AIC-AB NET：一种结合空间注意力与文本属性的图像描述神经网络
AIC-AB NET: A Neural Network for Image Captioning with Spatial Attention and Text Attributes
AI总结：
提出 AIC-AB NET，在编码器—解码器中融合自适应空间注意力与同步文本属性，并在 MS COCO 和新建 Fashion 单目标数据集上验证其 CIDEr 性能优于基线及消融模型。
摘要：
图像描述是横跨计算机视觉与自然语言处理的重要领域。我们提出并展示了 AIC-AB NET，这是一种新颖的属性信息组合、基于注意力的网络，在编码器—解码器中结合了空间注意力架构与文本属性。在描述生成过程中，自适应空间注意力会确定哪个图像区域最能代表图像，并决定应关注视觉特征还是视觉哨兵。文本属性信息被同步输入解码器，以辅助图像识别并降低不确定性。我们在 MS COCO 数据集和一个新提出的 Fashion 数据集上测试并评估了 AIC-AB NET。Fashion 数据集被用作单目标图像的基准。结果表明，与最先进的基线模型及消融模型相比，所提模型在 MSCOCO 图像和我们的单目标图像上均具有优越性能。我们的 AIC-AB NET 在 MS COCO 数据集上比基线自适应注意力网络高出 0.017（CIDEr 分数），在 Fashion 数据集上高出 0.095（CIDEr 分数）。
英文摘要：
Image captioning is a significant field across computer vision and natural language processing. We propose and present AIC-AB NET, a novel Attribute-Information-Combined Attention-Based Network that combines spatial attention architecture and text attributes in an encoder-decoder. For caption generation, adaptive spatial attention determines which image region best represents the image and whether to attend to the visual features or the visual sentinel. Text attribute information is synchronously fed into the decoder to help image recognition and reduce uncertainty. We have tested and evaluated our AICAB NET on the MS COCO dataset and a new proposed Fashion dataset. The Fashion dataset is employed as a benchmark of single-object images. The results show the superior performance of the proposed model compared to the state-of-the-art baseline and ablated models on both the images from MSCOCO and our single-object images. Our AIC-AB NET outperforms the baseline adaptive attention network by 0.017 (CIDEr score) on the MS COCO dataset and 0.095 (CIDEr score) on the Fashion dataset.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
