SOURCE-LINKED INTELLIGENCE

Aggregating Neighbor Embedding Projection and Rank-Based Manifold Learning for Image Retrieval

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Content-based image retrieval (CBIR) has advanced significantly with deep learning, yet effectively ranking similar images remains challenging, particularly in high-dimensional feature spaces, where pairwise distances often fail to capture contextual relationships and the semantic gap between visual features and high-level concepts persists. Manifold learning and rank-based refinement methods have emerged as complementary strategies, respectively improving feature representations and exploiting contextual information embedded in ranked lists, such as neighborhood relationships among images. Ho

Read original source ↗ Open in workspace

recordType

paper

region

Global