Stack-VS : stacked visual-semantic attention for image caption generation

• Main Authors: Cheng, Ling, Wei, Wei, Mao, Xianling, Liu, Yong, Miao, Chunyan
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2021
• Subjects: Engineering::Computer science and engineering; Image Captioning; Recurrent Neural Network
• Online Access: https://hdl.handle.net/10356/148460
• Institution: Nanyang Technological University

Recently, automatic image caption generation has been an important focus of the work on multimodal translation task. Existing approaches can be roughly categorized into two classes, top-down and bottom-up, the former transfers the image information (called as visual-level feature) directly into a caption, and the later uses the extracted words (called as semantic-level attribute) to generate a description. However, previous methods either are typically based one-stage decoder or partially utilize part of visual-level or semantic-level information for image caption generation. In this paper, we address the problem and propose an innovative multi-stage architecture (called as Stack-VS) for rich fine-grained image caption generation, via combining bottom-up and top-down attention models to effectively handle both visual-level and semantic-level information of an input image. Specifically, we also propose a novel well-designed stack decoder model, which is constituted by a sequence of decoder cells, each of which contains two LSTM-layers work interactively to re-optimize attention weights on both visual-level feature vectors and semantic-level attribute embeddings for generating a fine-grained image caption. Extensive experiments on the popular benchmark dataset MSCOCO show the significant improvements on different evaluation metrics, i.e., the improvements on BLEU-4 / CIDEr / SPICE scores are 0.372, 1.226 and 0.216, respectively, as compared to the state-of-the-art.