Audio-visual forgery detection method and device
The invention provides an audio-visual forgery detection method and device. The method comprises the following steps: acquiring video data to be detected; wherein the to-be-tested video data comprises at least two video frames, and each video frame comprises at least one group of audio-visual pairs...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | DUAN JUNXIAN LI JIA HE RAN LIU CHENYU HUANG HUAIBO |
| description | The invention provides an audio-visual forgery detection method and device. The method comprises the following steps: acquiring video data to be detected; wherein the to-be-tested video data comprises at least two video frames, and each video frame comprises at least one group of audio-visual pairs composed of face images and audio data; inputting each audio-visual pair into the trained double-flow network to obtain a counterfeit detection result of the to-be-detected video data; wherein the double-flow network comprises an image network branch, an audio network branch and a prediction network; the image network branch is used for extracting face key point features of the face image and extracting inter-frame consistency features of the face image based on the face key point features; the audio network branch is used for extracting audio features of the audio data and extracting time consistency features of the audio data based on the audio features; and the prediction network obtains a forgery detection resu |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN114596609A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN114596609A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN114596609A3</originalsourceid><addsrcrecordid>eNrjZDBwLE3JzNctyywuTcxRSMsvSk8tqlRISS1JTS7JzM9TyE0tychPUUjMSwEKlmUmp_IwsKYl5hSn8kJpbgZFN9cQZw_d1IL8-NTigsTk1LzUknhnP0NDE1NLMzMDS0djYtQAAGaGK10</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Audio-visual forgery detection method and device</title><source>esp@cenet</source><creator>DUAN JUNXIAN ; LI JIA ; HE RAN ; LIU CHENYU ; HUANG HUAIBO</creator><creatorcontrib>DUAN JUNXIAN ; LI JIA ; HE RAN ; LIU CHENYU ; HUANG HUAIBO</creatorcontrib><description>The invention provides an audio-visual forgery detection method and device. The method comprises the following steps: acquiring video data to be detected; wherein the to-be-tested video data comprises at least two video frames, and each video frame comprises at least one group of audio-visual pairs composed of face images and audio data; inputting each audio-visual pair into the trained double-flow network to obtain a counterfeit detection result of the to-be-detected video data; wherein the double-flow network comprises an image network branch, an audio network branch and a prediction network; the image network branch is used for extracting face key point features of the face image and extracting inter-frame consistency features of the face image based on the face key point features; the audio network branch is used for extracting audio features of the audio data and extracting time consistency features of the audio data based on the audio features; and the prediction network obtains a forgery detection resu</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; HANDLING RECORD CARRIERS ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2022</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220607&DB=EPODOC&CC=CN&NR=114596609A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,778,883,25551,76302</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220607&DB=EPODOC&CC=CN&NR=114596609A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>DUAN JUNXIAN</creatorcontrib><creatorcontrib>LI JIA</creatorcontrib><creatorcontrib>HE RAN</creatorcontrib><creatorcontrib>LIU CHENYU</creatorcontrib><creatorcontrib>HUANG HUAIBO</creatorcontrib><title>Audio-visual forgery detection method and device</title><description>The invention provides an audio-visual forgery detection method and device. The method comprises the following steps: acquiring video data to be detected; wherein the to-be-tested video data comprises at least two video frames, and each video frame comprises at least one group of audio-visual pairs composed of face images and audio data; inputting each audio-visual pair into the trained double-flow network to obtain a counterfeit detection result of the to-be-detected video data; wherein the double-flow network comprises an image network branch, an audio network branch and a prediction network; the image network branch is used for extracting face key point features of the face image and extracting inter-frame consistency features of the face image based on the face key point features; the audio network branch is used for extracting audio features of the audio data and extracting time consistency features of the audio data based on the audio features; and the prediction network obtains a forgery detection resu</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDBwLE3JzNctyywuTcxRSMsvSk8tqlRISS1JTS7JzM9TyE0tychPUUjMSwEKlmUmp_IwsKYl5hSn8kJpbgZFN9cQZw_d1IL8-NTigsTk1LzUknhnP0NDE1NLMzMDS0djYtQAAGaGK10</recordid><startdate>20220607</startdate><enddate>20220607</enddate><creator>DUAN JUNXIAN</creator><creator>LI JIA</creator><creator>HE RAN</creator><creator>LIU CHENYU</creator><creator>HUANG HUAIBO</creator><scope>EVB</scope></search><sort><creationdate>20220607</creationdate><title>Audio-visual forgery detection method and device</title><author>DUAN JUNXIAN ; LI JIA ; HE RAN ; LIU CHENYU ; HUANG HUAIBO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN114596609A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>DUAN JUNXIAN</creatorcontrib><creatorcontrib>LI JIA</creatorcontrib><creatorcontrib>HE RAN</creatorcontrib><creatorcontrib>LIU CHENYU</creatorcontrib><creatorcontrib>HUANG HUAIBO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>DUAN JUNXIAN</au><au>LI JIA</au><au>HE RAN</au><au>LIU CHENYU</au><au>HUANG HUAIBO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Audio-visual forgery detection method and device</title><date>2022-06-07</date><risdate>2022</risdate><abstract>The invention provides an audio-visual forgery detection method and device. The method comprises the following steps: acquiring video data to be detected; wherein the to-be-tested video data comprises at least two video frames, and each video frame comprises at least one group of audio-visual pairs composed of face images and audio data; inputting each audio-visual pair into the trained double-flow network to obtain a counterfeit detection result of the to-be-detected video data; wherein the double-flow network comprises an image network branch, an audio network branch and a prediction network; the image network branch is used for extracting face key point features of the face image and extracting inter-frame consistency features of the face image based on the face key point features; the audio network branch is used for extracting audio features of the audio data and extracting time consistency features of the audio data based on the audio features; and the prediction network obtains a forgery detection resu</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN114596609A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS |
| title | Audio-visual forgery detection method and device |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-16T04%3A19%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=DUAN%20JUNXIAN&rft.date=2022-06-07&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN114596609A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |