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

Citations Over TimeTop 1% of 2018 papers

Abstract

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 mechanism that enables attention to be calculated at the level of objects and other salient image regions. This is the natural basis for attention to be considered. Within our approach, the bottom-up mechanism (based on Faster R-CNN) proposes image regions, each with an associated feature vector, while the top-down mechanism determines feature weightings. Applying this approach to image captioning, our results on the MSCOCO test server establish a new state-of-the-art for the task, achieving CIDEr / SPICE / BLEU-4 scores of 117.9, 21.5 and 36.9, respectively. Demonstrating the broad applicability of the method, applying the same approach to VQA we obtain first place in the 2017 VQA Challenge.

Related Papers

• → OSCAR and ActivityNet: an Image Captioning model can effectively learn a Video Captioning dataset(2021)1 cited
• → Video Captioning via Hierarchical Reinforcement Learning(2017)22 cited
• → Boosted Attention: Leveraging Human Attention for Image Captioning(2019)1 cited
• → Image Captioning Methodologies Using Deep Learning: A Review(2020)
• → Image Captioning using Neural Networks(2022)