Rich Image Captioning in the Wild

Kenneth Tran, Xiaodong He, Lei Zhang, Jian Sun

Abstract: We present an image caption system that addresses new challenges of automatically describing images in the wild. The challenges include generating high quality caption with respect to human judgments, out-of-domain data handling, and low latency required in many applications. Built on top of a state-of-the-art framework, we developed a deep vision model that detects a broad range of visual concepts, an entity recognition model that identifies celebrities and landmarks, and a confidence model for the caption output. Experimental results show that our caption engine outperforms previous state-of-the-art systems significantly on both in-domain dataset (i.e. MS COCO) and out-of-domain datasets. We also make the system publicly accessible as a part of the Microsoft Cognitive Services.