2017 IEEE International Conference on Computer Vision (ICCV) (2017)
Oct. 22, 2017 to Oct. 29, 2017
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICCV.2017.140
We propose “Areas of Attention”, a novel attentionbased model for automatic image captioning. Our approach models the dependencies between image regions, caption words, and the state of an RNN language model, using three pairwise interactions. In contrast to previous attentionbased approaches that associate image regions only to the RNN state, our method allows a direct association between caption words and image regions. During training these associations are inferred from image-level captions, akin to weakly-supervised object detector training. These associations help to improve captioning by localizing the corresponding regions during testing. We also propose and compare different ways of generating attention areas: CNN activation grids, object proposals, and spatial transformers nets applied in a convolutional fashion. Spatial transformers give the best results. They allow for image specific attention areas, and can be trained jointly with the rest of the network. Our attention mechanism and spatial transformer attention areas together yield state-of-the-art results on the MSCOCO dataset.
image segmentation, inference mechanisms, natural language processing, object detection, recurrent neural nets
M. Pedersoli, T. Lucas, C. Schmid and J. Verbeek, "Areas of Attention for Image Captioning," 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2018, pp. 1251-1259.