CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
Paper
•
2305.14014
•
Published
Shuai Zhao
mzhaoshuai
AI & ML interests
foundation models
Recent Activity
liked
a dataset
about 8 hours ago
cais/hle
upvoted
a
paper
29 days ago
Unified Video Editing with Temporal Reasoner
upvoted
a
collection
about 1 month ago
Embedding Model Datasets
Organizations
authored
5
papers
5 months ago
Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
Paper
•
2305.18010
•
Published
Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data
Paper
•
2504.09895
•
Published
•
1
Protecting Copyrighted Material with Unique Identifiers in Large Language Model Training
Paper
•
2403.15740
•
Published
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval
Paper
•
2205.00823
•
Published