A Robust Feature Extraction Algorithm for Audio Fingerprinting

Chen, Jianping; Huang, Tiejun

doi:10.1007/978-3-540-89796-5_106

Cited by 13 publications

(3 citation statements)

References 8 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[51] extracted audio-visual features. They applied a BoW scheme on the local visual features (SIFT [35], SURF [5]) and a locality sensitive hashing (LSH) scheme on global visual features (DCT) and audio features (WASF [7]). A sequential pyramid matching (SPM) algorithm was devised to localize the similar video sequences.…”

Section: Filter-and-refine Matchingmentioning

confidence: 99%

Finding Near-Duplicate Videos in Large-Scale Collections

Kordopatis-Zilos

Papadopoulos

Patras

et al. 2019

Video Verification in the Fake News Era

View full text Add to dashboard Cite

This chapter discusses the problem of Near-Duplicate Video Retrieval (NDVR). The main objective of a typical NDVR approach is: given a query video, retrieve all near-duplicate videos in a video repository and rank them based on their similarity to the query. Several approaches have been introduced in the literature, which can be roughly classified in three categories based on the level of video matching, i.e. (i) video-level, (ii) frame-level and (iii) filter-and-refine matching. Two methods based on video-level matching are presented in this chapter. The first is an unsupervised scheme that relies on a modified Bag-of-Word (BoW) video representation. The second is a supervised method based on Deep Metric Learning (DML). For the development of both methods, features are extracted from the intermediate layers of Convolutional Neural Networks and leveraged as frame descriptors, since they offer a compact and informative image representation, and lead to increased system efficiency. Extensive evaluation has been conducted on publicly available benchmark datasets, and the presented methods are compared with state-of-art approaches, achieving the best results in all evaluation setups.

show abstract

Section: Filter-and-refine Matchingmentioning

confidence: 99%

Finding Near-Duplicate Videos in Large-Scale Collections

Kordopatis-Zilos

Papadopoulos

Patras

et al. 2019

Video Verification in the Fake News Era

View full text Add to dashboard Cite

show abstract

“…3) Audio feature: Weighted audio spectrum flatness (WASF) [9] is used to address audio transformations such as MP3 compression and multiband companding. WASF extends the MPEG-7 descriptor -audio spectrum flatness (ASF) [10] by introducing human auditory system (HAS) functions to weight audio spectrum, making the resulted feature more consistent with the outer ear and middle ear models of HAS.…”

Section: B Frame-level Retrievalmentioning

confidence: 99%

Video Copy Detection Using a Soft Cascade of Multimodal Features

Jiang

Huang

2012

2012 IEEE International Conference on Multimedia and Expo

Self Cite

View full text Add to dashboard Cite

In the video copy detection task, it is widely recognized that none of any single feature can work well for all transformations. Thus more and more approaches adopt a set of complementary features to cope with complex audiovisual transformations. However, most of them utilize individual features separately and the final result is obtained by fusing results of several basic detectors. Often, this will lead to low detection efficiency. Moreover, there are some thresholds or parameters to be elaborately tuned. To address these problems, we propose a soft cascade approach to integrate multiple features for efficient copy detection. In our approach, basic detectors are organized in a cascaded framework, which processes a query video in sequence until one detector asserts it as a copy. To fully exert the complementarity of these detectors, a learning algorithm is proposed to estimate the optimal decision thresholds in the cascade architecture. Excellent performance on the benchmark dataset of TRECVid 2011 CBCD task demonstrates the effectiveness and efficiency of our approach.

show abstract

“…So, 'M' feature vectors are integrated to compose a feature block for identification. This leads to increased number of fingerprints [8].…”

Section: Existing Techniquesmentioning

confidence: 99%

Fingerprint generation of audio signal using Difference of Gaussian

Kamaladhas¹,

Abitha²

2012

2012 International Conference on Devices, Circuits and Systems (ICDCS)

View full text Add to dashboard Cite

In the recent times, several audio search sites use audio fingerprinting technology which provides the ability to identify short and unlabeled audio clips in a rapid and reliable manner.However, if the number of fingerprints per audio file increases, the amount of query data for audio retrieval also increases. In this paper, therefore, a novel method is proposed that can reduce the number of fingerprints by using Difference of Gaussian and provide a degree of performance as same as that of the existing techniques. The proposed method uses Difference of Gaussian for feature extraction so that it is used effectively for audio retrieval even if the quality of the audio signal has been changed.

show abstract

A Robust Feature Extraction Algorithm for Audio Fingerprinting

Cited by 13 publications

References 8 publications

Finding Near-Duplicate Videos in Large-Scale Collections

Finding Near-Duplicate Videos in Large-Scale Collections

Video Copy Detection Using a Soft Cascade of Multimodal Features

Fingerprint generation of audio signal using Difference of Gaussian

Contact Info

Product

Resources

About