Código QR (código de barras bidimensional)

MVItem: A Benchmark for Multi-View Cross-Modal Item Retrieval

The existing text-image pre-training models have demonstrated strong generalization capabilities, however, their performance of item retrieval in real-world scenarios still falls short of expectations. In order to optimize the performance of text-image pre-training model to retrieve items in real sc...

Fuld beskrivelse

Na minha lista:
Principais autores: Bo Li, Jiansheng Zhu, Linlin Dai, Hui Jing, Zhizheng Huang, Yuteng Sui
Format: Artigo
Sprog:Inglês
Udgivet: IEEE 2024-01-01
Serier:IEEE Access
Fag:
Cross-model retrieval
deep learning
item retrieval
contrastive text-image pre-training model
multi-view
Online adgang:https://ieeexplore.ieee.org/document/10643520/
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!

Lignende værker