論文-《Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering 》重點翻譯+擴展

論文下載 摘要Abstract Top-down: Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grai
相關文章
相關標籤/搜索