arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.05103cs.CVcs.AIcs.CL
收藏

基于自注意力机制的多Transformers图像描述

Image Captioning using Multiple Transformers for Self-Attention Mechanism

Farrukh Olimov, Shikha Dubey, Labina Shrestha, Tran Trung Tin, Moongu Jeon

摘要:

实时图像描述,以及足够的精度,是这个研究领域的主要挑战。目前的工作,多个Transformers的自我注意力机制(MTSM),利用多个变压器来解决这些问题。所提出的算法,MTSM,获取区域的建议,使用Transformer检测器(DETR)。MTSM通过另一个Transformer来传递这些区域建议及其视觉和几何特征,并学习对象的局部和全局互连,从而实现自注意力机制。所提出的算法,MTSM,定性和定量的结果显示在MSCOCO数据集。

英文摘要:

Real-time image captioning, along with adequate precision, is the main challenge of this research field. The present work, Multiple Transformers for Self-Attention Mechanism (MTSM), utilizes multiple transformers to address these problems. The proposed algorithm, MTSM, acquires region proposals using a transformer detector (DETR). Consequently, MTSM achieves the self-attention mechanism by transferring these region proposals and their visual and geometrical features through another transformer and learns the objects' local and global interconnections. The qualitative and quantitative results of the proposed algorithm, MTSM, are shown on the MSCOCO 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。

↑