Show, attend and tell
Download as PPTX, PDF0 likes53 views
This document discusses neural image caption generation using attention mechanisms. It introduces image caption generators that previously lost information using high-level representations or needed powerful mechanisms when using low-level representations. It then describes using an encoder-decoder model with CNN and RNN, and explores two types of attention mechanisms: stochastic "hard" attention and deterministic "soft" attention to better generate image captions while preserving important information.
1 of 8
Download to read offline
Show, attend and tell
- 1. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention July 6, 2021 HeeDae Kwon
- 2. contents • Introduction • Image Caption Generation with Attention Mechanism • Stochastic “Hard” Attention • Deterministic “Soft” Attention
- 3. Introduction Image caption generator Previous Using representaion => losing impormation Using more low-level reprentation => preserve this informtaion , need a powerful mechanism
- 4. Introduction • incorporate a form of attention with "hard" , "soft"
- 5. Image Caption Generation with Attentio n Mechanism • Encoder (CNN) • Decoder (RNN)
- 8. • 감사합니다