DEMO: A Statistical Perspective for Efficient Image-Text Matching

arXiv:2405.11496v1 Announce Type: new
Abstract: Image-text matching has been a long-standing problem, which seeks to connect vision and language through semantic understanding. Due to the capability to manage large-scale raw data, unsupervised hashing-based approaches have gained prominence recently. They typically construct a semantic similarity structure using the natural distance, which subsequently provides guidance to the model optimization process. However, the similarity structure could be biased at the boundaries of semantic distributions, causing error accumulation during sequential optimization. To tackle this, …

abstract arxiv capability construct cs.cv cs.ir data demo hashing image language natural perspective raw raw data scale semantic statistical text through type understanding unsupervised vision