Image-text Retrieval via Preserving Main Semantics of Vision

1 code implementation • 20 Apr 2023 • Xu Zhang, Xinzheng Niu, Philippe Fournier-Viger, Xudong Dai

To address this issue, this paper presents a semantic optimization approach, implemented as a Visual Semantic Loss (VSL), to assist the model in focusing on an image's main content.

Cross-Modal Retrieval Retrieval +1