Join us for Day 4 of AI Paper Reading Clubs!
đź—Ł Speaker: Syeda Aiman Mumtaz
(Women in Tech Lead at GDGOC CUI)
🔓 Paper Title: Learning Transferable Visual Models From Natural Language Supervision (CLIP)
🔍 Key Focus Areas:
- Shared vision–language embedding space for images and text without manual labels
- Dual encoder setup using ViT or ResNet for images and a Transformer for text
- Contrastive learning to align image–text pairs and separate large negative samples
- Zero shot classification using text prompts with no task specific retraining
- Cross modal retrieval and strong real world performance across OCR, action, and image retrieval
đź“… Date: 3rd January 2025
⏰ Time: 01:00 PM PKT
đź“Ť Venue: Live on YouTube
Discover how CLIP bridges vision and language, allowing models to generalize across tasks without retraining. A great session for anyone interested in multimodal AI, zero-shot learning, and foundation models.
📱 Stay connected with our WhatsApp Community for updates and future events:
https://chat.whatsapp.com/Lw0HRGerAYz6OTTo6ZBHlW
đź”— Follow us on our Social Media channels:
