Subject: [AUDITORY] AVA Active Speaker dataset now available From: Sourish Chaudhuri <0000007fde242bbe-dmarc-request@xxxxxxxx> Date: Fri, 11 Jan 2019 16:16:49 -0800 List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>--00000000000008f2fa057f37bb28 Content-Type: text/plain; charset="UTF-8" Hi Everyone, I'm happy to announce the release of a new dataset, AVA Active Speaker <http://research.google.com/ava/>, addressing the problem of identifying which, if any, of the visible faces in a video are speaking at any point in time. Labels are provided over continuous 15 minute segments of movies from v1.0 of the AVA dataset. The dataset creation process and our initial audiovisual models for this task are described in this arxiv paper <https://arxiv.org/abs/1901.01342>. The dataset is available on the AVA Download page <https://research.google.com/ava/download.html#ava_active_speaker_download>, along with details on the dataset format. Please use the ava-dataset-users Google group <https://groups.google.com/forum/#!forum/ava-dataset-users> for discussions and questions around the dataset, and please feel free to forward this note to relevant lists. Regards, Sourish Chaudhuri & the AVA team Google AI Perception <https://ai.google/research/teams/perception/> --00000000000008f2fa057f37bb28 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable <div dir=3D"ltr">Hi Everyone,<div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0= =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0I'm happy to announce the release of= a new=C2=A0<span class=3D"gmail-m_350168834708580306gmail-il">dataset</spa= n>,=C2=A0<a href=3D"http://research.google.com/ava/" target=3D"_blank">AVA= =C2=A0Active Speaker</a>,=C2=A0<span style=3D"color:rgb(0,0,0)">addressing = the problem of identifying which, if any, of the visible faces in a video a= re speaking at any point in time. Labels are provided over continuous 15 mi= nute segments of movies from v1.0 of the AVA dataset.</span></div><div><spa= n class=3D"gmail-m_350168834708580306gmail-il"><br></span></div><div><span = class=3D"gmail-m_350168834708580306gmail-il">=C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 The dataset creation process and = our initial audiovisual models for this task are described in=C2=A0<a href= =3D"https://arxiv.org/abs/1901.01342" target=3D"_blank">this arxiv paper</a= >.=C2=A0=C2=A0</span><span style=3D"font-size:12.8px">The=C2=A0</span><span= class=3D"gmail-m_350168834708580306gmail-il" style=3D"font-size:12.8px">da= taset</span><span style=3D"font-size:12.8px">=C2=A0is=C2=A0</span><span cla= ss=3D"gmail-m_350168834708580306gmail-il" style=3D"font-size:12.8px">availa= ble</span><span style=3D"font-size:12.8px">=C2=A0on the=C2=A0</span><a href= =3D"https://research.google.com/ava/download.html#ava_active_speaker_downlo= ad" target=3D"_blank" style=3D"font-size:12.8px"><span class=3D"gmail-m_350= 168834708580306gmail-il">AVA</span>=C2=A0Download page</a>, along with deta= ils on the dataset format<span style=3D"font-size:12.8px">.</span></div><di= v><br></div><div>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0=C2=A0<span style=3D"font-size:12.8px">Please use the=C2=A0</s= pan><a href=3D"https://groups.google.com/forum/#!forum/ava-dataset-users" t= arget=3D"_blank" style=3D"font-size:12.8px"><span class=3D"gmail-m_35016883= 4708580306gmail-il">ava</span>-<span class=3D"gmail-m_350168834708580306gma= il-il">dataset</span>-users Google group</a><span style=3D"font-size:12.8px= ">=C2=A0for discussions and questions around the=C2=A0</span><span class=3D= "gmail-m_350168834708580306gmail-il" style=3D"font-size:12.8px">dataset</sp= an><span style=3D"font-size:12.8px">, and please feel free to forward this = note to relevant lists.</span><br></div><div><span style=3D"font-size:12.8p= x"><br></span></div><div><span style=3D"font-size:12.8px">Regards,</span></= div><div><span style=3D"font-size:12.8px">=C2=A0Sourish Chaudhuri & the= AVA team</span></div><div><span style=3D"font-size:12.8px"><a href=3D"http= s://ai.google/research/teams/perception/" target=3D"_blank">Google AI Perce= ption</a></span></div></div> --00000000000008f2fa057f37bb28--