Kim
Stephan Alaniz
Shyamgopal Karthik
Thomas Hummel