arxiv:2512.12678
Fatimah Zohra
zohraf
AI & ML interests
Image and Video Understanding, Vision-Text Alignment
Recent Activity
upvoted
a
paper
29 minutes ago
VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
authored
a paper
21 days ago
OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action
Detection
authored
a paper
21 days ago
$β$-CLIP: Text-Conditioned Contrastive Learning for Multi-Granular Vision-Language Alignment
Organizations
