Online weighted hashing for cross-modal retrieval
Online hashing algorithm that can process large-scaled multi-modal data in a streaming manner has a lot of attention recently. This work pursues further improvements using the weighted hamming distance, besides traditional label embedding learning and hash function learning. By learning different we...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/158323 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | Online hashing algorithm that can process large-scaled multi-modal data in a streaming manner has a lot of attention recently. This work pursues further improvements using the weighted hamming distance, besides traditional label embedding learning and hash function learning. By learning different weights on each bit of binary hash codes, it can preserve more semantic information and therefore becomes more accurate for retrieving similar data. |
|---|