Two-stream convolutional neural network for multimodal matching

Multimodal representation learning: Advances, trends and challenges

SF Zhang, JH Zhai, BJ Xie, Y Zhan… - … on Machine Learning …, 2019 - ieeexplore.ieee.org
Representation learning is the base and crucial for consequential tasks, such as
classification, regression, and recognition. The goal of representation learning is to …
被引用次数：43 相关文章

Referring expression comprehension via co-attention and visual context

Y Gao, Y Ji, T Xu, Y Xu, C Liu - … Munich, Germany, September 17–19, 2019 …, 2019 - Springer
As a research hotspot of multimodal media analysis, referring expression comprehension
locates the referred object region in an image by mapping a natural language. Though the …
被引用次数：1 相关文章 所有 2 个版本