BERT Can See Out of the Box

The video explores an interesting paper seeing how easily (w.r.t fine-tuning effort) pre-trained visual embeddings can be combined with text captions for visual question generation in the BERT model. This video explores the approach the authors take for this, applications of vision-language models, and question generation. Thanks for watching! Please Subscribe! Paper Links: BERT Can See Out of the Box: https://ift.tt/3ar15K1 BERT: https://ift.tt/2pMXn84 ImageBERT: https://ift.tt/398zzAe Training QA Models from Synthetic Data: https://ift.tt/2VB8nX9 AI2 BREAK: https://ift.tt/2PG7cSD Google Street View Panoramas for Language Grounding Tasks: https://ift.tt/2SYlgJj Google Open Images V6 with Localized Narratives: https://ift.tt/2SYlgJj Salesforce Learning Reasoning Paths: https://ift.tt/32pAB8N Thanks for Watching! Please Subscribe!