Image-Text Matching with Multi-View Attention

arXiv:2402.17237v1 Announce Type: new
Abstract: Existing two-stream models for image-text matching show good performance while ensuring retrieval speed and have received extensive attention from industry and academia. These methods use a single representation to encode image and text separately and get a matching score with cosine similarity or the inner product of vectors. However, the performance of the two-stream model is often sub-optimal. On the one hand, a single representation is challenging to cover complex content comprehensively. On the other …

abstract academia arxiv attention cs.cl cs.cv encode good image industry performance product representation retrieval show speed text type vectors view