2016/12/03 by Marco Pedersoli, Thomas Lucas, Pedersoli, Marco +6 · 2 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Artificial intelligence #Closed captioning #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Convolutional neural network #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Image (mathematics) #Language model #Machine learning #Multimodal Machine Learning Applications #Natural language processing #Pairwise comparison #Pattern recognition (psychology) #Transformer #cs.CV
paper · pdf · doi:10.48550/arxiv.1612.01033
published in arXiv (Cornell University) (Cornell University) · Accepted in ICCV 2017
openalex publication_date 2016/12/03 · arxiv created 2017/08/25 · arxiv updated 2017/08/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08
We propose "Areas of Attention", a novel attention-based 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 attention-based 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.o meaningful latent semantic structure in the generated captions.