Self-supervised learning of visual features through embedding images into text topic spaces

Keyphrases

• Visual Features 100%
• Topic Space 100%
• Self-supervised Learning 100%
• Text Topic 100%
• Freely Available 33%
• Text Corpus 33%
• Computer Vision Problems 33%
• Image Classification 33%
• Deep Learning Architectures 33%
• ImageNet 33%
• Object Detection 33%
• Supervised Approach 33%
• Multimodal Images 33%
• Art Performance 33%
• Computer Vision Algorithms 33%
• Large Corpora 33%
• Topic Modeling 33%
• Semantic Structure 33%
• Multimodal Retrieval 33%
• Multimodal Texts 33%
• Multimodal Content 33%
• Semantic Context 33%
• Training from Scratch 33%
• Hidden Semantics 33%
• Human Supervision 33%

Computer Science

• Visual Feature 100%
• Self-Supervised Learning 100%
• Image Classification 33%
• Convolutional Neural Network 33%
• Art Performance 33%
• Deep Architecture 33%
• Object Detection 33%
• Computer Vision Algorithms 33%
• document image 33%
• Topic Modeling 33%
• Information Retrieval 33%
• Computer Vision 33%