[AUDITORY] CFP: Workshop on Audio-Visual Scene Understanding for Immersive Multimedia @xxxxxxxx ACM Multimedia (Hansung Kim )

Subject: [AUDITORY] CFP: Workshop on Audio-Visual Scene Understanding for Immersive Multimedia @xxxxxxxx ACM Multimedia From: Hansung Kim <0000007072a27375-dmarc-request@xxxxxxxx> Date: Mon, 4 Jun 2018 11:12:41 +0000 List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY> --_000_AM0PR0602MB334650EB3D4FBC31EABB34F3D5670AM0PR0602MB3346_ Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable ACM MULTIMEDIA 2018 Workshop on Audio-Visual Scene Understanding for Immersive Multimedia http://cvssp.org/data/s3a/mmav2018/ 22-26 October 2018, Seoul, South Korea, in conjunction with ACM Multimedia = 2018 http://www.acmmm.org/2018/ Dates: Submission Due: July 8, 2018 (Now the submission system is open!) Acceptance Notification: August 5, 2018 Camera Ready Submission: August 12, 2018 Workshop Date: TBA (Oct 22 or 26, 2018) --------------------------------------------------------------------- Call for papers: Audio-visual data is the most familiar format of multimedia information acq= uired in our daily life. In most cases, they are already paired as audio-vi= deo streams in various fields and platforms such as media contents, surveil= lance data, communication, game, biomedical, education, etc. However, audio= and video processing have been researched in separate research areas for l= ong time ignoring their synergy when they work together. The goals of this workshop are to (1) present and discuss the latest trends= in audio and computer vision fields for the common research goals, (2) und= erstand state-of-the-art techniques and bottlenecks in the other's discipli= ne for the common topics, (3) investigate research opportunities of joint a= udio-visual scene understandings in multimedia content production. This workshop will be a good opportunity to bring together leading experts = in audio and vision, and bridge the gap between two research fields in mult= imedia content production and reproduction. We welcome research contributio= ns related the following (but not limited to) topics: - 3D audio-visual capture system - Object segmentation and audio source separation - Audio-Visual Tracking - Speaker identification and speech recognition - Scene understanding using audio-visual sensors - Deep learning for audio-visual data analysis - Geometry-aware auditory scene analysis - Virtual/Augmented reality content production - 360 video and spatial audio - Adaptive audio-visual content rendering All the submissions will be reviewed by the workshop's Steering Committee M= embers. Accepted papers will be presented during the workshop and included in the A= CM Workshop proceedings. --------------------------------------------------------------------- We look forward to your contributions. Adrian Hilton (University of Surrey, UK) Hong-Goo Kang (Yonsei University, = Republic of Korea) Hansung Kim (University of Surrey, UK) Kwanghoon Sohn (Y= onsei University, Republic of Korea) --_000_AM0PR0602MB334650EB3D4FBC31EABB34F3D5670AM0PR0602MB3346_ Content-Type: text/html; charset="us-ascii" Content-Transfer-Encoding: quoted-printable <html xmlns:v=3D"urn:schemas-microsoft-com:vml" xmlns:o=3D"urn:schemas-micr= osoft-com:office:office" xmlns:w=3D"urn:schemas-microsoft-com:office:word" = xmlns:m=3D"http://schemas.microsoft.com/office/2004/12/omml" xmlns=3D"http:= //www.w3.org/TR/REC-html40"> <head> <meta http-equiv=3D"Content-Type" content=3D"text/html; charset=3Dus-ascii"= > <meta name=3D"Generator" content=3D"Microsoft Word 15 (filtered medium)"> <style></style> </head> <body lang=3D"EN-GB" link=3D"blue" vlink=3D"purple"> <div class=3D"WordSection1"> ACM M= ULTIMEDIA 2018 Workshop<o:p></o:p> on Au= dio-Visual Scene Understanding for Immersive Multimedia<o:p></o:p></= p> <o:p> </o:p></= span> <a href=3D"http://c= vssp.org/data/s3a/mmav2018/">http://cvssp.org/data/s3a/mmav2018/</a><o:p></= o:p> <o:p> </o:p></= span> 22-26 October 2018,= Seoul, South Korea, in conjunction with ACM Multimedia 2018 <a href=3D"http://www.acmmm.org/2018/">http://www.acmmm.org/2018/</a><o:p><= /o:p> <o:p> </o:p></= span> Dates:<o:p></o:p></= span> Submission Due: Jul= y 8, 2018 (Now the submission system is open!)<o:p></o:p> Acceptance Notifica= tion: August 5, 2018<o:p></o:p> Camera Ready Submis= sion: August 12, 2018 <o:p></o:p> Workshop Date: TBA = (Oct 22 or 26, 2018)<o:p></o:p> <o:p> </o:p></= span> -------------------= --------------------------------------------------<o:p></o:p> <o:p> </o:p></= span> Call for papers:<o:= p></o:p> <o:p> </o:p></= span> Audio-visual data i= s the most familiar format of multimedia information acquired in our daily = life. In most cases, they are already paired as audio-video streams in vari= ous fields and platforms such as media contents, surveillance data, communication, game, biomedical, education, e= tc. However, audio and video processing have been researched in separate re= search areas for long time ignoring their synergy when they work together.<= o:p></o:p> <o:p> </o:p></= span> The goals of this w= orkshop are to (1) present and discuss the latest trends in audio and compu= ter vision fields for the common research goals, (2) understand state-of-th= e-art techniques and bottlenecks in the other’s discipline for the common topics, (3) investigate resear= ch opportunities of joint audio-visual scene understandings in multimedia c= ontent production.<o:p></o:p> <o:p> </o:p></= span> This workshop will = be a good opportunity to bring together leading experts in audio and vision= , and bridge the gap between two research fields in multimedia content prod= uction and reproduction. We welcome research contributions related the following (but not limited to) topics:<= o:p></o:p> <o:p> </o:p></= span> - 3D audio-visual c= apture system<o:p></o:p> - Object segmentati= on and audio source separation<o:p></o:p> - Audio-Visual Trac= king<o:p></o:p> - Speaker identific= ation and speech recognition<o:p></o:p> - Scene understandi= ng using audio-visual sensors<o:p></o:p> - Deep learning for= audio-visual data analysis<o:p></o:p> - Geometry-aware au= ditory scene analysis<o:p></o:p> - Virtual/Augmented= reality content production<o:p></o:p> - 360 video and spa= tial audio<o:p></o:p> - Adaptive audio-vi= sual content rendering<o:p></o:p> <o:p> </o:p></= span> <o:p> </o:p></= span> All the submissions= will be reviewed by the workshop’s Steering Committee Members.<o:p><= /o:p> <o:p> </o:p></= span> Accepted papers wil= l be presented during the workshop and included in the ACM Workshop proceed= ings. <o:p></o:p> <o:p> </o:p></= span> -------------------= --------------------------------------------------<o:p></o:p> <o:p> </o:p></= span> We look forward to = your contributions.<o:p></o:p> <o:p> </o:p></= span> Adrian Hilton (Univ= ersity of Surrey, UK) Hong-Goo Kang (Yonsei University, Republic of Korea) = Hansung Kim (University of Surrey, UK) Kwanghoon Sohn (Yonsei University, R= epublic of Korea)<o:p></o:p> <o:p> </o:p></= span> </div> </body> </html> --_000_AM0PR0602MB334650EB3D4FBC31EABB34F3D5670AM0PR0602MB3346_--

This message came from the mail archive
src/postings/2018/
maintained by:

DAn Ellis <dpwe@ee.columbia.edu>
Electrical Engineering Dept., Columbia University