Unsupervised Hashing with Semantic Concept Mining
Summary: UHSCM builds a semantic similarity matrix via VLP-based concept mining; concepts are denoised with prompts to capture semantics. A modified contrastive regularizer guided by this matrix boosts unsupervised image retrieval. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Rong-Cheng Tu
- 2. Xian-Ling Mao
- 3. Kevin Qinghong Lin
- 4. Chengfei Cai
- 5. Weize Qin
- 6. Wei Wei
- 7. Hongfa Wang
- 8. Heyan Huang
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 1 of 1 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 34 | Similarity Search in High Dimensions via Hashing | 1999 | VLDB | 0.00076637636 |
Previous
Page 1 / 1
Next