TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval
Paper
•
2104.08271
•
Published
Vlad Bogolin
vladbogo
AI & ML interests
LLMs, Computer Vision
Recent Activity
updated
a collection
about 13 hours ago
AI Paper of the Day
upvoted
a
paper
about 13 hours ago
Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits
updated
a collection
about 13 hours ago
AI Paper of the Day
Organizations
authored
5
papers
almost 2 years ago
Cross Modal Retrieval with Querybank Normalisation
Paper
•
2112.12777
•
Published
•
2
Unsupervised learning from video to detect foreground objects in single images
Paper
•
1703.10901
•
Published
Unsupervised learning of foreground object detection
Paper
•
1808.04593
•
Published
Mining for meaning: from vision to language through multiple networks consensus
Paper
•
1806.01954
•
Published