CLIP Multi-modal Hashing For Multimedia Retrieval

Abstract

Multi-modal hashing methods are widely used in multimedia retrieval, which can fuse multi-source data to generate binary hash code. However, the individual backbone networks have limited feature expression capabilities and are not jointly pre-trained on large-scale unsupervised multi-modal data, resulting in low retrieval accuracy. To address this issue, we propose a novel CLIP Multi-modal Hashing (CLIPMH) method. Our method employs the CLIP framework to extract both text and vision features and then fuses them to generate hash code. Due to enhancement on each modal feature, our method has great improvement in the retrieval performance of multi-modal hashing methods. Compared with state-of-the-art unsupervised and supervised multi-modal hashing methods, experiments reveal that the proposed CLIPMH can significantly improve performance (a maximum increase of 8.38% in mAP).

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyzhu2024clip

Related papers

• CLIP Multi-modal Hashing: A New Baseline CLIPMH (2023)0.00
• Transitive Hashing Network For Heterogeneous Multimedia Retrieval (2016)8.35
• Adaptive Confidence Multi-view Hashing For Multimedia Retrieval (2023)9.95
• Adaptive Asymmetric Label-guided Hashing For Multimedia Search (2022)0.00
• Deep Semantic Multimodal Hashing Network For Scalable Image-text And Video-text Retrievals (2019)14.43
• Unsupervised Multi-modal Hashing For Cross-modal Retrieval (2019)8.35
• MOON: Multi-hash Codes Joint Learning For Cross-media Retrieval (2021)8.60
• Fusion-supervised Deep Cross-modal Hashing (2019)8.60