研究人员正在开发新的无监督跨模态检索方法，旨在提高效率并减少对大型手动标注数据集的依赖。论文提出了属性提示核哈希（APKH）和全局邻域对齐哈希（GNAH）等技术，这些技术利用视觉语言基础模型和有限的配对数据来构建紧凑、对齐的汉明空间。另一种方法UniCA引入了双向交叉注意力和正相似性损失，以实现更鲁棒的多模态检索，并在WebQA+等基准测试中取得了改进。
AI
Unsupervised cross-modal hashing enables efficient retrieval of semantically related instances across different modalities without requiring manual semantic annotation. However, existing unsupervised methods rely heavily on large-scale image-text pairs. Collecting such data can b…
arXiv cs.AI
TIER_1English(EN)·Fan Xu, Luis A. Leiva·
arXiv:2506.08774v2 Announce Type: replace-cross Abstract: Different machine learning models can represent the same underlying concept in different ways. This variability is particularly valuable for in-the-wild multimodal retrieval, where the objective is to identify the correspo…
arXiv:2607.00379v1 Announce Type: cross Abstract: Unsupervised cross-modal hashing enables efficient retrieval of semantically related instances across different modalities without requiring manual semantic annotation. However, existing unsupervised methods rely heavily on large-…
arXiv cs.CV
TIER_1English(EN)·Zixu Zhao, Yang Zhan, Yunhao Li, Yan Li·
arXiv:2510.10180v2 Announce Type: replace Abstract: Unmanned aerial vehicles (UAVs) have become powerful platforms for real-time, high-resolution data collection, producing massive volumes of aerial videos. Efficient retrieval of relevant content from these videos is crucial for …
Compared to supervised cross-modal hashing (CMH), unsupervised CMH reduces the reliance on manual labeling by learning binary codes from unlabeled image-text pairs. However, existing unsupervised CMH methods often rely on large-scale image-text pairs, which are costly to collect.…
arXiv:2606.28350v1 Announce Type: cross Abstract: Multi-modal retrieval has become increasingly critical for handling the growing volume of integrated visual-textual data in real-world applications, but existing frameworks rely on implicit fusion via text encoder self-attention, …
