scholarly journals Similarity-preserving hash for content-based audio retrieval using unsupervised deep neural networks

2021 ◽  
Vol 11 (1) ◽  
pp. 879
Author(s):  
Petcharat Panyapanuwat ◽  
Suwatchai Kamonsantiroj ◽  
Luepol Pipanmaekaporn
Keyword(s):  
Deep Neural Networks ◽  
Binary Codes ◽  
Search Performance ◽  
Linear Transformations ◽  
Compact Binary ◽  
Audio Retrieval ◽  
Musical Excerpts ◽  
Search Speed ◽  
Similarity Preserving ◽  
Effectiveness And Efficiency

Due to its efficiency in storage and search speed, binary hashing has become an attractive approach for a large audio database search. However, most existing hashing-based methods focus on data-independent scheme where random linear projections or some arithmetic expression are used to construct hash functions. Hence, the binary codes do not preserve the similarity and may degrade the search performance. In this paper, an unsupervised similarity-preserving hashing method for content-based audio retrieval is proposed. Different from data-independent hashing methods, we develop a deep network to learn compact binary codes from multiple hierarchical layers of nonlinear and linear transformations such that the similarity between samples is preserved. The independence and balance properties are included and optimized in the objective function to improve the codes. Experimental results on the Extended Ballroom dataset with 8 genres of 3,000 musical excerpts show that our proposed method significantly outperforms state-of-the-art data-independent method in both effectiveness and efficiency.

scholarly journals The effects of induced optical blur on visual search performance and training

2021 ◽  
pp. 174702182110502
Author(s):  
Azuwan Musa ◽  
Alison R Lane ◽  
Amanda Ellison
Keyword(s):  
Visual Acuity ◽  
Visual Search ◽  
Visual Field Loss ◽  
Search Performance ◽  
Searching Behaviour ◽  
Feature Search ◽  
Search Tasks ◽  
Search Speed ◽  
Search Training ◽  
Optical Blur

Visual search is a task often used in the rehabilitation of patients with cortical and non-cortical visual pathologies such as visual field loss. Reduced visual acuity is often comorbid with these disorders, and it remains poorly defined how low visual acuity may affect a patient’s ability to recover visual function through visual search training. The two experiments reported here investigated whether induced blurring of vision (from 6/15 to 6/60) in a neurotypical population differentially affected various types of feature search tasks, whether there is a minimal acceptable level of visual acuity required for normal search performance, and whether these factors affected the degree to which participants could improve with training. From the results, it can be seen that reducing visual acuity did reduce search speed, but only for tasks where the target was defined by shape or size (not colour), and only when acuity was worse than 6/15. Furthermore, searching behaviour was seen to improve with training in all three feature search tasks, irrespective of the degree of blurring that was induced. The improvement also generalised to a non-trained search task, indicating that an enhanced search strategy had been developed. These findings have important implications for the use of visual search as a rehabilitation aid for partial visual loss, indicating that individuals with even severe comorbid blurring should still be able to benefit from such training.

scholarly journals Scalable supervised online hashing for image retrieval

2021 ◽  
Vol 8 (5) ◽  
pp. 1391-1406
Author(s):  
Yuzhi Fang ◽  
Li Liu
Keyword(s):  
Data Streams ◽  
Data Stream ◽  
Superior Performance ◽  
Binary Codes ◽  
Retrieval Performance ◽  
Unified Framework ◽  
Retrieval Task ◽  
Compact Binary ◽  
Hash Codes ◽  
Existing Data

Abstract Online hashing methods aim to learn compact binary codes of the new data stream, and update the hash function to renew the codes of the existing data. However, the addition of new data streams has a vital impact on the retrieval performance of the entire retrieval system, especially the similarity measurement between new data streams and existing data, which has always been one of the focuses of online retrieval research. In this paper, we present a novel scalable supervised online hashing method, to solve the above problems within a unified framework. Specifically, the similarity matrix is established by the label matrix of the existing data and the new data stream. The projection of the existing data label matrix is then used as an intermediate term to approximate the binary codes of the existing data, which not only realizes the semantic information of the hash codes learning but also effectively alleviates the problem of data imbalance. In addition, an alternate optimization algorithm is proposed to efficiently make the solution of the model. Extensive experiments on three widely used datasets validate its superior performance over several state-of-the-art methods in terms of both accuracy and scalability for online retrieval task.

Sign in / Sign up

Export Citation Format

Share Document