Subspace Clustering Based Tag Sharing for Inductive Tag Matrix Refinement with Complex Errors
arXiv:1601.03055
Abstract
Annotating images with tags is useful for indexing and retrieving images. However, many available annotation data include missing or inaccurate annotations. In this paper, we propose an image annotation framework which sequentially performs tag completion and refinement. We utilize the subspace property of data via sparse subspace clustering for tag completion. Then we propose a novel matrix completion model for tag refinement, integrating visual correlation, semantic correlation and the novelly studied property of complex errors. The proposed method outperforms the state-of-the-art approaches on multiple benchmark datasets even when they contain certain levels of annotation noise.
arXiv comment4 pages
References in corpus (8)
- Efficient Estimation of Word Representations in Vector Space
- Robust Recovery of Subspace Structures by Low-Rank Representation
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Linearized Alternating Direction Method with Adaptive Penalty for Low-Rank Representation
- Large-scale Multi-label Learning with Missing Labels
- Provable Inductive Matrix Completion
- Large Margin Nearest Neighbor Embedding for Knowledge Representation
- Jointly Embedding Relations and Mentions for Knowledge Population