Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

• Published in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 6077 - 6086
• Main Authors: Anderson, Peter, He, Xiaodong, Buehler, Chris, Teney, Damien, Johnson, Mark, Gould, Stephen, Zhang, Lei
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Context modeling; Mathematical model; Object detection; Proposals; Servers; Task analysis; Visualization

Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning. In this work, we propose a combined bottom-up and top-down attention mechan...