no code implementations • 10 Oct 2022 • Sofia Nikiforova, Tejaswini Deoskar, Denis Paperno, Yoad Winter
Our approach includes a novel way of using image location to identify relevant open-domain facts in an external knowledge base, with their subsequent integration into the captioning pipeline at both the encoding and decoding stages.
no code implementations • COLING 2020 • Sofia Nikiforova, Tejaswini Deoskar, Denis Paperno, Yoad Winter
Standard image caption generation systems produce generic descriptions of images and do not utilize any contextual information or world knowledge.