Hash Code Indexing in Cross-Modal Retrieval
Title | Hash Code Indexing in Cross-Modal Retrieval |
Publication Type | Conference Paper |
Year of Publication | 2019 |
Authors | Markchit, Sarawut, Chiu, Chih-Yi |
Conference Name | 2019 International Conference on Content-Based Multimedia Indexing (CBMI) |
Date Published | Sept. 2019 |
Publisher | IEEE |
ISBN Number | 978-1-7281-4673-7 |
Keywords | Artificial neural networks, Benchmark testing, binary code representation, Binary codes, binary hash codes, content-based retrieval, cross-modal hashing, cross-modal hashing algorithms, cross-modal retrieval, data representations, data structures, database indexing, Hamming codes, Hamming distance, Hamming distance computation, hash code indexing, index code representation, indexing, inverted indexing, Measurement, Metrics, multimedia databases, multimedia retrieval, nearest neighbor search, nearest neighbour methods, neural network training, pubcrawl, search problems, Two dimensional displays |
Abstract | Cross-modal hashing, which searches nearest neighbors across different modalities in the Hamming space, has become a popular technique to overcome the storage and computation barrier in multimedia retrieval recently. Although dozens of cross-modal hashing algorithms are proposed to yield compact binary code representation, applying exhaustive search in a large-scale dataset is impractical for the real-time purpose, and the Hamming distance computation suffers inaccurate results. In this paper, we propose a novel index scheme over binary hash codes in cross-modal retrieval. The proposed indexing scheme exploits a few binary bits of the hash code as the index code. Based on the index code representation, we construct an inverted index structure to accelerate the retrieval efficiency and train a neural network to improve the indexing accuracy. Experiments are performed on two benchmark datasets for retrieval across image and text modalities, where hash codes are generated by three cross-modal hashing methods. Results show the proposed method effectively boosts the performance over the benchmark datasets and hash methods. |
URL | https://ieeexplore.ieee.org/document/8877405 |
DOI | 10.1109/CBMI.2019.8877405 |
Citation Key | markchit_hash_2019 |
- Hamming distance computation
- Two dimensional displays
- search problems
- pubcrawl
- neural network training
- nearest neighbour methods
- nearest neighbor search
- multimedia retrieval
- multimedia databases
- Metrics
- Measurement
- inverted indexing
- indexing
- index code representation
- hash code indexing
- Artificial Neural Networks
- Hamming distance
- Hamming codes
- database indexing
- data structures
- data representations
- cross-modal retrieval
- cross-modal hashing algorithms
- cross-modal hashing
- content-based retrieval
- binary hash codes
- Binary codes
- binary code representation
- Benchmark testing