Close
Metadata

1. Identity statement
Reference TypeFilm or Video (Film or Broadcast)
Sitesibgrapi.sid.inpe.br
Identifier8JMKD3MGPEW34M/47QSKHH
Repositorysid.inpe.br/sibgrapi/2022/10.17.09.07
Last Update2022:10.17.09.07.31 (UTC) dioognei@gmail.com
Metadata Repositorysid.inpe.br/sibgrapi/2022/10.17.09.07.31
Metadata Last Update2022:10.27.13.02.50 (UTC) administrator
Citation KeyMatosNasc:2022:MuApAc
TitleMusical Hyperlapse: A Multimodal Approach to Accelerate First-Person Videos
Short TitleVideo
FormatOn-line
Year Released2022
Access Date2024, May 19
Number of Files1
Size389278 KiB
2. Context
Director1 Matos, Diognei
2 Nascimento, Erickson R.
Affiliation1 Federal University of Minas Gerais
2 Federal University of Minas Gerais
e-Mail Addressdioognei@gmail.com
Series TitleConference on Graphics, Patterns and Images, 35 (SIBGRAPI)
History (UTC)2022-10-17 09:07:31 :: dioognei@gmail.com -> administrator ::
2022-10-27 13:02:50 :: administrator -> dioognei@gmail.com :: 2022
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Keywordscomputer vision
music emotion recognition
image emotion recognition
semantic hyperlapse
SynopsisWith the advance in technology and social media usage, first-person recording videos has become a common habit. These videos are usually very long and tiring to watch, bringing the need to speed up them. Despite recent progress of fast-forward methods, they do not consider inserting background music in the videos, which could make them more enjoyable. This thesis presents a new method that creates accelerated videos and includes the background music keeping the same emotion induced by visual and acoustic modalities. Our approach is based on the automatic recognition of emotions induced by music and video contents and an optimization algorithm that maximizes the visual quality of the output video and seeks to match the similarity of the music and the video's emotions. Quantitative results show that our method achieves the best performance in matching emotion similarity while maintaining the visual quality of the output video compared with other literature methods. Visual results can be seen through the link: https://youtu.be/9ykQa9zhcz8.
Arrangement 1urlib.net > SDLA > Fonds > Video
Arrangement 2urlib.net > SDLA > Fonds > SIBGRAPI 2022 > Musical Hyperlapse: A Multimodal Approach to Accelerate First-Person Videos > Video
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 17/10/2022 06:07 2.0 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/47QSKHH
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/47QSKHH
Languageen
Target FileSupplementary Video.mp4
User Groupdioognei@gmail.com
Visibilityshown
Update Permissionnot transferred
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/46T9EHH
8JMKD3MGPEW34M/47QSJL5
Citing Item Listsid.inpe.br/sibgrapi/2022/05.18.20.13 4
sid.inpe.br/banon/2001/03.30.15.38.24 1
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
6. Notes
Empty Fieldsaccessionnumber alternatetitle archivingpolicy archivist area callnumber cast city contenttype copyholder copyright creatorhistory datereleased descriptionlevel dissemination distributor doi edition electronicmailaddress group holdercode isbn issn label lineage mark medium nextedition notes orcid parameterlist parentrepositories photographer previousedition previouslowerunit producer progress project readergroup readpermission resumeid rightsholder runningtime schedulinginformation secondarydate secondarykey secondarymark secondarytype seriesdirector session sponsor subject tertiarymark tertiarytype url versiontype
7. Description control
e-Mail (login)dioognei@gmail.com
update 


Close